Related
This is a very difficult problem about how to maneuver a spaceship that can both translate and rotate in 3D, for a space game.
The spaceship has n jets placing in various positions and directions.
Transformation of i-th jet relative to the CM of spaceship is constant = Ti.
Transformation is a tuple of position and orientation (quaternion or matrix 3x3 or, less preferable, Euler angles).
A transformation can also be denoted by a single matrix 4x4.
In other words, all jet are glued to the ship and cannot rotate.
A jet can exert force to the spaceship only in direction of its axis (green).
As a result of glue, the axis rotated along with the spaceship.
All jets can exert force (vector,Fi) at a certain magnitude (scalar,fi) :
i-th jet can exert force (Fi= axis x fi) only within range min_i<= fi <=max_i.
Both min_i and max_i are constant with known value.
To be clear, unit of min_i,fi,max_i is Newton.
Ex. If the range doesn't cover 0, it means that the jet can't be turned off.
The spaceship's mass = m and inertia tensor = I.
The spaceship's current transformation = Tran0, velocity = V0, angularVelocity = W0.
The spaceship physic body follows well-known physic rules :-
Torque=r x F
F=ma
angularAcceleration = I^-1 x Torque
linearAcceleration = m^-1 x F
I is different for each direction, but for the sake of simplicity, it has the same value for every direction (sphere-like). Thus, I can be thought as a scalar instead of matrix 3x3.
Question
How to control all jets (all fi) to land the ship with position=0 and angle=0?
Math-like specification: Find function of fi(time) that take minimum time to reach position=(0,0,0), orient=identity with final angularVelocity and velocity = zero.
More specifically, what are names of technique or related algorithms to solve this problem?
My research (1 dimension)
If the universe is 1D (thus, no rotation), the problem will be easy to solve.
( Thank Gavin Lock, https://stackoverflow.com/a/40359322/3577745 )
First, find the value MIN_BURN=sum{min_i}/m and MAX_BURN=sum{max_i}/m.
Second, think in opposite way, assume that x=0 (position) and v=0 at t=0,
then create two parabolas with x''=MIN_BURN and x''=MAX_BURN.
(The 2nd derivative is assumed to be constant for a period of time, so it is parabola.)
The only remaining work is to join two parabolas together.
The red dash line is where them join.
In the period of time that x''=MAX_BURN, all fi=max_i.
In the period of time that x''=MIN_BURN, all fi=min_i.
It works really well for 1D, but in 3D, the problem is far more harder.
Note:
Just a rough guide pointing me to a correct direction is really appreciated.
I don't need a perfect AI, e.g. it can take a little more time than optimum.
I think about it for more than 1 week, still find no clue.
Other attempts / opinions
I don't think machine learning like neural network is appropriate for this case.
Boundary-constrained-least-square-optimisation may be useful but I don't know how to fit my two hyper-parabola to that form of problem.
This may be solved by using many iterations, but how?
I have searched NASA's website, but not find anything useful.
The feature may exist in "Space Engineer" game.
Commented by Logman: Knowledge in mechanical engineering may help.
Commented by AndyG: It is a motion planning problem with nonholonomic constraints. It could be solved by Rapidly exploring random tree (RRTs), theory around Lyapunov equation, and Linear quadratic regulator.
Commented by John Coleman: This seems more like optimal control than AI.
Edit: "Near-0 assumption" (optional)
In most case, AI (to be designed) run continuously (i.e. called every time-step).
Thus, with the AI's tuning, Tran0 is usually near-identity, V0 and W0 are usually not so different from 0, e.g. |Seta0|<30 degree,|W0|<5 degree per time-step .
I think that AI based on this assumption would work OK in most case. Although not perfect, it can be considered as a correct solution (I started to think that without this assumption, this question might be too hard).
I faintly feel that this assumption may enable some tricks that use some "linear"-approximation.
The 2nd Alternative Question - "Tune 12 Variables" (easier)
The above question might also be viewed as followed :-
I want to tune all six values and six values' (1st-derivative) to be 0, using lowest amount of time-steps.
Here is a table show a possible situation that AI can face:-
The Multiplier table stores inertia^-1 * r and mass^-1 from the original question.
The Multiplier and Range are constant.
Each timestep, the AI will be asked to pick a tuple of values fi that must be in the range [min_i,max_i] for every i+1-th jet.
Ex. From the table, AI can pick (f0=1,f1=0.1,f2=-1).
Then, the caller will use fi to multiply with the Multiplier table to get values''.
Px'' = f0*0.2+f1*0.0+f2*0.7
Py'' = f0*0.3-f1*0.9-f2*0.6
Pz'' = ....................
SetaX''= ....................
SetaY''= ....................
SetaZ''= f0*0.0+f1*0.0+f2*5.0
After that, the caller will update all values' with formula values' += values''.
Px' += Px''
.................
SetaZ' += SetaZ''
Finally, the caller will update all values with formula values += values'.
Px += Px'
.................
SetaZ += SetaZ'
AI will be asked only once for each time-step.
The objective of AI is to return tuples of fi (can be different for different time-step), to make Px,Py,Pz,SetaX,SetaY,SetaZ,Px',Py',Pz',SetaX',SetaY',SetaZ' = 0 (or very near),
by using least amount of time-steps as possible.
I hope providing another view of the problem will make it easier.
It is not the exact same problem, but I feel that a solution that can solve this version can bring me very close to the answer of the original question.
An answer for this alternate question can be very useful.
The 3rd Alternative Question - "Tune 6 Variables" (easiest)
This is a lossy simplified version of the previous alternative.
The only difference is that the world is now 2D, Fi is also 2D (x,y).
Thus I have to tune only Px,Py,SetaZ,Px',Py',SetaZ'=0, by using least amount of time-steps as possible.
An answer to this easiest alternative question can be considered useful.
I'll try to keep this short and sweet.
One approach that is often used to solve these problems in simulation is a Rapidly-Exploring Random Tree. To give at least a little credibility to my post, I'll admit I studied these, and motion planning was my research lab's area of expertise (probabilistic motion planning).
The canonical paper to read on these is Steven LaValle's Rapidly-exploring random trees: A new tool for path planning, and there have been a million papers published since that all improve on it in some way.
First I'll cover the most basic description of an RRT, and then I'll describe how it changes when you have dynamical constraints. I'll leave fiddling with it afterwards up to you:
Terminology
"Spaces"
The state of your spaceship can be described by its 3-dimension position (x, y, z) and its 3-dimensional rotation (alpha, beta, gamma) (I use those greek names because those are the Euler angles).
state space is all possible positions and rotations your spaceship can inhabit. Of course this is infinite.
collision space are all of the "invalid" states. i.e. realistically impossible positions. These are states where your spaceship is in collision with some obstacle (With other bodies this would also include collision with itself, for example planning for a length of chain). Abbreviated as C-Space.
free space is anything that is not collision space.
General Approach (no dynamics constraints)
For a body without dynamical constraints the approach is fairly straightforward:
Sample a state
Find nearest neighbors to that state
Attempt to plan a route between the neighbors and the state
I'll briefly discuss each step
Sampling a state
Sampling a state in the most basic case means choosing at random values for each entry in your state space. If we did this with your space ship, we'd randomly sample for x, y, z, alpha, beta, gamma across all of their possible values (uniform random sampling).
Of course way more of your space is obstacle space than free space typically (because you usually confine your object in question to some "environment" you want to move about inside of). So what is very common to do is to take the bounding cube of your environment and sample positions within it (x, y, z), and now we have a lot higher chance to sample in the free space.
In an RRT, you'll sample randomly most of the time. But with some probability you will actually choose your next sample to be your goal state (play with it, start with 0.05). This is because you need to periodically test to see if a path from start to goal is available.
Finding nearest neighbors to a sampled state
You chose some fixed integer > 0. Let's call that integer k. Your k nearest neighbors are nearby in state space. That means you have some distance metric that can tell you how far away states are from each other. The most basic distance metric is Euclidean distance, which only accounts for physical distance and doesn't care about rotational angles (because in the simplest case you can rotate 360 degrees in a single timestep).
Initially you'll only have your starting position, so it will be the only candidate in the nearest neighbor list.
Planning a route between states
This is called local planning. In a real-world scenario you know where you're going, and along the way you need to dodge other people and moving objects. We won't worry about those things here. In our planning world we assume the universe is static but for us.
What's most common is to assume some linear interpolation between the sampled state and its nearest neighbor. The neighbor (i.e. a node already in the tree) is moved along this linear interpolation bit by bit until it either reaches the sampled configuration, or it travels some maximum distance (recall your distance metric).
What's going on here is that your tree is growing towards the sample. When I say that you step "bit by bit" I mean you define some "delta" (a really small value) and move along the linear interpolation that much each timestep. At each point you check to see if you the new state is in collision with some obstacle. If you hit an obstacle, you keep the last valid configuration as part of the tree (don't forget to store the edge somehow!) So what you'll need for a local planner is:
Collision checking
how to "interpolate" between two states (for your problem you don't need to worry about this because we'll do something different).
A physics simulation for timestepping (Euler integration is quite common, but less stable than something like Runge-Kutta. Fortunately you already have a physics model!
Modification for dynamical constraints
Of course if we assume you can linearly interpolate between states, we'll violate the physics you've defined for your spaceship. So we modify the RRT as follows:
Instead of sampling random states, we sample random controls and apply said controls for a fixed time period (or until collision).
Before, when we sampled random states, what we were really doing was choosing a direction (in state space) to move. Now that we have constraints, we randomly sample our controls, which is effectively the same thing, except we're guaranteed not to violate our constraints.
After you apply your control for a fixed time interval (or until collision), you add a node to the tree, with the control stored on the edge. Your tree will grow very fast to explore the space. This control application replaces linear interpolation between tree states and sampled states.
Sampling the controls
You have n jets that individually have some min and max force they can apply. Sample within that min and max force for each jet.
Which node(s) do I apply my controls to?
Well you can choose at random, or your can bias the selection to choose nodes that are nearest to your goal state (need the distance metric). This biasing will try to grow nodes closer to the goal over time.
Now, with this approach, you're unlikely to exactly reach your goal, so you need to define some definition of "close enough". That is, you will use your distance metric to find nearest neighbors to your goal state, and then test them for "close enough". This "close enough" metric can be different than your distance metric, or not. If you're using Euclidean distance, but it's very important that you goal configuration is also rotated properly, then you may want to modify the "close enough" metric to look at angle differences.
What is "close enough" is entirely up to you. Also something for you to tune, and there are a million papers that try to get you a lot closer in the first place.
Conclusion
This random sampling may sound ridiculous, but your tree will grow to explore your free space very quickly. See some youtube videos on RRT for path planning. We can't guarantee something called "probabilistic completeness" with dynamical constraints, but it's usually "good enough". Sometimes it'll be possible that a solution does not exist, so you'll need to put some logic in there to stop growing the tree after a while (20,000 samples for example)
More Resources:
Start with these, and then start looking into their citations, and then start looking into who is citing them.
Kinodynamic RRT*
RRT-Connect
This is not an answer, but it's too long to place as a comment.
First of all, a real solution will involve both linear programming (for multivariate optimization with constraints that will be used in many of the substeps) as well as techniques used in trajectory optimization and/or control theory. This is a very complex problem and if you can solve it, you could have a job at any company of your choosing. The only thing that could make this problem worse would be friction (drag) effects or external body gravitation effects. A real solution would also ideally use Verlet integration or 4th order Runge Kutta, which offer improvements over the Euler integration you've implemented here.
Secondly, I believe your "2nd Alternative Version" of your question above has omitted the rotational influence on the positional displacement vector you add into the position at each timestep. While the jet axes all remain fixed relative to the frame of reference of the ship, they do not remain fixed relative to the global coordinate system you are using to land the ship (at global coordinate [0, 0, 0]). Therefore the [Px', Py', Pz'] vector (calculated from the ship's frame of reference) must undergo appropriate rotation in all 3 dimensions prior to being applied to the global position coordinates.
Thirdly, there are some implicit assumptions you failed to specify. For example, one dimension should be defined as the "landing depth" dimension and negative coordinate values should be prohibited (unless you accept a fiery crash). I developed a mockup model for this in which I assumed z dimension to be the landing dimension. This problem is very sensitive to initial state and the constraints placed on the jets. All of my attempts using your example initial conditions above failed to land. For example, in my mockup (without the 3d displacement vector rotation noted above), the jet constraints only allow for rotation in one direction on the z-axis. So if aZ becomes negative at any time (which is often the case) the ship is actually forced to complete another full rotation on that axis before it can even try to approach zero degrees again. Also, without the 3d displacement vector rotation, you will find that Px will only go negative using your example initial conditions and constraints, and the ship is forced to either crash or diverge farther and farther onto the negative x-axis as it attempts to maneuver. The only way to solve this is to truly incorporate rotation or allow for sufficient positive and negative jet forces.
However, even when I relaxed your min/max force constraints, I was unable to get my mockup to land successfully, demonstrating how complex planning will probably be required here. Unless it is possible to completely formulate this problem in linear programming space, I believe you will need to incorporate advanced planning or stochastic decision trees that are "smart" enough to continually use rotational methods to reorient the most flexible jets onto the currently most necessary axes.
Lastly, as I noted in the comments section, "On May 14, 2015, the source code for Space Engineers was made freely available on GitHub to the public." If you believe that game already contains this logic, that should be your starting place. However, I suspect you are bound to be disappointed. Most space game landing sequences simply take control of the ship and do not simulate "real" force vectors. Once you take control of a 3-d model, it is very easy to predetermine a 3d spline with rotation that will allow the ship to land softly and with perfect bearing at the predetermined time. Why would any game programmer go through this level of work for a landing sequence? This sort of logic could control ICBM missiles or planetary rover re-entry vehicles and it is simply overkill IMHO for a game (unless the very purpose of the game is to see if you can land a damaged spaceship with arbitrary jets and constraints without crashing).
I can introduce another technique into the mix of (awesome) answers proposed.
It lies more in AI, and provides close-to-optimal solutions. It's called Machine Learning, more specifically Q-Learning. It's surprisingly easy to implement but hard to get right.
The advantage is that the learning can be done offline, so the algorithm can then be super fast when used.
You could do the learning when the ship is built or when something happens to it (thruster destruction, large chunks torn away...).
Optimality
I observed you're looking for near-optimal solutions. Your method with parabolas is good for optimal control. What you did is this:
Observe the state of the system.
For every state (coming in too fast, too slow, heading away, closing in etc.) you devised an action (apply a strategy) that will bring the system into a state closer to the goal.
Repeat
This is pretty much intractable for a human in 3D (too many cases, will drive you nuts) however a machine may learn where to split the parabolas in every dimensions, and devise an optimal strategy by itself.
THe Q-learning works very similarly to us:
Observe the (secretized) state of the system
Select an action based on a strategy
If this action brought the system into a desirable state (closer to the goal), mark the action/initial state as more desirable
Repeat
Discretize your system's state.
For each state, have a map intialized quasi-randomly, which maps every state to an Action (this is the strategy). Also assign a desirability to each state (initially, zero everywhere and 1000000 to the target state (X=0, V=0).
Your state would be your 3 positions, 3 angles, 3translation speed, and three rotation speed.
Your actions can be any combination of thrusters
Training
Train the AI (offline phase):
Generate many diverse situations
Apply the strategy
Evaluate the new state
Let the algo (see links above) reinforce the selected strategies' desirability value.
Live usage in the game
After some time, a global strategy for navigation emerges. You then store it, and during your game loop you simply sample your strategy and apply it to each situation as they come up.
The strategy may still learn during this phase, but probably more slowly (because it happens real-time). (Btw, I dream of a game where the AI would learn from every user's feedback so we could collectively train it ^^)
Try this in a simple 1D problem, it devises a strategy remarkably quickly (a few seconds).
In 2D I believe excellent results could be obtained in an hour.
For 3D... You're looking at overnight computations. There's a few thing to try and accelerate the process:
Try to never 'forget' previous computations, and feed them as an initial 'best guess' strategy. Save it to a file!
You might drop some states (like ship roll maybe?) without losing much navigation optimality but increasing computation speed greatly. Maybe change referentials so the ship is always on the X-axis, this way you'll drop x&y dimensions!
States more frequently encountered will have a reliable and very optimal strategy. Maybe normalize the state to make your ship state always close to a 'standard' state?
Typically rotation speeds intervals may be bounded safely (you don't want a ship tumbling wildely, so the strategy will always be to "un-wind" that speed). Of course rotation angles are additionally bounded.
You can also probably discretize non-linearly the positions because farther away from the objective, precision won't affect the strategy much.
For these kind of problems there are two techniques available: bruteforce search and heuristics. Bruteforce means to recognize the problem as a blackbox with input and output parameters and the aim is to get the right input parameters for winning the game. To program such a bruteforce search, the gamephysics runs in a simulation loop (physics simulation) and via stochastic search (minimax, alpha-beta-prunning) every possibility is tried out. The disadvantage of bruteforce search is the high cpu consumption.
The other techniques utilizes knowledge about the game. Knowledge about motion primitives and about evaluation. This knowledge is programmed with normal computerlanguages like C++ or Java. The disadvantage of this idea is, that it is often difficult to grasp the knowledge.
The best practice for solving spaceship navigation is to combine both ideas into a hybrid system. For programming sourcecode for this concrete problem I estimate that nearly 2000 lines of code are necessary. These kind of problems are normaly done within huge projects with many programmers and takes about 6 months.
I have a simple task to classify people by their height and hair length to either MAN or WOMAN category using a neural network. Also teach it the pattern with some examples and then use it to classify on its own.
I have a basic understanding of neural networks but would really need some help here.
I know that each neuron divides the area to two subareas, basically that is why P = w0 + w1*x1 + w2*x2 + ... + wn*xn is being used here (weights are just moving the line if we consider geometric representation).
I do understand that each epoche should modify the weights to get closer to correct result, yet I have never program it and I am hopeless about how to start.
How should I proceed, meaning: How can I determine the threshold and how should I deal with the inputs?
It is not a homework rather than task for the ones who were interested. I am and I would like to understand it.
Looks like you are dealing with a simple Perceptron with a threshold activation function. Have a look at this question. Since you ARE using a bias neuron (w0), you would set the threshold to 0.
You then simply take the output of your network and compare it to 0, so you would e.g. output class 1 if x < 0 and class 2 if x > 0. You could model the case x=0 as "indistinct".
For learning the weights you need to apply the Delta Learning Rule which can be implemented very easily. But be careful: a perceptron with a simple threshold activation function can only be correct if your data are linearly separable. If you have more complex data you will need a Multilayer Perceptron and a nonlinear activation function like the Logistic Sigmoid Function.
Have a look at Geoffrey Hintons Coursera Course, Lecture 2 for details.
I've been working with machine learning lately (but I'm not an expert) but you should look at the Accord.NET framework. It contains all the common machine learning algorithme out of the box. So it's easy to take an existing samples and modify it instead of starting from scratch. Also, the developper of the framework is very helpful in the forum available on the same page.
With the available samples, you may also discover something better than neural network like the Kernel Support Vector Machine. If you stick to the neural network, have fun modifying all the different variables and by tryout and error you will understand how it work.
Have fun!
Since you said:
I know that each neuron divides the area to two subareas
&
weights are just moving the line if we consider geometric representation
I think you want to use perseptron or ADALINE neural networks. These neural networks can just classify linear separable patterns. since your input data is complicated, It's better to use a Multi layer Non-Linear Neural network. (my suggestion is a two layer neural network with tanh activation function) . For training these network you should use back propagation algorithm.
For answering to
how should I deal with the inputs?
I need to know more details about the inputs( Like: are they just height and hair length or there is more, what is their range and your resolution and etc.)
If you're dealing with just height and hair length I suggest that divide heights and length in some classes (for example 160cm-165cm, 165cm-170cm & etc.) and for each one of these classes set an On/Off input neuron. then put a hidden layer after all classes related to heights and another hidden layer after all classes related to hair length (tanh activation function). Number of neurons in these two hidden layer is determined based on number of training cases.
then take these two hidden layer output and send them to an aggregation layer with 1 output neuron.
Nominally a good problem to have, but I'm pretty sure it is because something funny is going on...
As context, I'm working on a problem in the facial expression/recognition space, so getting 100% accuracy seems incredibly implausible (not that it would be plausible in most applications...). I'm guessing there is either some consistent bias in the data set that it making it overly easy for an SVM to pull out the answer, =or=, more likely, I've done something wrong on the SVM side.
I'm looking for suggestions to help understand what is going on--is it me (=my usage of LibSVM)? Or is it the data?
The details:
About ~2500 labeled data vectors/instances (transformed video frames of individuals--<20 individual persons total), binary classification problem. ~900 features/instance. Unbalanced data set at about a 1:4 ratio.
Ran subset.py to separate the data into test (500 instances) and train (remaining).
Ran "svm-train -t 0 ". (Note: apparently no need for '-w1 1 -w-1 4'...)
Ran svm-predict on the test file. Accuracy=100%!
Things tried:
Checked about 10 times over that I'm not training & testing on the same data files, through some inadvertent command-line argument error
re-ran subset.py (even with -s 1) multiple times and did train/test only multiple different data sets (in case I randomly upon the most magical train/test pa
ran a simple diff-like check to confirm that the test file is not a subset of the training data
svm-scale on the data has no effect on accuracy (accuracy=100%). (Although the number of support vectors does drop from nSV=127, bSV=64 to nBSV=72, bSV=0.)
((weird)) using the default RBF kernel (vice linear -- i.e., removing '-t 0') results in accuracy going to garbage(?!)
(sanity check) running svm-predict using a model trained on a scaled data set against an unscaled data set results in accuracy = 80% (i.e., it always guesses the dominant class). This is strictly a sanity check to make sure that somehow svm-predict is nominally acting right on my machine.
Tentative conclusion?:
Something with the data is wacked--somehow, within the data set, there is a subtle, experimenter-driven effect that the SVM is picking up on.
(This doesn't, on first pass, explain why the RBF kernel gives garbage results, however.)
Would greatly appreciate any suggestions on a) how to fix my usage of LibSVM (if that is actually the problem) or b) determine what subtle experimenter-bias in the data LibSVM is picking up on.
Two other ideas:
Make sure you're not training and testing on the same data. This sounds kind of dumb, but in computer vision applications you should take care that: make sure you're not repeating data (say two frames of the same video fall on different folds), you're not training and testing on the same individual, etc. It is more subtle than it sounds.
Make sure you search for gamma and C parameters for the RBF kernel. There are good theoretical (asymptotic) results that justify that a linear classifier is just a degenerate RBF classifier. So you should just look for a good (C, gamma) pair.
Notwithstanding that the devil is in the details, here are three simple tests you could try:
Quickie (~2 minutes): Run the data through a decision tree algorithm. This is available in Matlab via classregtree, or you can load into R and use rpart. This could tell you if one or just a few features happen to give a perfect separation.
Not-so-quickie (~10-60 minutes, depending on your infrastructure): Iteratively split the features (i.e. from 900 to 2 sets of 450), train, and test. If one of the subsets gives you perfect classification, split it again. It would take fewer than 10 such splits to find out where the problem variables are. If it happens to "break" with many variables remaining (or even in the first split), select a different random subset of features, shave off fewer variables at a time, etc. It can't possibly need all 900 to split the data.
Deeper analysis (minutes to several hours): try permutations of labels. If you can permute all of them and still get perfect separation, you have some problem in your train/test setup. If you select increasingly larger subsets to permute (or, if going in the other direction, to leave static), you can see where you begin to lose separability. Alternatively, consider decreasing your training set size and if you get separability even with a very small training set, then something is weird.
Method #1 is fast & should be insightful. There are some other methods I could recommend, but #1 and #2 are easy and it would be odd if they don't give any insights.
I've read about neural network a little while ago and I understand how an ANN (especially a multilayer perceptron that learns via backpropagation) can learn to classify an event as true or false.
I think there are two ways :
1) You get one output neuron. It it's value is > 0.5 the events is likely true, if it's value is <=0.5 the event is likely to be false.
2) You get two output neurons, if the value of the first is > than the value of the second the event is likely true and vice versa.
In these case, the ANN tells you if an event is likely true or likely false. It does not tell how likely it is.
Is there a way to convert this value to some odds or to directly get odds out of the ANN. I'd like to get an output like "The event has a 84% probability to be true"
Once a NN has been trained, for eg. using backprogation as mentioned in the question (whereby the backprogation logic has "nudged" the weights in ways that minimize the error function) the weights associated with all individual inputs ("outside" inputs or intra-NN inputs) are fixed. The NN can then be used for classifying purposes.
Whereby the math (and the "options") during the learning phase can get a bit thick, it is relatively simple and straightfoward when operating as a classifier. The main algorithm is to compute an activation value for each neuron, as the sum of the input x weight for that neuron. This value is then fed to an activation function which purpose's is to normalize it and convert it to a boolean (in typical cases, as some networks do not have an all-or-nothing rule for some of their layers). The activation function can be more complex than you indicated, in particular it needn't be linear, but whatever its shape, typically sigmoid, it operate in the same fashion: figuring out where the activation fits on the curve, and if applicable, above or below a threshold. The basic algorithm then processes all neurons at a given layer before proceeding to the next.
With this in mind, the question of using the perceptron's ability to qualify its guess (or indeed guesses - plural) with a percentage value, finds an easy answer: you bet it can, its output(s) is real-valued (if anything in need of normalizing) before we convert it to a discrete value (a boolean or a category ID in the case of several categories), using the activation functions and the threshold/comparison methods described in the question.
So... How and Where do I get "my percentages"?... All depends on the NN implementation, and more importantly, the implementation dictates the type of normalization functions that can be used to bring activation values in the 0-1 range and in a fashion that the sum of all percentages "add up" to 1. In its simplest form, the activation function can be used to normalize the value and the weights of the input to the output layer can be used as factors to ensure the "add up" to 1 question (provided that these weights are indeed so normalized themselves).
Et voilà!
Claritication: (following Mathieu's note)
One doesn't need to change anything in the way the Neural Network itself works; the only thing needed is to somehow "hook into" the logic of output neurons to access the [real-valued] activation value they computed, or, possibly better, to access the real-valued output of the activation function, prior its boolean conversion (which is typically based on a threshold value or on some stochastic function).
In other words, the NN works as previously, neither its training nor recognition logic are altered, the inputs to the NN stay the same, as do the connections between various layers etc. We only get a copy of the real-valued activation of the neurons in the output layer, and we use this to compute a percentage. The actual formula for the percentage calculation depends on the nature of the activation value and its associated function (its scale, its range relative to other neurons' output etc.).
Here are a few simple cases (taken from the question's suggested output rules)
1) If there is a single output neuron: the ratio of the value provided by the activation function relative to the range of that function should do.
2) If there are two (or more output neurons), as with classifiers for example: If all output neurons have the same activation function, the percentage for a given neuron is that of its activation function value divided by the sum of all activation function values. If the activation functions vary, it becomes a case by case situation because the distinct activation functions may be indicative of a purposeful desire to give more weight to some of the neurons, and the percentage should respect this.
What you can do is to use a sigmoid transfer function on the output layer nodes (that accepts data ranges (-inf,inf) and outputs a value in [-1,1]).
Then by using the 1-of-n output encoding (one node for each class), you can map the range [-1,1] to [0,1] and use it as probability for each class value (note that this works naturally for more than just two classes).
The activation value of a single output neuron is a linearly weighted sum, and may be directly interpreted as an approximate probability if the network is trained to give outputs a range from 0 to 1. This would tend to be the case if the transfer function (or output function) in both the preceding stage and providing the final output is in the 0 to 1 range too (typically the sigmoidal logistic function). However, there is no guarantee that it will but repairs are possible. Moreover unless the sigmoids are logistic and the weights are constrained to be positive and sum to 1, it is unlikely. Generally a neural network will train in a more balanced way using the tanh sigmoid and weights and activations that range positive and negative (due to the symmetry of this model). Another factor is the prevalence of the class - if it is 50% then a 0.5 threshold is likely to be effective for logistic and a 0.0 threshold for tanh. The sigmoid is designed to push things towards the centre of the range (on backpropogation) and constrain it from going out of the range (in feedforward). The significance of the performance (with respect to the Bernoulli distribution) can also be interpreted as a probability that the neuron is making real predictions rather than guessing. Ideally the bias of the predictor to positives should match the prevalence of positives in the real world (which may vary at different times and places, e.g. bull vs bear markets, e.g. credit worthiness of people applying for loans vs people who fail to make loan payments) - calibrating to probabilities has the advantage that any desired bias can be set easily.
If you have two neurons for two classes, each can be interpreted independently as above, and the halved difference between them can also be. It is like flipping the negative class neuron and averaging. The differences can also give rise to a probability of significance estimate (using the T-test).
The Brier score and its Murphy decomposition give a more direct estimate of the probability that an average answer is correct, while Informedness gives the probability the classifier is making an informed decision rather than a guess, ROC AUC gives the probability a positive class will be ranked higher than a negative class (by a positive predictor), and Kappa will give a similar number that matches Informedness when prevalence = bias.
What you normally want is both a significance probability for the overall classifier (to ensure that you are playing on a real field, and not in an imaginary framework of guestimates) and a probability estimate for a specific example. There are various ways to calibrate, including doing a regression (linear or nonlinear) versus probability and using its inverse function to remap to a more accurate probability estimate. This can be seen by the Brier score improving, with the calibration component reducing towards 0, but the discrimination component remaining the same, as should ROC AUC and Informedness (Kappa is subject to bias and may worsen).
A simple non-linear way to calibrate to probabilities is to use the ROC curve - as the threshold changes for the output of a single neuron or the difference between two competing neurons, we plot the results true and false positive rates on a ROC curve (the false and true negative rates are naturally the complements, as what isn't really a positive is a negative). Then you scan the ROC curve (polyline) point by point (each time the gradient changes) sample by sample and the proportion of positive samples gives you a probability estimate for positives corresponding to the neural threshold that produced that point. Values between points on the curve can be linearly interpolated between those that are represented in the calibration set - and in fact any bad points in the ROC curve, represented by deconvexities (dents) can be smoothed over by the convex hull - probabilistically interpolating between the endpoints of the hull segment. Flach and Wu propose a technique that actually flips the segment, but this depends on information being used the wrong way round and although it could be used repeatedly for arbitrary improvement on the calibration set, it will be increasingly unlikely to generalize to a test situation.
(I came here looking for papers I'd seen ages ago on these ROC-based approaches - so this is from memory and without these lost references.)
I will be very prudent in interpreting the outputs of a neural networks (in fact any machine learning classifier) as a probability. The machine is trained to discriminate between classes, not to estimate the probability density. In fact, we don't have this information in the data, we have to infer it. For my experience I din't advice anyone to interpret directly the outputs as probabilities.
did you try prof. Hinton's suggestion of training the network with softmax activation function and cross entropy error?
as an example create a three layer network with the following:
linear neurons [ number of features ]
sigmoid neurons [ 3 x number of features ]
linear neurons [ number of classes ]
then train them with cross entropy error softmax transfer with your favourite optimizer stochastic descent/iprop plus/ grad descent. After training the output neurons should be normalized to sum of 1.
Please see http://en.wikipedia.org/wiki/Softmax_activation_function for details. Shark Machine Learning framework does provide Softmax feature through combining two models. And prof. Hinton an excellent online course # http://coursera.com regarding the details.
I can remember I saw an example of Neural network trained with back propagation to approximate the probability of an outcome in the book Introduction to the theory of neural computation (hertz krogh palmer). I think the key to the example was a special learning rule so that you didn't have to convert the output of a unit to probability, but instead you got automatically the probability as output.
If you have the opportunity, try to check that book.
(by the way, "boltzman machines", although less famous, are neural networks designed specifically to learn probability distributions, you may want to check them as well)
When using ANN for 2-class classification and logistic sigmoid activation function is used in the output layer, the output values could be interpreted as probabilities.
So if you choosing between 2 classes, you train using 1-of-C encoding, where 2 ANN outputs will have training values (1,0) and (0,1) for each of classes respectively.
To get probability of first class in percent, just multiply first ANN output to 100. To get probability of other class use the second output.
This could be generalized for multi-class classification using softmax activation function.
You can read more, including proofs of probabilistic interpretation here:
[1] Bishop, Christopher M. Neural networks for pattern recognition. Oxford university press, 1995.
I'm working with a couple of AI algorithms at school and I find people use the words Fuzzy Logic to explain any situation that they can solve with a couple of cases. When I go back to the books I just read about how instead of a state going from On to Off it's a diagonal line and something can be in both states but in different "levels".
I've read the wikipedia entry and a couple of tutorials and even programmed stuff that "uses fuzzy logic" (an edge detector and a 1-wheel self-controlled robot) and still I find it very confusing going from Theory to Code... for you, in the less complicated definition, what is fuzzy logic?
Fuzzy logic is logic where state membership is, essentially, a float with range 0..1 instead of an int 0 or 1. The mileage you get out of it is that things like, for example, the changes you make in a control system are somewhat naturally more fine-tuned than what you'd get with naive binary logic.
An example might be logic that throttles back system activity based on active TCP connections. Say you define "a little bit too many" TCP connections on your machine as 1000 and "a lot too many" as 2000. At any given time, your system has a "too many TCP connections" state from 0 (<= 1000) to 1 (>= 2000), which you can use as a coefficient in applying whatever throttling mechanisms you have available. This is much more forgiving and responsive to system behavior than naive binary logic that only knows how to determine "too many", and throttle completely, or "not too many", and not throttle at all.
I'd like to add to the answers (that have been modded up) that, a good way to visualize fuzzy logic is follows:
Traditionally, with binary logic you would have a graph whose membership function is true or false whereas in a fuzzy logic system, the membership function is not.
1|
| /\
| / \
| / \
0|/ \
------------
a b c d
Assume for a second that the function is "likes peanuts"
a. kinda likes peanuts
b. really likes peanuts
c. kinda likes peanuts
d. doesn't like peanuts
The function itself doesn't have to be triangular and often isn't (it's just easier with ascii art).
A fuzzy system will likely have many of these, some even overlapping (even opposites) like so:
1| A B
| /\ /\ A = Likes Peanuts
| / \/ \ B = Doesn't Like Peanuts
| / /\ \
0|/ / \ \
------------
a b c d
so now c is "kind likes peanuts, kinda doesn't like peanuts" and d is "really doesn't like peanuts"
And you can program accordingly based on that info.
Hope this helps for the visual learners out there.
The best definition of fuzzy logic is given by its inventor Lotfi Zadeh:
“Fuzzy logic means of representing problems to computers in a way akin to the way human solve them and the essence of fuzzy logic is that everything is a matter of degree.”
The meaning of solving problems with computers akin to the way human solve can easily be explained with a simple example from a basketball game; if a player wants to guard another player firstly he should consider how tall he is and how his playing skills are. Simply if the player that he wants to guard is tall and plays very slow relative to him then he will use his instinct to determine to consider if he should guard that player as there is an uncertainty for him. In this example the important point is the properties are relative to the player and there is a degree for the height and playing skill for the rival player. Fuzzy logic provides a deterministic way for this uncertain situation.
There are some steps to process the fuzzy logic (Figure-1). These steps are; firstly fuzzification where crisp inputs get converted to fuzzy inputs secondly these inputs get processed with fuzzy rules to create fuzzy output and lastly defuzzification which results with degree of result as in fuzzy logic there can be more than one result with different degrees.
Figure 1 – Fuzzy Process Steps (David M. Bourg P.192)
To exemplify the fuzzy process steps, the previous basketball game situation could be used. As mentioned in the example the rival player is tall with 1.87 meters which is quite tall relative to our player and can dribble with 3 m/s which is slow relative to our player. Addition to these data some rules are needed to consider which are called fuzzy rules such as;
if player is short but not fast then guard,
if player is fast but not short then don’t guard
If player is tall then don’t guard
If player is average tall and average fast guard
Figure 2 – how tall
Figure 3- how fast
According to the rules and the input data an output will be created by fuzzy system such as; the degree for guard is 0.7, degree for sometimes guard is 0.4 and never guard is 0.2.
Figure 4-output fuzzy sets
On the last step, defuzzication, is using for creating a crisp output which is a number which may determine the energy that we should use to guard the player during game. The centre of mass is a common method to create the output. On this phase the weights to calculate the mean point is totally depends on the implementation. On this application it is considered to give high weight to guard or not guard but low weight given to sometimes guard. (David M. Bourg, 2004)
Figure 5- fuzzy output (David M. Bourg P.204)
Output = [0.7 * (-10) + 0.4 * 1 + 0.2 * 10] / (0.7 + 0.4 + 0.2) ≈ -3.5
As a result fuzzy logic is using under uncertainty to make a decision and to find out the degree of decision. The problem of fuzzy logic is as the number of inputs increase the number of rules increase exponential.
For more information and its possible application in a game I wrote a little article check this out
To build off of chaos' answer, a formal logic is nothing but an inductively defined set that maps sentences to a valuation. At least, that's how a model theorist thinks of logic. In the case of a sentential boolean logic:
(basis clause) For all A, v(A) in {0,1}
(iterative) For the following connectives,
v(!A) = 1 - v(A)
v(A & B) = min{v(A), v(B)}
v(A | B) = max{v(A), v(B)}
(closure) All sentences in a boolean sentential logic are evaluated per above.
A fuzzy logic changes would be inductively defined:
(basis clause) For all A, v(A) between [0,1]
(iterative) For the following connectives,
v(!A) = 1 - v(A)
v(A & B) = min{v(A), v(B)}
v(A | B) = max{v(A), v(B)}
(closure) All sentences in a fuzzy sentential logic are evaluated per above.
Notice the only difference in the underlying logic is the permission to evaluate a sentence as having the "truth value" of 0.5. An important question for a fuzzy logic model is the threshold that counts for truth satisfaction. This is to ask: for a valuation v(A), for what value D it is the case the v(A) > D means that A is satisfied.
If you really want to found out more about non-classical logics like fuzzy logic, I would recommend either An Introduction to Non-Classical Logic: From If to Is or Possibilities and Paradox
Putting my coder hat back on, I would be careful with the use of fuzzy logic in real world programming, because of the tendency for a fuzzy logic to be undecidable. Maybe it's too much complexity for little gain. For instance a supervaluational logic may do just fine to help a program model vagueness. Or maybe probability would be good enough. In short, I need to be convinced that the domain model dovetails with a fuzzy logic.
Maybe an example clears up what the benefits can be:
Let's say you want to make a thermostat and you want it to be 24 degrees.
This is how you'd implement it using boolean logic:
Rule1: heat up at full power when
it's colder than 21 degrees.
Rule2:
cool down at full power when it's
warmer than 27 degrees.
Such a system will only once and a while be 24 degrees, and it will be very inefficient.
Now, using fuzzy logic, it would be like something like this:
Rule1: For each degree that it's colder than 24 degrees, turn up the heater one notch (0 at 24).
Rule2: For each degree that it's warmer than 24 degress, turn up the cooler one notch (0 at 24).
This system will always be somewhere around 24 degrees, and it only once and will only once and a while make a tiny adjustment. It will also be more energy-efficient.
Well, you could read the works of Bart Kosko, one of the 'founding fathers'. 'Fuzzy Thinking: The New Science of Fuzzy Logic' from 1994 is readable (and available quite cheaply secondhand via Amazon). Apparently, he has a newer book 'Noise' from 2006 which is also quite approachable.
Basically though (in my paraphrase - not having read the first of those books for several years now), fuzzy logic is about how to deal with the world where something is perhaps 10% cool, 50% warm, and 10% hot, where different decisions may be made on the degree to which the different states are true (and no, it wasn't entirely an accident that those percentages don't add up to 100% - though I'd accept correction if needed).
A very good explanation, with a help of Fuzzy Logic Washing Machines.
I know what you mean about it being difficult to go from concept to code. I'm writing a scoring system that looks at the values of sysinfo and /proc on Linux systems and comes up with a number between 0 and 10, 10 being the absolute worst. A simple example:
You have 3 load averages (1, 5, 15 minute) with (at least) three possible states, good, getting bad, bad. Expanding that, you could have six possible states per average, adding 'about to' to the three that I just noted. Yet, the result of all 18 possibilities can only deduct 1 from the score. Repeat that with swap consumed, actual VM allocated (committed) memory and other stuff .. and you have one big bowl of conditional spaghetti :)
Its as much a definition as it is an art, how you implement the decision making process is always more interesting than the paradigm itself .. whereas in a boolean world, its rather cut and dry.
It would be very easy for me to say if load1 < 2 deduct 1, but not very accurate at all.
If you can teach a program to do what you would do when evaluating some set of circumstances and keep the code readable, you have implemented a good example of fuzzy logic.
Fuzzy Logic is a problem-solving methodology that lends itself to implementation in systems ranging from simple, small, embedded micro-controllers to large, networked, multi-channel PC or workstation-based data acquisition and control systems. It can be implemented in hardware, software, or a combination of both. Fuzzy Logic provides a simple way to arrive at a definite conclusion based upon vague, ambiguous, imprecise, noisy, or missing input information. Fuzzy Logic approach to control problems mimics how a person would make decisions, only much faster.
Fuzzy logic has proved to be particularly useful in expert system and other artificial intelligence applications. It is also used in some spell checkers to suggest a list of probable words to replace a misspelled one.
To learn more, just check out: http://en.wikipedia.org/wiki/Fuzzy_logic.
The following is sort of an empirical answer.
A simple (possibly simplistic answer) is that "fuzzy logic" is any logic that returns values other than straight true / false, or 1 / 0. There are a lot of variations on this and they tend to be highly domain specific.
For example, in my previous life I did search engines that used "content similarity searching" as opposed to then common "boolean search". Our similarity system used the Cosine Coefficient of weighted-attribute vectors representing the query and the documents and produced values in the range 0..1. Users would supply "relevance feedback" which was used to shift the query vector in the direction of desirable documents. This is somewhat related to the training done in certain AI systems where the logic gets "rewarded" or "punished" for results of trial runs.
Right now Netflix is running a competition to find a better suggestion algorithm for their company. See http://www.netflixprize.com/. Effectively all of the algorithms could be characterized as "fuzzy logic"
Fuzzy logic is calculating algorithm based on human like way of thinking. It is particularly useful when there is a large number of input variables. One online fuzzy logic calculator for two variables input is given:
http://www.cirvirlab.com/simulation/fuzzy_logic_calculator.php