What do you use?
Fast Artificial Neural Network Library (FANN) is a free open source neural network library, which implements multilayer artificial neural networks in C with support for both fully connected and sparsely connected networks. Cross-platform execution in both fixed and floating point are supported. It includes a framework for easy handling of training data sets. It is easy to use, versatile, well documented, and fast. PHP, C++, .NET, Ada, Python, Delphi, Octave, Ruby, Prolog Pure Data and Mathematica bindings are available.
FannTool A graphical user interface is also available for the library.
There are a lot of different network simulators dependant on how detailed you want to do your sim, and what kind of network you want to simulate.
NEURON and GENESIS are good if you want to simulate full biological networks (Which I'm geussing you probably don't) even down to the behaviour of dendrites etc.
NEST and SPLIT and some others are good for doing population simulations where you create the population on a node-by-node basis and see what the whole population does. This is pretty much the 'industry' standard approach, and is used a lot in research and commercial applications, so there are worth looking into. I know that IBM use SPLIT for some of their research.
MIIND is good if you want to use differential equations to model what a population would do, but this approach is relatively new and computationally expensive (if very cool).
Not sure if that is exactly what you wanted!
(N.B. if you google any of the names in caps along with the word "simulator" you will end up at the relevant web page =)
Whenever I've wanted to play around with any data mining algorithm quickly, I just load up Weka. It's pretty complex but it implements a lot of algorithms (including neural networks) with a lot of customizability. Plus, it has some visualizations for NNs.
It is old, but I have always used NeuroShell 2 when not using my own code. Unfortunately, it is not free. I think The newer NeuroShells are designed only for predicting stocks.
If you're looking to experiment with deep learning, you should look into
Theano
Pylearn2 (which is based on Theano)
Related
I have built several domains and problems in PDDL and now I'm looking for a possibilty to visualize my domains, problems and solutions. My questions are as follows:
Are there any tools for a rather simple graphical representation of plans (e.g. nodes and connections)?
Are there tools that can display the current world state of my domain at any time (i.e. the value of all variables in my domain, after each step in my plan) in plain text?
How do I integrate PDDL in the system architecture? If I want to use a 2D or 3D representation of my world (e.g. Gazebo) how can i "connect" Gazebo and PDDL?
Thanks!
Going over your questions one by one:
None made publicly available, but I am aware of several students of members of the Planning community working in tools like that. I'd suggest you to make the question on this mailing list: planning-list#googlegroups.com
For that you'd need to modify one of the many existing planners and work it out yourself from their data structures or extend whatever debugging methods planners' authors have built into their systems. If you have the time and good C++ skills I'd suggest you to look into either Fast Downward (http://www.fast-downward.org/) or the less mature and simpler lwaptk (https://github.com/miquelramirez/lwaptk). If you are after some fast prototyping, and you are happy to compute the plans off-line, then I'd recommend you to look at Pyperplan (https://bitbucket.org/malte/pyperplan) a native Python planner which should quite easy to interface with pretty much anything (it just won't be very efficient when it comes to compute plans).
You'll have to work out yourself an interface between the model of your "Gazebo" world and the planning back-end, and the details depend on what a) what are you modeling in the "front-end" and b) what do you exactly want the planner to do for you. For an example of how to expose a relatively complex object model I'd suggest you to look at this little demo I put together a while back (https://github.com/miquelramirez/pr-as-planning-demo).
Read this link, it might be useful for you
https://www.ida.liu.se/~TDDD48/labs/2015/planners.en.shtml
I know that Artificial Intelligence field is very vast and there are many books on it. But i just want to know the any resource where i can get the simple inroduction to all Artificail Intelligence techniques like
It would like to have 1 or 2 page introduction of all techniques and their examples of how they can be applied or for what purpose they can be used. I am interested in
Backpropagation Algoritm
Hebbs Law
Bayesian networks
Markov Chain Models
Simulated Annealing
Tabu Search
Genetic Algorithms or Evolutionary Algos
Now there are many variants and more AI techniques. And each one have many books written on them. i am unable to decide which algos i can use unless i know what they are capable of doing.
So can i find 1-2 page inroduction of them with Application examples
Essentials of Metaheuristics covers several of these - I can't promise it'll cover all of them, but I know there's good stuff on simulated annealing and genetic algorithms in there. Probably at least a few of the others, but I'd have to re-download it to check. It's available for free download.
It can be a bit light on the theory, but it'll give you a straightforward description, some explanation of when you'd want to use each, and a lot of useful pseudocode.
Here's an image on local search (= tabu search without tabu) from the Drools Planner manual:
I am working on similar images for Greedy algorithms, brute force, branch and bound and simulated annealing.
As an example of Genetic Algorithms implementation I can give you this.
It's an API I developed for GA, with one implementation for each operator, and one concrete example problem solved ((good) Soccer Team among ~600 players with budget restriction). Its all setup so you run it with mvn exec:java and watch it evolving in the console output. But you can implement your own problem structure, or even other operators (crossing, mutating, selection) methods.
There are many papers about ranged combat artificial intelligences, like Killzones's (see this paper), or Halo. But I've not been able to find much about a fighting IA except for this work, which uses neural networs to learn how to fight, which is not exactly what I'm looking for.
Occidental AI in games is heavily focused on FPS, it seems! Does anyone know which techniques are used to implement a decent fighting AI? Hierarchical Finite State Machines? Decision Trees? They could end up being pretty predictable.
In our research labs, we are using AI planning technology for games. AI Planning is used by NASA to build semi-autonomous robots. Planning can produce less predictable behavior than state machines, but planning is a highly complex problem, that is, solving planning problems has a huge computational complexity.
AI Planning is an old but interesting field. Particularly for gaming only recently people have started using planning to run their engines. The expressiveness is still limited in the current implementations, but in theory the expressiveness is limited "only by our imagination".
Russel and Norvig have devoted 4 chapters on AI Planning in their book on Artificial Intelligence. Other related terms you might be interested in are: Markov Decision Processes, Bayesian Networks. These topics are also provided sufficient exposure in this book.
If you are looking for some ready-made engine to easily start using, I guess using AI Planning would be a gross overkill. I don't know of any AI Planning engine for games but we are developing one. If you are interested in the long term, we can talk separately about it.
You seem to know already the techniques for planning and executing. Another thing that you need to do is predict the opponent's next move and maximize the expected reward of your response. I wrote a blog article about this: http://www.masterbaboon.com/2009/05/my-ai-reads-your-mind-and-kicks-your-ass-part-2/ and http://www.masterbaboon.com/2009/09/my-ai-reads-your-mind-extensions-part-3/ . The game I consider is very simple, but I think the main ideas from Bayesian decision theory might be useful for your project.
I have reverse engineered the routines related to the AI subsystem within the Street Figher II series of games. It does not incorporate any of the techniques mentioned above. It is entirely reactive and involves no planning, learning or goals. Interestingly, there is no "technique weight" system that you mention, either. They don't use global weights for decisions to decide the frequency of attack versus block, for example. When taking apart the routines related to how "difficulty" is made to seem to increase, I did expect to find something like that. Alas, it relates to a number of smaller decisions that could potentially affect those ratios in an emergent way.
Another route to consider is the so called Ghost AI as described here & here. As the name suggests you basically extract rules from actual game play, first paper does it offline and the second extends the methodology for online real time learning.
Check out also the guy's webpage, there are a number of other papers on fighting games that are interesting.
http://www.ice.ci.ritsumei.ac.jp/~ftgaic/index-R.html
its old but here are some examples
Out of curiosity, I've been reading up a bit on the field of Machine Learning, and I'm surprised at the amount of computation and mathematics involved. One book I'm reading through uses advanced concepts such as Ring Theory and PDEs (note: the only thing I know about PDEs is that they use that funny looking character). This strikes me as odd considering that mathematics itself is a hard thing to "learn."
Are there any branches of Machine Learning that use different approaches?
I would think that a approaches relying more on logic, memory, construction of unfounded assumptions, and over-generalizations would be a better way to go, since that seems more like the way animals think. Animals don't (explicitly) calculate probabilities and statistics; at least as far as I know.
The behaviour of the neurons in our brains is very complex, and requires some heavy duty math to model. So, yes we do calculate extremely complex math, but it's done in a way that we don't perceive.
I don't know whether the math you typically find in A.I. research is entirely due to the complexity of the natural neural systems being modelled. It may also be due, in part, to heuristic techniques that don't even attempt to model the mind (e.g., using convolution filters to recognise shapes).
If you want to avoid the math but do AI like stuff, you can always stick to simpler models. In 90% of the time, the simpler models will be good enough for real world problems.
I don't know of a track of AI that is completely decoupled from math though. Probability theory is the tool for handling uncertainty which plays a major role in AI. So even if there was not-so-mathematical subfield, math techniques would most be a way to improve on those methods. And thus the mathematics would be back in game. Even simple techniques like the naive Bayes and decision trees can be used without a lot of math, but the real understanding comes only through it.
Machine learning is very math heavy. It is sometimes said to be close to "computational statistics", with a little more focus on the computational side. You might want to check out "Collective Intelligence" by O'Reilly, though. I hear they have a good collection of ML techniques without math too hard.
You might find evolutionary computing approaches to machine learning a little less front-loaded with heavy-duty maths, approaches such as ant-colony optimisation or swarm intelligence.
I think you should put to one side, if you hold it as your question kind of suggests you do, the view that machine learning is trying to simulate what goes on in the brains of animals (including Homo Sapiens). A lot of the maths in modern machine learning arises from its basis in pattern recognition and matching; some of it comes from attempts to represent what is learnt as quasi-mathematical statements; some of it comes from the need to use statistical methods to compare different algorithms and approaches. And some of it comes because some of the leading practitioners come from scientific and mathematical backgrounds rather than computer science backgrounds, and they bring their toolset with them when they come.
And I'm very surprised that you are suprised that machine learning involves a lot of computation since the long history of AI has proven that it is extremely difficult to build machines which (seem to) think.
I've been thinking about this kind of stuff a lot lately.
Unfortunately, most engineer/mathematician types are so tied to their own familiar mathematical/computational worlds, they often forget to consider other paradigms.
Artists, for example, often think of the world in a very fluid way, usually untethered by mathematical models. Much of what happens in art is archetypal or symbolic, and often doesn't follow any seemingly conventional logical arrangement. There are, of course, very strong exceptions to this. Music, for instance, especially in music theory, often requires strong left brained processes and so forth. In truth, I would argue that even the most right brained activities are not devoid of left logic, but rather are more complex mathematical paradigms, like chaos theory is to the beauty of fractals. So the cross-over from left to right and back again is not a schism, but a symbiotic coupling. Humans utilize both sides of the brain.
Lately I've been thinking about a more artful representational approach to math and machine language -- even in a banal world of ones and zeroes. The world has been thinking about machine language in terms of familiar mathematical, numeric, and alphabetic conventions for a fairly long time now, and it's not exactly easy to realign the cosmos. Yet in a way, it happens naturally. Wikis, wysisygs, drafting tools, photo and sound editors, blogging tools, and so forth, all these tools do the heavy mathematical and machine code lifting behind the scenes to make for a more artful end experience for the user.
But we rarely think of doing the same lifting for coders themselves. To be sure, code is symbolic, by its very nature, lingual. But I think it is possible to turn the whole thing on its head, and adopt a visual approach. What this would look like is anyone's guess, but in a way we see it everywhere as the whole world of machine learning is abstracted more and more over time. As machines become more and more complex and can do more and more sophisticated things, there is a basic necessity to abstract and simplify those very processes, for ease of use, design, architecture, development, and...you name it.
That all said, I do not believe machines will ever learn anything on their own without human input. But that is another debate, as to the character of religion, God, science, and the universe.
I attended a course in machine-learning last semester. The cognitive science chair at our university is very interested in symbolic machine learning (That's the stuff without mathematics or statistics ;o)). I can recommend two outstanding textbooks:
Machine Learning (Thomas Mitchell)
Artificial Intelligence: A Modern Approach (Russel and Norvig)
The first one is more focused on machine learning, but its very compact has got a very gentle learning curve. The second one is a very interesting read with many historical informations.
These two titles should give you a good overview (All aspects of machine learning not just symbolic approaches), so that you can decide for yourself which aspect you want to focus on.
Basically there is always mathematics involved but I find symbolic machine learning easier to start with because the ideas behind most approaches are often amazingly simple.
Mathematics is simply a tool in machine learning. Knowing the maths enables one to efficiently approach the modelled problems at hand. Of course it might be possible to brute force one's way through, but usually this would come with the expense of lessened understanding of the basic principles involved.
So, pick up a maths book, study the topics until it you're familiar with the concepts. No mechanical engineer is going to design a bridge without understanding the basic maths behind the system behaviour; why should this be any different in the area of machine learning?
There is a lot of stuff in Machine Learning, outside just the math..
You can build the most amazing probabilistic model using a ton of math, but fail because you aren't extracting the right features from the data (which might often require domain insight) or are having trouble figuring out what your model is failing on a particular dataset (which requires you to have a high-level understanding of what the data is giving, and what the model needs).
Without the math, you cannot build new complicated ML models by yourself, but you sure can play with existing tried-and-tested ones to analyze information and do cool things.
You still need some math knowledge to interpret the results the model gives you, but this is usually a lot easier than having to build these models on your own.
Try playing with http://www.cs.waikato.ac.nz/ml/weka/ and http://mallet.cs.umass.edu/ .. The former comes with all the standard ML algorithms along with a lot of amazing features that enable you to visualize your data and pre/post-process it to get good results.
Yes, machine learning research is now dominated by researchers trying to solve the classification problem: given positive/negative examples in an n-dimensional space, what is the best n-dimensional shape that captures the positive ones.
Another approach is taken by case-based reasoning (or case-based learning) where deduction is used alongside induction. The idea is that your program starts with a lot of knowledge about the world (say, it understands Newtonian physics) and then you show it some positive examples of the desired behavior (say, here is how the robot should kick the ball under these circumstances) then the program uses these together to extrapolate the desired behavior to all circumstances. Sort of...
firstly cased based AI, symbolic AI are all theories.. There are very few projects that have employed them in a sucessfull manner. Nowadays AI is Machine Learning. And even neural nets are also a core element in ML, which uses a gradient based optimization. U wanna do Machine learning, Linear Algebra, Optimization, etc is a must..
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
Welcome!
I very enjoyed programming artificial intelligence in my studies - neural networks, expert machines and other. But in work I develop mainly web applications.
And now I think about returning to such programming, maybe in hobby, or maybe in work. Are there areas where AI is commonly used in applications development and programmer with such skills can search work?
Or maybe I can sold some ideas to my boss and use AI to extend some of our applications.
What are you experience and ideas with using AI in applications?
I recently started reading the book Programming Collective Intelligence. It's an excellent book which discusses exactly what you are looking for - using AI techniques in web applications.
The book is written clearly, is easy to understand, explains everything in terms of real applications (it covers how some commonly used technology works: Google Pagerank, Amazons recommendation system, matchmaking websites, link recommendation systems, bayesian spam filters and more) and it uses actually useful examples using real data (ebay API, facebook API etc are used to collect data). In one chapter, it even explains how you can draw graphs (I mean the data structure, not bar/line/etc graphs) optimally (so that no nodes are too close together, minimum overlapping lines etc), which could be useful for, for example, mapping social networks.
I would recommend having a look at it and see the different ways AI can be applied to web applications.
As a counter-example, parsing data acquired from water testing equipment would probably be a bad place to use artificial intelligence:
The Daily WTF: No, We Need a Neural Network
Just a reminder for all of us to choose the right tool for the right job.
Neural networks are great for working on images, so one area of web applications you could use AI for would be identifying and/or manipulating patterns in images over large sets of data. For example, a site like Flickr or Facebook might have some interesting training material to identify people based on face or associating groupings of pixels (those being the features you work with) with certain items mentioned in captions or tags.
In terms of text manipulation, there's a lot of stuff, but it's usually icing on the cake for other web apps. I'm talking mostly in the areas of automatic completion in search bars and back-end things the user doesn't usually see, like automatic machine translation or improved search capability.
The problem with putting AI at the front of an application's offering is that usually, artificial intelligence is not a feature in and of itself, but rather a way of negotiating large data sets effectively without regular prompts from the designer. In general, a user will associate with an application on a one-to-one basis, and therefore judges it only on the quality of a relatively low number of responses.
Email spam filtering systems - definitely.
Any other security applications which need to spot patterns for malicious stuff.
You probably could analyze the behavior of the visitors of your web applications ; how do they navigate inside the website to provide a better, optimized interface. Now it depends on what kind of web applications you're working on. For on line shopping you can come with suggestions extrapolated from customers habits.
You can also detect "abnormal" behavior and fraud. Fraud and bot detection can take advantage of AI.
Forecasting, of course.
It has immense value for businesses (i.e.: inventory optimization) and is especially valuable in the time of global crisis.
Games do need AI.
Expert systems too.
Outside of games, I've seen very few commercial uses of AI.
It could, in theory, be very useful in industrial robotics and imaging, but those fields also tend to be very conservative, and uncomfortable with non-deterministic algorithms.
You might want to research what iRobot does, but even them use rather simple algorithms in their commercial robots.
In the area of cognitive architectures (e.g. Soar, ACT-R, etc), rather than concentrating on algorithms like A* and games, researchers investigate models of human behavior including decision-making, cultural interchange and learning. They often focus on cognitive plausibility, i.e. how close does a model track what a human would do, including timing, etc.
These systems tend to be strictly research-based with limited commercial applications. So far anyway. Military applications, especially for training, are fairly common though.
Image Processing for detecting cancer! (We actually code IEEE papers about it, creating the algoritms is way harder than coding them so we write papers about the performance of other papers)
Risk assessment is a pretty good case for neural networks, mostly because they're pretty good at pattern matching. Insurance and credit companies use them to some degree for determining the risk of a customer.
I have done some extensive research on using Artificial Neural Networks for classification of underwater sound sources. The algorithm seemed to work quite well, especially that I devoted a big portion of the work on figuring out what combination of fourier transform coefficient composed the best set for the classification (with Principal Component Analysis).
Anything (seriously):
http://highlevellogic.blogspot.com/2010/09/high-level-logic-rethinking-software.html
The High Level Logic (HLL) Open Source project is about finding and coding high level logic under which all the other AI (and in fact, all programming) fits. There are serious concrete ideas and code. HLL is already an application framework.