What is the difference between these three heavily related fields? Is there one specific whole they are all a part of (aside from CS)?
AI is the intellectual project of trying to capture all aspects of human intelligence in computers. A different project, also called AI, seeks to use human-inspired algorithms to approximate conventionally intractable problems. AI could be said to encompass such fields as robotics, planning, reasoning, learning, and natural language understanding.
Machine learning is the discipline which attempts to improve on a machine's performance of a task, given examples. It could be considered to be within AI's range of interests, but researchers in machine learning need have no intellectual stakes in AI's overall success. Machine learning has a close overlap with statistical physics and certain signal processing topics, and certain formulations strongly overlap planning, control theory, and dynamic programming.
Soft computing involves processes that involve indirect, approximate solutions instead of binary algorithms, widely considered to include such technologies as fuzzy logic, neural networks, and genetic algorithms. There is a broad overlap between these techniques and a certain planning and learning subset of AI, control theory, complex systems theory, etc.
Machine Learning could be considered a part of AI, however I would classify Machine Learning as the study of creation of semantic models and adaptive behavior with AI being the overall science of systems that intelligent-seeming behavior.
Most of what goes as "AI" is rather simplistic, but highly effective, such as heuristics and the like.
Soft Computing doesn't fell like it has many ML and AI components as it is more about analysis of complex systems. I could be wrong though. As with most things in computer science, the deeper you dig, the more you discover that it's all related.
Related
Is a neural network a lazy or eager learning method? Different web pages say different things so I want to get a solid answer with good literature to back it up. The most obvious book to look in would be Mitchell's famous Machine Learning book but skimming through the whole thing I can't see the answer. Thanks :).
Looking at the definition of the terms lazy and eager learning, and knowing how a neural network works, I believe that it is clear that it is eager. A trained network is a generalisation function, all the weights and paths used to arrive at a classification are entirely determined by training data, but the training data itself is not retained for the purposes of the decision making.
An important distinction is that a Lazy system stores its training data and uses it directly to determine a solution. An eager system determines a function from the training data, and thereafter the training data is no longer required. That is to say you cannot determine what the training data was from an eager system's function. A neural network certainly fits that description. An eager system can therfore be very storage efficient, but conversely is non-deterministic, in the sense that it is not possible to determine how or why it arrived a a particular solution, so problems of poor or inappropriate training data may be difficult deal with.
The eager article linked above even gives artificial neural networks as an example. You might of course prefer a cited text to Wikipedia but the page has existed with that assertion since 2007 without contradictory edits, so I'd say that was pretty robust.
Some neural networks are eager learners, and some are lazy. Feedforward neural networks (as are commonly trained by some variant of backpropagation) are eager: they attempt to derive a representation of the underlying relationships in the data at the time of training. Radial basis function networks (such as probabilistic NN or generalized regression NN), on the other hand, are lazy learners (very much like k-nearest neighbors, the classic lazy learner).
A neural network is generally considered to be an "eager" learning method.
"Eager" learning methods are models that learn from the training data in real-time, adjusting the model parameters as new examples are presented. Neural networks are an example of an eager learning method because the model parameters are updated during the training process, as the algorithm iteratively processes the training examples. This allows the model to adapt and improve its performance as more examples are seen.
On the other hand, "lazy" learning methods, also known as instance-based or memory-based learning, only learn from the training data when a new example is presented. The model does not update its parameters during the training process but instead, it memorizes the training data and uses it to make predictions. Lazy learning methods typically require less computation time to make predictions than eager learning methods, but they may not perform as well on unseen data.
In general, neural networks are considered eager learning methods because their parameters are updated during the training process.
Here are a few literature references:
"Eager Learning vs. Lazy Learning" by R. S. Michalski, J. G. Carbonell, and T. M. Mitchell. This paper provides a comprehensive overview of the distinction between eager and lazy learning, and discusses the strengths and weaknesses of each approach. It was published in Machine Learning, 1983.
"An overview of instance-based learning algorithms" by A. K. Jain and R. C. Dubes. This book chapter provides an overview of the main concepts and techniques used in instance-based or lazy learning, and compares them to other types of learning algorithms, such as decision trees and neural networks. It was published in "Algorithms for Clustering Data" by Prentice-Hall, Inc. in 1988.
" Machine Learning" by Tom Mitchell. This book provides a comprehensive introduction to the field of machine learning, including the concepts of eager and lazy learning. It covers a wide range of topics, from supervised and unsupervised learning to deep learning and reinforcement learning. It was published by McGraw-Hill Education in 1997.
"Introduction to Machine Learning" by Alpaydin, E. This book provides an introduction to the field of machine learning, including the concepts of eager and lazy learning, as well as a broad range of machine learning algorithms. It was published by MIT press in 2010
It's also worth noting, that this classification of lazy and eager learning is not always clear cut and can be somewhat subjective, and some algorithms can belong to both categories, depending on the specific implementation.
I'm starting to study machine learning and bayesian inference applied to computer vision and affective computing.
If I understand right, there is a big discussion between
classical IA, ontology, semantic web researchers
and machine learning and bayesian guys
I think it is usually referred as strong AI vs weak AI related also to philosophical issues like functional psychology (brain as black box set) and cognitive psychology (theory of mind, mirror neuron), but this is not the point in a programming forum like this.
I'd like to understand the differences between the two points of view. Ideally, answers will reference examples and academic papers where one approach get good results and the other fails. I am also interested in the historical trends: why approaches fell out of favour and a newer approaches began to rise up. For example, I know that Bayesian inference is computationally intractable, problem in NP, and that's why for a long time probabilistic models was not favoured in information technology world. However, they've began to rise up in econometrics.
I think you have got several ideas mixed up together. It's true that there is a distinction that gets drawn between rule-based and probabilistic approaches to 'AI' tasks, however it has nothing to do with strong or weak AI, very little to do with psychology and it's not nearly as clear cut as being a battle between two opposing sides. Also, I think saying Bayesian inference was not used in computer science because inference is NP complete in general is a bit misleading. That result often doesn't matter that much in practice and most machine learning algorithms don't do real Bayesian inference anyway.
Having said all that, the history of Natural Language Processing went from rule-based systems in the 80s and early 90s to machine learning systems up to the present day. Look at the history of the MUC conferences to see the early approaches to information extraction task. Compare that with the current state-of-the-art in named entity recognition and parsing (the ACL wiki is a good source for this) which are all based on machine learning methods.
As far as specific references, I doubt you'll find anyone writing an academic paper that says 'statistical systems are better than rule-based systems' because it's often very hard to make a definite statement like that. A quick Google for 'statistical vs. rule based' yields papers like this which looks at machine translation and recommends using both approaches, according to their strengths and weaknesses. I think you'll find that this is pretty typical of academic papers. The only thing I've read that really makes a stand on the issue is 'The Unreasonable Effectiveness of Data' which is a good read.
As for the "rule-based" vs. " probabilistic" thing you can go for the classic book by Judea Pearl - "Probabilistic Reasoning in Intelligent Systems. Pearl writes very biased towards what he calls "intensional systems" which is basically the counter-part to rule-based stuff. I think this book is what set off the whole probabilistic thing in AI (you can also argue the time was due, but then it was THE book of that time).
I think machine-learning is a different story (though it's nearer to probabilistic AI than to logics).
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
Has anyone worked with the programming language Church? Can anyone recommend practical applications? I just discovered it, and while it sounds like it addresses some long-standing problems in AI and machine-learning, I'm skeptical. I had never heard of it, and was surprised to find it's actually been around for a few years, having been announced in the paper Church: a language for generative models.
I'm not sure what to say about the matter of practical applications. Does modeling cognitive abilities with generative models constitute a "practical application" in your mind?
The key importance of Church (at least right now) is that it allows those of us working with probabilistic inference solutions to AI problems a simpler way to model. It's essentially a subset of Lisp.
I disagree with Chris S that it is at all a toy language. While some of these inference problems can be replicated in other languages (I've built several in Matlab) they generally aren't very reusable and you really have to love working in 4 and 5 for loops deep (I hate it).
Instead of tackling the problem that way, Church uses the recursive advantages of lamda calaculus and also allows for something called memoization which is really useful for generative models since your generative model is often not the same one trial after trial--though for testing you really need this.
I would say that if what you're doing has anything to do with Bayesian Networks, Hierarchical Bayesian Models, probabilistic solutions to POMDPs or Dynamic Bayesian Networks then I think Church is a great help. For what it's worth, I've worked with both Noah and Josh (two of Church's authors) and no one has a better handle on probabilistic inference right now (IMHO).
Church is part of the family of probabilistic programming languages that allows the separation of the estimation of a model from its definition. This makes probabilistic modeling and inference a lot more accessible to people that want to apply machine learning but who are not themselves hardcore machine learning researchers.
For a long time, probabilistic programming meant you'd have to come up with a model for your data and derive the estimation of the model yourself: you have some observed values, and you want to learn the parameters. The structure of the model is closely related to how you estimate the parameters, and you'd have to be pretty advanced knowledge of machine learning to do the computations correctly. The recent probabilistic programming languages are an attempt to address that and make things more accessible for data scientists or people doing work that applies machine learning.
As an analogy, consider the following:
You are a programmer and you want to run some code on a computer. Back in the 1970s, you had to write assembly language on punch cards and feed them into a mainframe (for which you had to book time on) in order to run your program. It is now 2014, and there are high-level, simple to learn languages that you can write code in even with no knowledge of how computer architecture works. It's still helpful to understand how computers work to write in those languages, but you don't have to, and many more people write code than if you had to program with punch cards.
Probabilistic programming languages do the same for machine learning with statistical models. Also, Church isn't the only choice for this. If you aren't a functional programming devotee, you can also check out the following frameworks for Bayesian inference in graphical models:
Infer.NET, written in C# by the Microsoft Research lab in Cambridge, UK
stan, written in C++ by the Statistics department at Columbia
You know what does a better job of describing Church than what I said? This MIT article: http://web.mit.edu/newsoffice/2010/ai-unification.html
It's slightly more hyperbolic, but then, I'm not immune to the optimism present in this article.
Likely, the article was intended to be published on April Fool's Day.
Here's another article dated late march of last year. http://dspace.mit.edu/handle/1721.1/44963
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..