30

First, I guess that you mean Common Lisp (which is a standard language specification, see its HyperSpec) with efficient implementations (à la SBCL). But some recent implementations of Scheme could also be relevant (with good implementations such as Bigloo or Chicken/Scheme). Both Common Lisp and Scheme (and even Clojure) are from the same Lisp family. And as ...


22

We are absolutely nowhere near, nor do we have any idea how to bridge the gap between what we can currently do and what is depicted in these films. The current trend for DL approaches (coupled with the emergence of data science as a mainstream discipline) has led to a lot of popular interest in AI. However, researchers and practitioners would do well to ...


15

David Nolen (contributor to Clojure and ClojureScript; creator of Core Logic a port of miniKanren) in a talk called LISP as too powerful stated that back in his days LISP was decades ahead of other programming languages. There are number of reasons why the language wasn't able to maintain it's name. This article highlights som key points why LISP is good ...


15

Your question is quite broad, but here are some tips: For feedforward networks, see this question: @doug's answer has worked for me. There's one additional rule of thumb that helps for supervised learning problems. The upper bound on the number of hidden neurons that won't result in over-fitting is: $$N_h = \frac{N_s} {(\alpha * (N_i + N_o))}$$...


11

There are some wonderful resources for keeping up to date in the ML community. Here are just a handful that a coworker showed me: Deep Learning Monitor: this site contains hot and new papers along with tweets that are popularized by the community! You can even checkout RL papers specifically here arxiv-sanity: this site updates with popular and new papers ...


9

In my opinion, this would be Phaeaco, which was developed by Harry Foundalis at Douglas Hofstadter's CRCC research group. It takes noisy photographic images of Bongard problems as input and (using a variant of Hofstadter's 'Fluid Concepts' architecture) successfully deduces the required rule in many cases. Hofstadter has described the related success of ...


9

Why in every aspect we are now considering artificial intelligence as a neural network? "We" aren't. It is generally due to reporting by media sources that simplify science and technology news. The definition of AI is somewhat fluid, and also contentious at times, but in research and scientific circles it has not changed to the degree that AI=NN. What has ...


9

In artificial intelligence (sometimes called machine intelligence or computational intelligence), there are several problems that are based on mathematical topics, especially optimization, statistics, probability theory, calculus and linear algebra. Marcus Hutter has worked on a mathematical theory for artificial general intelligence, called AIXI, which is ...


8

Alexander Kronrod once said, “Chess is the Drosophila of artificial intelligence”. John McCarthy disagrees with this statement. I think it's primarily because he has different vision.Techniques and Innovative methods developed to play these games have been found useful over the wide spectrum of Computer Science (and not just Artificial Intelligence). The ...


7

The authors do actually give an English definition in terms of the well-known agent formulation of AI: We intend this usage to be intuitive: death means that one sees no more percepts, and takes no more actions. It would seem that this becomes possible for a reinforcement learning agent such as AIXI in a formulation that uses semi-measures of ...


7

On the suggestion of the O.P. rcpinto I converted a comment about seeing "around a half-dozen papers that follow up on Graves et al.'s work which have produced results of the caliber" and will provide a few links. Keep in mind that this only answers the part of the question pertaining to NTMs, not Google DeepMind itself, plus I'm still learning the ropes in ...


7

Select the number of hidden layers and number of memory cells in LSTM is always depend on application domain and context where you want to apply this LSTM. For hidden Layers. The introduction of hidden layer(s) makes it possible for the network to exhibit non-linear behaviour. The optimal number of hidden units could easily be smaller than the number of ...


6

As per this site Researchers recorded the complex patterns of electrical activity generated by someone’s brain, as the subject listened to someone talking. By feeding those brainwave patterns into a computer, they were able to translate them back into actual words — the same words that the volunteer had been hearing. The scientists behind the work ...


6

OpenCog is an open source AGI project. But it is is also incredibly complex and IMHO not a good idea (I have not fully read his theories). You can learn the essential ideas behind OpenCog from the co-founder Ben Goertzel site as well. Or, you can participate in the philosophical discussion regarding AGI. For strictly AGI, decision theory, logic, and math ...


5

We are getting pretty good at image generation, some examples: Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised representation learning with deep convolutional generative adversarial networks." arXiv preprint arXiv:1511.06434 (2015). https://arxiv.org/pdf/1511.06434.pdf Gregor, Karol, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, and Daan ...


5

There is a small survey of continuous states, actions and time in reinforcement learning in my thesis proposal. Regarding books, Reinforcement Learning: State-of-the-Art seems to be pretty up-to-date from the excerpts I've read.


5

There has been previous research with promising results cited at length in the following recent article, and although they have limited training data, here is some impressive research for an undergraduate thesis at the University of Arkansas which extends that research using an artificial neural network on enhancing a classifying algorithm's capacity to ...


5

One popular technique for doing this is to use Artificial Immune Systems, an evolutionary computation approach which maintains a population of pattern detectors. Here is a survey paper.


5

Yes, many people have worked on this sort of thing, due to its obvious industrial applications (most of the ones I'm familiar with are in the pharmaceutical industry). Here's a paper from 2013 that claims good results; following the trail of papers that cited it will likely give you more recent work.


5

It's an interesting question about what makes humans unique. There is a good book on the subject titled What Computers Cant Do by Hubert Dreyfus. One task that a computer can't handle (for now at least) is ranking important things. For example, CAPTCHA asks you to order a random list of things (small one, five or six items) by importance. This particular ...


5

A method that could possibly work is utilising optical illusions such as one where two lines down a hallway are identical but one seems longer to the human eye, then they could be prompted with a multiple choice question as to the state of the line, which to our eyes looks longer, but to a computer, is still the same length of line. Of course, there is ...


5

The following survey article by researchers from IIT Bombay summarizes recent advances in sarcasm detection: Arxiv link. In reference to your question, I do not think it is considered either extraordinarily difficult or open-ended. While it does introduce ambiguity that computers cannot yet handle, Humans are easily able to understand sarcasm, and are thus ...


5

Will computers be able to understand user emotions? The term Understand is multidimensional, so characterizing the degree of understanding — emotional or otherwise — is a slippery task. Nonetheless, some forms of AI emotional understanding are possible. An Interesting Simple Case Even the embedded programs of velocity sensitive musical ...


5

I can only refer you to the wisdom contained in the Tao of Programming: A manager went to the Master Programmer and showed him the requirements document for a new application. The manager asked the Master: "How long will it take to design this system if I assign five programmers to it?" "It will take one year," said the Master promptly. "But we ...


4

I tend to think this question is border-line and may get close. A few comments for now, though. wrongx There are (at least) two issues with reproducing the work of a company like DeepMind: Technicalities missing from publications. Access to the same level of data. Technicalities should be workable. Some people have reproduced some of the Atari gaming ...


4

AI is a wide field that goes far beyond machine learning, deep learning, neural networks, etc. In some of these fields, the programming language does not matter at all (except for speed issues), so LISP would certainly not be a topic there. In search or AI planning, for instance, standard languages like C++ and Java are often the first choice, because they ...


4

This link includes various journals for artificial intelligence applied to various domains. Some of those are: 1. IEEE Transactions on Human-Machine Systems 2. Journal of the ACM 3. Knowledge-based systems 4. IEEE Transactions on Pattern Analysis and Machine Intelligence 5. Journal of Memory and Language. There are lots more. You can refer to any of those ...


4

A couple of others: Journal of Artificial Intelligence Research (JAIR) - http://jair.org IEEE Transactions on Knowledge and Data Engineering IEEE Computational Intelligence Magazine


4

This depends on your definition of human-like. If you mean a robot that looks and acts like a human, arguably, yes. Here's one of many examples: http://www.hansonrobotics.com/robot/sophia/ If you are looking for something that performs work and tasks, or works and thinks and talks like-or better than a human, the answer is mostly no, not yet. I recommend ...


4

High-level answer: Increase in resources has been important in AI, and definitely was a factor with Deep Blue, but Machine Learning is a newer method that seems to produces more optimal results with less resources on problems of greater complexity. Here is an article on AlphaGo's hardware: "Google reveals the mysterious custom hardware that powers AlphaGo"...


Only top voted, non community-wiki answers of a minimum length are eligible