Goto

Collaborating Authors

Results


Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

arXiv.org Artificial Intelligence

Deep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans may still be difficult for neural models. Humans possess the ability to extrapolate reasoning strategies learned on simple problems to solve harder examples, often by thinking for longer. For example, a person who has learned to solve small mazes can easily extend the very same search techniques to solve much larger mazes by spending more time. In computers, this behavior is often achieved through the use of algorithms, which scale to arbitrarily hard problem instances at the cost of more computation. In contrast, the sequential computing budget of feed-forward neural networks is limited by their depth, and networks trained on simple problems have no way of extending their reasoning to accommodate harder problems. In this work, we show that recurrent networks trained to solve simple problems with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference. We demonstrate this algorithmic behavior of recurrent networks on prefix sum computation, mazes, and chess. In all three domains, networks trained on simple problem instances are able to extend their reasoning abilities at test time simply by "thinking for longer."


114 Milestones In The History Of Artificial Intelligence (AI)

#artificialintelligence

In an expanded edition published in 1988, they responded to claims that their 1969 conclusions significantly reduced funding for neural network research: "Our version is that progress had already come to a virtual halt because of the lack of adequate basic theories… by the mid-1960s there had been a great many experiments with perceptrons, but no one had been able to explain why they were able to recognize certain kinds of patterns and not others."


114 Milestones In The History Of Artificial Intelligence (AI)

#artificialintelligence

In an expanded edition published in 1988, they responded to claims that their 1969 conclusions significantly reduced funding for neural network research: "Our version is that progress had already come to a virtual halt because of the lack of adequate basic theories… by the mid-1960s there had been a great many experiments with perceptrons, but no one had been able to explain why they were able to recognize certain kinds of patterns and not others."


The relationship between Biological and Artificial Intelligence

#artificialintelligence

Intelligence can be defined as a predominantly human ability to accomplish tasks that are generally hard for computers and animals. Artificial Intelligence [AI] is a field attempting to accomplish such tasks with computers. AI is becoming increasingly widespread, as are claims of its relationship with Biological Intelligence. Often these claims are made to imply higher chances of a given technology succeeding, working on the assumption that AI systems which mimic the mechanisms of Biological Intelligence should be more successful. In this article I will discuss the similarities and differences between AI and the extent of our knowledge about the mechanisms of intelligence in biology, especially within humans. I will also explore the validity of the assumption that biomimicry in AI systems aids their advancement, and I will argue that existing similarity to biological systems in the way Artificial Neural Networks [ANNs] tackle tasks is due to design decisions, rather than inherent similarity of underlying mechanisms. This article is aimed at people who understand the basics of AI (especially ANNs), and would like to be better able to evaluate the often wild claims about the value of biomimicry in AI. Symbolic AI was the prevailing approach to AI until the early 90's. It is reliant on human programmers coding complex rules to enable machines to complete complex tasks. Continuing failure of this approach to solve many tasks crucial to intelligence provides a good contrast with Machine Learning -- an alternative approach to AI which is essential to the current advent of artificially intelligent machines. In 1994 the reigning chess champion Garry Kasparov was beaten by Deep Blue.


AI Insider: What is AI and How Does AI Works?

#artificialintelligence

Ai is everywhere, it has incorporated into every aspect of our life, unknowingly. It changed the way we live by simplifying things we do in our routine, like shopping, traveling, man-machine interaction. AI almost gained control of our actions. It decides what we shop, by showing ads and recommendations while you are shopping, AI trip advisors suggest you a travel destination and the best vacation packages for your budget. AI helping Businesses and financial institutions to serve their customers better with the automated question and answer chatbots. AI also defines our social media feeds, how many of your Facebook friends have not been showing up on your wall, even they active in social media? Because AI knows what and who you are interested in.


Humans Versus Artificial Intelligence

#artificialintelligence

The complexity of the human brain, in relation to that of other species, is one of the biggest wonders in science. Today, neural networks compete alongside us with processing powers that can calculate 200 million potential outcomes per second. With the data trail we feed into it as we go through our lives, and the vast data sets scientists are training machines on, they are learning to compete with the greatest human minds at our own games. In this story we explore how humans compare with machines in games, healthcare, art and emotional intelligence. AlphaGo, DeepMind's Go playing AI, has been dubbed "The AI that has nothing to learn from humans". Go is a complex strategy game over 3000 years old, with 10170 different board configurations.


Derived metrics for the game of Go -- intrinsic network strength assessment and cheat-detection

arXiv.org Artificial Intelligence

The widespread availability of superhuman AI engines is changing how we play the ancient game of Go. The open-source software packages developed after the AlphaGo series shifted focus from producing strong playing entities to providing tools for analyzing games. Here we describe two ways of how the innovations of the second generation engines (e.g.~score estimates, variable komi) can be used for defining new metrics that help deepen our understanding of the game. First, we study how much information the search component contributes in addition to the raw neural network policy output. This gives an intrinsic strength measurement for the neural network. Second, we define the effect of a move by the difference in score estimates. This gives a fine-grained, move-by-move performance evaluation of a player. We use this in combating the new challenge of detecting online cheating.


Difference between artificial and human intelligence may be smaller than you think

#artificialintelligence

Artificial intelligence (AI) has made spectacular progress in the last two decades. Computers can now diagnose medical images, predict customer behaviour, manage financial portfolios, compose poetry, and even generate art. The AI can do some of these things better than humans. As AI marches furiously towards becoming increasingly smart systems, an old philosophical question has returned to haunt us: Is human intelligence qualitatively different from artificial intelligence, or are their differences only quantitative? The revolution in AI is primarily powered by a class of algorithms called artificial neural networks.


GPT-3 Creative Fiction

#artificialintelligence

What if I told a story here, how would that story start?" Thus, the summarization prompt: "My second grader asked me what this passage means: …" When a given prompt isn't working and GPT-3 keeps pivoting into other modes of completion, that may mean that one hasn't constrained it enough by imitating a correct output, and one needs to go further; writing the first few words or sentence of the target output may be necessary.


Understanding Artificial Intelligence

#artificialintelligence

Jul 19 · 9 min read Artificial Intelligence (AI) is such a buzz word these days and one thing about buzz words is… 'They often get lost in translation'. But I think it's time we all take a deep breath, exhale, pause… And realize that AI is a well-founded discipline in its own right. Machine Learning and Deep Learning do not define Artificial Intelligence. AI is a much broader field than ML, which is a Statistical subset of AI and DL, which is a specialized subset of ML involving Neural networks computation… ML and DL are Subsets of a much broader field called AI… So what exactly is Artificial Intelligence? To answer this question we must consider the four historical approaches to AI.