Affiliation:
1. Mila, University of Montreal, Montreal, Quebec Canada
Abstract
A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopaedic list of heuristics). If that hypothesis was correct, we could more easily both understand our own intelligence and build intelligent machines. Just like in physics, the principles themselves would not be sufficient to predict the behaviour of complex systems like brains, and substantial computation might be needed to simulate human-like intelligence. This hypothesis would suggest that studying the kind of inductive biases that humans and animals exploit could help both clarify these principles and provide inspiration for AI research and neuroscience theories. Deep learning already exploits several key inductive biases, and this work considers a larger list, focusing on those which concern mostly higher-level and sequential conscious processing. The objective of clarifying these particular principles is that they could potentially help us build AI systems benefiting from humans’ abilities in terms of flexible out-of-distribution and systematic generalization, which is currently an area where a large gap exists between state-of-the-art machine learning and human intelligence.
Subject
General Physics and Astronomy,General Engineering,General Mathematics
Reference246 articles.
1. Deng J Dong W Socher R Li LJ Li K Fei-Fei L. 2009 Imagenet: a large-scale hierarchical image database. In 2009 IEEE Conf. on Computer Vision and Pattern Recognition pp. 248–255. IEEE.
2. Mnih V Kavukcuoglu K Silver D Graves A Antonoglou I Wierstra D Riedmiller M. 2013 Playing atari with deep reinforcement learning. (http://arxiv.org/abs/1312.5602)
3. Schrittwieser J et al. 2019 Mastering atari go chess and shogi by planning with a learned model. (http://arxiv.org/abs/1911.08265)
4. Do New Caledonian crows solve physical problems through causal reasoning?
5. Brown TB et al. 2020 Language models are few-shot learners. (http://arxiv.org/abs/2005.14165)
Cited by
65 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献