A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding — mentioned by pinouchon

Thu, 02 Feb 2017 12:26:14 GMT

I agree that in practise, deep learning tend to perform very well. With that said, it is not without limitations. In general, model-based machine learning approaches do not perform as well, but we should not limit our assessment only to performance. For example in this review: https://arxiv.org/pdf/1605.01138.pdf, a model-based approach is compared against a deep learning approach. It is very interesting to me that even if deep learning performs better, its failure cases are very different than human failure cases (deep learning is not sensitive to "physics illusions"). Whereas the…

Paper and discussion history. A mention is not an endorsement.

A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding · HackerPapers discussions

A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding — mentioned by pinouchon