Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective — mentioned by benibraz

Thu, 13 Aug 2020 09:01:47 GMT

What do you mean by 'the best'? Deeper architectures are popular because they quiet easy to train. They do work well in practice on many tasks (especially vision) but they have their limits. Infinite wide networks are a newly active field and has recently shown some promising results, theoretically [1, 2] and empirically [3]. [1] https://arxiv.org/abs/2001.06931 [3] https://arxiv.org/abs/1806.07572 [2] https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-w...

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

Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective · HackerPapers discussions

Any Target Function Exists in a Neighborhood of Any Sufficiently Wide Random Network: A Geometrical Perspective — mentioned by benibraz