Opening the Black Box of Deep Neural Networks via Information · HackerPapers discussions

Opening the Black Box of Deep Neural Networks via Information — mentioned by jhrmnn

Sat, 12 Jun 2021 20:45:57 GMT

There are a few works that try to put deep learning on some theoretical basis, I like this one, for example: https://arxiv.org/abs/1703.00810 This goes beyond mere intuition, but it is also still very far from a “complete theory”. I find it disappointing that so few people in deep learning work on the theoretical foundations.

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

Opening the Black Box of Deep Neural Networks via Information — mentioned by azag0

Tue, 12 Dec 2017 10:40:59 GMT

I think this recent paper [1] sheds quite a bit of light on this. [1] https://arxiv.org/abs/1703.00810v3

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

Opening the Black Box of Deep Neural Networks via Information — HN submission

Wed, 15 Nov 2017 21:34:16 GMT

Opening the Black Box of Deep Neural Networks via Information

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Opening the Black Box of Deep Neural Networks via Information — HN submission

Wed, 15 Nov 2017 16:26:18 GMT

Opening the Black Box – understanding what happens during deep learning

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Opening the Black Box of Deep Neural Networks via Information — mentioned by pinouchon

Wed, 08 Nov 2017 16:16:55 GMT

Hi. Thanks for the great article. Can you elaborate on what you mean by "directions in activation space" ? If I understand it right: You take a few neurons in a layer, and you follow some linear combination of their weights; you are then walking along a random direction. You take a single neuron and walk along its weights; you walk along this neuron's direction. Is this correct? Also another comment: Szegedy et al [9] (https://arxiv.org/pdf/1312.6199.pdf) has the following abstract: > First, we find that there is no distinction between individual high level units and random linear…

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

Opening the Black Box of Deep Neural Networks via Information — HN submission

Thu, 06 Jul 2017 03:49:45 GMT

Opening the Black Box of Deep Neural Networks via Information

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Opening the Black Box of Deep Neural Networks via Information — HN submission

Wed, 12 Apr 2017 23:46:23 GMT

Opening the Black Box of Deep Neural Networks via Information

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Opening the Black Box of Deep Neural Networks via Information — HN submission

Wed, 22 Mar 2017 00:08:25 GMT

Opening the Black Box of Deep Neural Networks via Information

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.