ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks — mentioned by kastnerkyle

Sun, 09 Aug 2015 01:51:45 GMT

This is really cool stuff - the network structure reminds me a lot of Graves' MDRNN[1] and Grid LSTM[2], as well as some work I helped with (ReNet [3]) I wonder if the structure over frequency/time is too "regular" - in general for sound the frequency correlation and the time correlation are on wildly different scales. Also if you are looking to go farther you might reconsider adding NADE or RBM [4] on top, or latent variables in the hiddens[5][6] to add more stochasticity. There was some alternate work by Kratarth Goel extending RNN-RBM to LSTM and DBN, it might give you some ideas to look…

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

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks — HN submission

Tue, 05 May 2015 21:56:43 GMT

A Recurrent Neural Network Based Alternative to Convolutional Networks

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

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks · HackerPapers discussions

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks — mentioned by kastnerkyle

ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks — HN submission