First Post
Hi! Just a rubbish post used to test code highlighting features. This function builds a YAML string from state.yaml_template, taking the values of hyper-parameters from state.hyper_parameters, creates...
View ArticleIntegrating Pylearn2 and Jobman
This post is adapted from an iPython Notebook I wrote which is part of a pull request to be added to the Pylearn2 documentation. I assume the reader is familiar with Pylearn2 (mostly its YAML file...
View ArticleSpeech Synthesis: Introduction
This semester I’m taking Yoshua Bengio’s representation learning class (IFT6266). In addition to formal evaluation, we’re also evaluated in the context of a big class project, in which we compete...
View ArticleClik here to view.
Speech Synthesis: Gaussian DBMs
This semester I’m taking Yoshua Bengio’s representation learning class (IFT6266). In addition to formal evaluation, we’re also evaluated in the context of a big class project, in which we compete...
View ArticleState of TIMIT dataset in Pylearn2
This is a small post just to let you know the current state of the TIMIT dataset in Pylearn2. You can find the source code here. I’m mostly done working on the initialization, thanks to Laurent Dinh’s...
View ArticleAn update on the state of TIMIT dataset in Pylearn2
I’m almost done implementing a first version the TIMIT dataset in Pylearn2. You can find the code in my public research repository. Let’s look at what the problem was and how I solved it. The challenge...
View ArticleAnother update on the state of TIMIT dataset in Pylearn2
Last week I continued working on the Pylearn2 implementation of the TIMIT dataset, so I figured now would be the time to write a quick progress report. More data integration Thanks to Laurent Dinh’s...
View Article(Yet) another update on the state of TIMIT dataset in Pylearn2
Remember my last post talking about improvements to the TIMIT dataset? Well here’s another big improvement: thanks to Laurent’s and David’s help, I was able to massively reduce memory footprint, which...
View ArticleClik here to view.
NADEs: an introduction
I might use neural autoregressive distribution estimators (NADEs) for the speech synthesis project; this has to do with an idea both Guillaume Desjardins and Yoshua Bengio talked about in the past...
View ArticleCombining acoustic samples and phones information
Good news: the pull request fixing a bug with Space classes got merged, which means we’re now able to combine phones information with acoustic samples. In this post, I’ll show you how it’s done. Note:...
View ArticleIterating over variable-length sequences
Lately I’ve been working on enabling Pylearn2 to iterate over variable-length sequences. In this post, I’ll discuss my progress so far. The problem Some types of models (such as convolutional or...
View ArticleClik here to view.
Starting on RNNs
This week I focused on training an RNN to solve our task. The RNN’s structure is really simple: it maps the k previous samples and the phone of the sample to predict to a recurrent hidden layer, which...
View ArticleClik here to view.
RNNs Part Two
Building on Jung-Hyung’s encouraging results, I tried going smaller and training an RNN to overfit a single phone. I implemented gradient clipping (my version rescales the gradient norm when it exceeds...
View ArticleVariational Autoencoder Demo
This is a tiny post to advertise the demo (available here) I built using a variational autoencoder trained on images of faces. There is an online version, but if you have the required Python...
View ArticleIntroducing the VAE framework in Pylearn2
After quite some time spent on the pull request, I’m proud to announce that the VAE model is now integrated in Pylearn2. In this post, I’ll go over the main features of the VAE framework and how to...
View ArticleYour models in Pylearn2
Who should read this This tutorial is designed for pretty much anyone working with Theano who’s tired of writing the same old boilerplate code over and over again. You have SGD implementations...
View Article
