15 open source projects by guillaume-chevalier

Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.

What about coding a Spiking Neural Network using an automatic differentiation framework? In SNNs, there is a time axis and the neural network sees data throughout time, and activation functions are instead spikes that are raised past a certain pre-activation threshold. Pre-activation values constantly fades if neurons aren't excited enough.

A recurrent attention module consisting of an LSTM cell which can query its own past cell states by the means of windowed multi-head attention. The formulas are derived from the BN-LSTM and the Transformer Network. The LARNN cell with attention can be easily used inside a loop on the cell state, just like any other RNN. (LARNN)

Rough list of my favorite deep learning resources, useful for revisiting topics or for reference. I have got through all of the content listed there, carefully. - Guillaume Chevalier

Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.

Taking a pretrained GloVe model, and using it as a TensorFlow embedding weight layer **inside the GPU**. Therefore, you only need to send the index of the words through the GPU data transfer bus, reducing data transfer overhead.

A question-answering chatbot, simply.

Signal forecasting with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier

Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

Both deep learning datasets can be imported in python directly with h5py (HDF5 format). The datasets can be directly imported or converted with a python script.

Growing the code out of your notebooks - the right way.

Simple demo of filtering signal with an LPF and plotting its Short-Time Fourier Transform (STFT) and Laplace transform, in Python.

Attempt at reproducing a SGNN's projection layer, but with word n-grams instead of skip-grams. Paper and more: http://aclweb.org/anthology/D18-1105

Predict whether income exceeds $50K/yr based on census data of the "Adult Dataset". Also known as "Census Income" dataset.

This is code I wrote within less than an hour so as to very roughly draft how I would code a Dynamic RNN Attention Decoder Tree with PyTorch.