Neuraxio

LSTM-Human-Activity-Recognition

Human activity recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six categories (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING) - Guillaume Chevalier

Sentiment-Analysis-AutoML

Machine-Learning-Figures

Multilingual-Latent-Dirichlet-Allocation-LDA

A Multilingual Latent Dirichlet Allocation (LDA) Pipeline with Stop Words Removal, n-gram features, and Inverse Stemming, in Python.

Linear-Attention-Recurrent-Neural-Network

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.

Awesome-Deep-Learning-Resources

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

Hyperopt-Keras-CNN-CIFAR-100

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

python-conv-lib

A lightweight library to do for-loop-styled convolution passes on your iterable objects (e.g.: on a list).

PyTorch-Dynamic-RNN-Attention-Decoder-Tree

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.

GloVe-as-a-TensorFlow-Embedding-Layer

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.

seq2seq-signal-prediction

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

Smoothly-Blend-Image-Patches

Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.

Autoencoder-TensorBoard-t-SNE

Plugging TensorBoard in an autoencoder on the MNIST dataset for demonstrating t-SNE embeddings visualization of unsupervised machine learning.

HAR-stacked-residual-bidir-LSTMs

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.

python-caffe-custom-cifar-100-conv-net

Custom convolutional neural network on cifar-100 dataset for image classification. Images and their labels are processed to HDF5 data format for use in Caffe.

filtering-stft-and-laplace-transform

Simple demo of filtering signal with an LP filter and plotting its STFT and Laplace transform, in Python.

Predict-if-salary-is-over-50k-with-Keras

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

scikit-learn-digit-recognition

Digit Recognition with scikit-learn's Bernoulli RBM and Logistic Classifier