LSTMs (Recurrent Neural Networks) for Human Activity Recognition
Human activity recognition 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).
Project Source: https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition

Human activity recognition with stacked residual bidirectional LSTMs
Human Activity Recognition (HAR) using stacked residual bidirectional-LSTM cells (RNN) with TensorFlow.
Project Source: https://github.com/guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs

Signal prediction with a seq2seq RNN model in TensorFlow
Solving different simple toy problems about signal prediction.
Project Source: https://github.com/guillaume-chevalier/seq2seq-signal-prediction

Hyperopt for solving CIFAR-100 with a convolutional neural network (CNN) built with Keras and TensorFlow, GPU backend
Auto-optimizing an artificial neural network (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.
Project Source: https://github.com/guillaume-chevalier/Hyperopt-Keras-CNN-CIFAR-100