Repo for Deep Learning Nanodegree by AWS and Facebook AI
Built and trained neural networks from scratch to predict the number of bikeshare users on a given day.
Designed and trained a convolutional neural network (CNN) to analyze images of dogs and correctly identify their breeds. Used transfer learning and well-known architectures to improve this model.
Built a Recurrent Neural Network (RNN) on TensorFlow to process text. Used it to generate new episodes of my favorite TV show, based on old scripts.
Built a pair of multi-layer neural networks and made them compete against each other in order to generate new, realistic faces. Used Generative Adversarial Networks(GAN) for image generation.
Trained and deployed my own PyTorch sentiment analysis model using Amazon's SageMaker service. Built a model and created a gateway for accessing it from a website.