/udacity-deep-learning-nanodegree

Project work for the Udacity Deep Learning Nanodegree

Primary LanguageJupyter NotebookMIT LicenseMIT

Deep Learning Nanodegree Portfolio

This repository contains my work for Udacity's Deep Learning Nanodegree program, August 2017 cohort.

Related: My Data Analyst Nanodegree Portfolio.

Projects:

  • Project 1: Your First Neural Network: Implement a neural network in Numpy to predict bike rentals.
  • Project 2: Image classification: Build a convolutional neural network with TensorFlow to classify CIFAR-10 images.
  • Project 3: Text Generation: Train a recurrent neural network on scripts from The Simpson's (copyright Fox) to generate new scripts.
  • Project 4: Machine Translation: Train a sequence to sequence network for English to French translation (on a simple dataset)
  • Project 5: Face Generation: Use a DCGAN on the CelebA dataset to generate images of novel and realistic human faces.

Courses taken:

  • Neural Networks
  • Deep Neural Networks
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)
  • Generative Adversarial Networks (GANs)

Skills acquired:

  • TensorFlow, Keras, TensorBoard
  • Cloud computing (AWS, GCE, FloydHub)
  • Weight initialization
  • Sentiment analysis
  • Image classification
  • Image generation
  • Autoencoders
  • Transfer learning
  • Embeddings and word2vec
  • Style transfer
  • Text summarization
  • Sequence to sequence
  • Dynamic memory networks
  • Machine translation
  • Semi-supervised learning
  • Reinforcement learning
  • One-shot learning