This is the repository for my implementations on mayor projects of the Deep Learning Nanodegree from Udacity.

Syllabus

• Mathematical demonstrations:

  • Backpropagation
  • Softmax & Cross-Entropy gradients
  • Batch Normalization gradient

• Weight Initilization review:

  • Implemented using TensorFlow.
  • Implication of different initializations over Cost function and Gradient descent.
  • Reviewed:
    • Ones initializatialization.
    • Uniform distribution, saled uniform.
    • Normal distribution, truncated distribution.
    • Comparison to Xavier initialization.

• Batch Normalization:

  • Implemented on TensorFlow.
  • Used in fully connected and convolutional layers.
  • Two levels of implementation:
    • Higher level of abstraction, tf.layers.batch_normalization: TensorFlow takes care of the normalization for training and inference, control dependencies through tf.control_dependencies() and tf.GraphKeys.UPDATE_OPS.
    • Lower level, tf.nn.batch_normalization: Explicit implementation instanciating gamma, beta, and calculating the batch/population mean, variance. Control training and inference through tf.cond().

• Sentiment Analysis using MLPs:

  • Implemented on Numpy/Python.
  • Predict Positive/Negative sentiment over movie reviews.
  • Preprocess data:
    • Create vocabulary, word frequency.
    • Analyze word-freq/sentiment review ratio.
    • Bit encoding per word.
  • Built the neural network.
  • Reviewed limitations with word freq instead of word-sentiment relationship. 10% Validation accuracy improvement.

• Bike Sharing Project:

  • Implemented on Numpy/Python.
  • Load & prepare the data:
    • Normalize features.
    • Created training, validation and test data.
  • Implement forward and backward propagation.
  • Trained and tested accuracy.

• CNN Autoencoder:

  • Implemented using Keras.
  • Usage of CNNs for encoding-decoding.
  • Denoising images.

• Data Augmentation & Transfer Learning:

  • Implemented using Keras.
  • Explored data augmentation of CIFAR-10 with ImageDataGenerator from Keras, and impact of it over training.
  • Reviewed transfer learning on VGG-16, bottleneck feature extraccion and new FC layers over them.

• Dog Breed Prediction Project:

  • Implemented using Keras.
  • Created CNN model from scratch and achieved at least 5% test accuracy in the first 5 epochs using data augmentation.
  • Used transfer learning of Xception model, and data augmentation to achieve 83% test accuracy.
  • Xception paper: Xception: Deep Learning with Depthwise Separable Convolutions

• Mathematical demonstrations:

  • RNN Backpropagation through time
  • LSTM Backpropagation through time
  • GRU Backpropagation through time

• Character-Level LSTM Network:

  • Implemented in TensorFlow.
  • Developed a Character-Wise RNN sequence predictor. A two 2 layer depth LSTM with Tx=50 time sequence length. With a 128 dimension for the LSTM memory cell, and a vocabulary size 83.
  • Steps:
    • Data processing for minibatches.
    • Built LSTM model.
    • Optimizer & Gradient clipping.
    • Checkpoint training.
    • Sequence generation with output sampling.

• Embeddings and Word2vec:

  • Implemented in TensorFlow.
  • Implemented and trained a Skip-gram Word Embedding matrix.
  • Used Subsampling, negative sampling.
  • Visualization of word vectors using T-SNE.
  • Based on papers:
    • Efficient Estimation of Word Representations in Vector Space
    • Distributed Representations of Words and Phrases and their Compositionality

• Sentiment Prediction:

  • Implemented in TensorFlow.
  • Sentiment prediction using Word Embedding on LSTM.

• The Simpsons Script Generation:

  • Implemented in TensorFlow.
  • Language sequence generation on a LSTM network using Word Embedding.

• GAN Personal Notes

• GAN over MNIST db:

  • Implemented in TensorFlow.
  • GAN implementation for the MNIST database.
  • Based on Generative Adversarial Networks Paper

• DCGAN: Deep Convolutional GAN:

  • Implemented in TensorFlow.
  • DCGAN implementation for the Street View House Number database.

• DCGAN for Face image generation: Deep Convolutional GAN:

  • Implemented in TensorFlow.
  • DCGAN implementation to generate faces, trained over CelebFaces Attributes Dataset (CelebA).
  • Based on papers:
    • A.Radford et al "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Paper"
    • T.Salimans et al. "Improved Techniques for Training GANs", 2016

• Reinforcement Learning Personal Notes

• Frozen Lake:

  • Implementation on Frozen Lake enviroment.
  • Reinforcement Learning by Richard S. Sutton and Andrew G. Barto: Chapters 3 & 4
  • Covers Finite Markov Processes and Dynamic Programming:
    • Policy Evaluation.
    • Policy Improvement.
    • Policy Iteration.
    • Truncated Policy Evaluation.
    • Value Iteration.

• BlackJack:

  • Implementation on BlackJack enviroment.
  • Reinforcement Learning by Richard S. Sutton and Andrew G. Barto: Chapter 5.
  • Monte Carlo Methods:
    • Monte Carlo Predictions: State-value and Action-value functions.
    • Monte Carlo Control.
    • GLIE MC Control(Greedy in the limit with Infinite Exploration).
    • Constant aplha-GLIE MC Control.

• CliffWalking:

  • Implementation on CliffWalking enviroment.
  • Reinforcement Learning by Richard S. Sutton and Andrew G. Barto: Chapter 6.
  • Temporal-Difference Methods:
    • Temporal-Difference Predictions: State-value and Action-value functions.
    • Sarsa.
    • Q-Learning (Sarsamax).
    • Expected Sarsa.

• Taxi-v2:

  • Implemented agent to solve the OpenAI gym of Taxi.
  • Tested Q-Learning, Sarsa, Expected Sarsa.
  • Best Score over 100 episode average rewards: 9.359 on Q-Learning.

• Reinforcement Learning in cotinuous spaces:

  • Discretization
  • Tile Coding

• Deep Q-Learning:

  • Based on V.Mnih et al. "Playing Atari with Deep Reinforcement Learning", 2013
  • Deep Q-Learning implementation.
  • Implementations of neural network action-value approximator in TensorFlow.
  • Implemented experience replay memory and fixed Q targets.

• Double Deep Q-Learning:

  • Based on H.Hasselt et al. "Deep Reinforcement Learning with Double Q-learning", 2015
  • Double Deep Q-Learning implementation.
  • Implemented experience replay memory and fixed Q targets.
  • Implemented two action-value neural network approximators, for action decision and fixed target.

• Deep Deterministic Policy Gradient:

  • Based on T.Lillicrap et al. "Continuous control with deep reinforcement learning", 2016
  • Deep Deterministic Policy Gradient implementation.
  • Implemented action repeat, experience replay memory and fixed targets for Actor/Critic Networks with soft update.
  • MountainCarContinuous-v0 solved after 70 episodes

• Quadracopter Agent:

  • Deep Deterministic Policy Gradient implementation based on T.Lillicrap et al. "Continuous control with deep reinforcement learning", 2016
  • Implemented action repeat, experience replay memory and fixed targets for Actor/Critic Networks with soft update.
  • Define 'Take off' task for the drone agent to solve, implementing the rewards function for it.
  • The drone is able to learn how to take off after 55 Episodes.