Keras Tutorial @ Web Valley 2017

Deep Learning with Keras and Tensorflow

Valerio Maggio: PostDoc Data Scientist @ FBK/MPBA

Contacts:

@leriomaggio

[email protected]

Installed Versions

import keras
print('keras: ', keras.__version__)

# optional
import theano
print('Theano: ', theano.__version__)

import tensorflow as tf
print('Tensorflow: ', tf.__version__)

keras:  2.0.4
Theano:  0.9.0
Tensorflow:  1.2.1

Outline

• Part I: Introduction

  • Intro to Artificial Neural Networks

    • Perceptron and MLP
    • naive pure-Python implementation
    • fast forward, sgd, backprop

  • Introduction to Deep Learning Frameworks

    • Intro to Theano
    • Intro to Tensorflow
    • Intro to Keras
      • Overview and main features
      • Overview of the core layers
      • Multi-Layer Perceptron and Fully Connected
        • Examples with keras.models.Sequential and Dense
      • Keras Backend

• Part II: Supervised Learning

  • Fully Connected Networks and Embeddings

    • Intro to MNIST Dataset
    • Hidden Leayer Representation and Embeddings

  • Convolutional Neural Networks

    • meaning of convolutional filters

      • examples from ImageNet

    • Visualising ConvNets

    • Advanced CNN

      • Dropout
      • MaxPooling
      • Batch Normalisation

    • HandsOn: MNIST Dataset

      • FC and MNIST
      • CNN and MNIST

    • Deep Convolutiona Neural Networks with Keras (ref: keras.applications)

      • VGG16
      • VGG19
      • ResNet50

  • Transfer Learning and FineTuning

  • Hyperparameters Optimisation

• Part III: Unsupervised Learning

  • AutoEncoders and Embeddings
  • AutoEncoders and MNIST
    • word2vec and doc2vec (gensim) with keras.datasets
    • word2vec and CNN

• Part IV: Recurrent Neural Networks

  • Recurrent Neural Network in Keras
    • SimpleRNN, LSTM, GRU
  • LSTM for Sentence Generation

• PartV: Additional Materials:

  • Custom Layers in Keras
  • Multi modal Network Topologies with Keras