Keras Tutorial @ PyData Florence 2017

Deep Learning with Keras and Tensorflow

Valerio Maggio: PostDoc Data Scientist @ FBK/MPBA

Contacts:

@leriomaggio

[email protected]

Library Versions

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

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

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

keras:  2.0.2
Theano:  0.9.0
Tensorflow:  1.0.1

Outline at a glance

• Part I: Introduction to ANN using Tensorflow and Keras

  • naive pure-Python implementation
  • fast forward, sgd, backprop
  • Model + SGD using Tensorflow
  • Introduction to Keras main features
    • keras.layers.core.Dense
    • keras.backend
    • Multi-Layer Perceptron and Fully Connected Networks

• Part II: Supervised Learning and Convolutional Neural Nets

  • Intro: Focus on Image Classification
  • Intro to ConvNets
  • Advanced CNN
    • Dropout
    • MaxPooling
    • Batch Normalisation
  • Famous Models in Keras
    (ref: keras.applications)
  • Transfer Learning

• Part III: Unsupervised Learning

  • AutoEncoders
  • word2vec & doc2vec (gensim) & keras.datasets
    • Embedding

• Part IV: Additional Materials

  • Recurrent Neural Networks: RNN, LSTM, GRU
  • HandsOn: IMDB
  • Multi-Input/Multi-Output Network Topologies