Deep Learning Architectures and Applications

Deep Learning Architectures and Applications

English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 12m | 261 MB

Learn Deep Convolutional GAN, Word Embeddings and RNN using Keras.

This video course presents deep learning architectures coded in Python using Keras, a modular neural network library that runs on top of either Google’s TensorFlow or Lisa Lab’s Theano backends. This video course introduces Generative Adversarial Networks (GANs) that are used to reproduce synthetic data that looks like data generated by humans, and then teach how to forge the MNIST and CIFAR-10 dataset with the help of Keras Adversarial GANs.

Practical applications include code for predicting the surrounding words given the current word, sentiment analysis, and synthetic generation of texts. We will learn about a specific form of word embedding word2vec. This embedding has proven more effective and has been widely adopted in the deep learning and NLP communities. We will also learn different ways in which you can generate your own embeddings in your Keras code.

By the end of this video course, you will be able to transform words in text into vector embeddings that retain the distributional semantics of the word.

The course aims to explains the Deep Learning concepts in a simple, easy to understand manner and provides intuitive knowledge of the subjects. Code examples illustrate all the important concepts in the course, and you can implement them yourself, guided by the course. This course showcases Deep learning networks in Python using Keras.

What You Will Learn

  • Reproduce synthetic data and create realistic images
  • Identify problems for which Recurrent Neural Network (RNN) solutions are suitable
  • Generate your own word embeddings using Keras code
  • Build various distributional representations of words in context
Table of Contents

Exploring GAN
1 The Course Overview
2 Introduction to GAN
3 Keras Adversarial GANs for Forging MNIST
4 Keras Adversarial GANs for Forging CIFAR

Recurrent Neural Network – RNN
5 SimpleRNN Cells and RNN Topologies
6 Variant of the SimpleRNN Cell
7 Stateful RNNs

WaveNet and Word Embeddings
8 WaveNet
9 Skip-Gram Word2vec Model
10 CBOW Word2vec Model in Keras