Recurrent Neural Networks

Recurrent Neural Networks

English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 1h 07m | 159 MB

Get started with recurrent neural network (RNN) concepts in a simplified way and build simple applications with RNNs and Keras. RNN is a fast-growing domain within the AI world. Popular groundbreaking applications like language translation, speech synthesis, question answering, and text generation use RNNs as their base technology. Studying this technology, however, has several challenges. Most learning resources are math heavy and are difficult to navigate without good math skills. IT professionals from varying backgrounds need a simplified resource to learn the concepts and build models quickly. In this course, Kumaran Ponnambalam provides a simplified path to studying the basics of recurrent neural networks, allowing you to become productive quickly. Kumaran starts with a simplified introduction of RNN before walking through the process of building a model. He then covers the popular building blocks of RNN with GRUs, LSTMs, word embeddings, and transformers.

Table of Contents

1 Getting started with RNNs
2 Scope and prerequisites for the course
3 Setting up exercise files

Introduction to RNNs
4 A review of deep learning
5 Why sequence models
6 A recurrent neural network
7 Types of RNNs
8 Applications of RNNs

RNN Concepts
9 Training RNN models
10 Forward propagation with RNN
11 Computing RNN loss
12 Backward propagation with RNN
13 Predictions with RNN

An RNN Example
14 A simple RNN example Predicting stock prices
15 Data preprocessing for RNN
16 Preparing time series data with lookback
17 Creating an RNN model
18 Testing and predictions with RNN

RNN Architectures
19 The vanishing gradient problem
20 The gated recurrent unit
21 Long short-term memory
22 Bidirectional RNNs

An LSTM Example
23 Forecasting service loads with LSTM
24 Time series patterns
25 Preparing time series data for LSTM
26 Creating an LSTM model
27 Testing the LSTM model
28 Forecasting service loads Predictions

Word Embeddings
29 Text based models Challenges
30 Intro to word embeddings
31 Pretrained word embeddings
32 Text preprocessing for RNN
33 Creating an embedding matrix

Spam Detection with Word Embeddings
34 Spam detection example for embeddings
35 Preparing spam data for training
36 Building the embedding matrix
37 Creating a spam classification model
38 Predicting spam with LSTM and word embeddings

39 Next steps