Book Image

Keras 2.x Projects

By : John Bura
Book Image

Keras 2.x Projects

By: John Bura

Overview of this book

Keras is a Python library that provides a simple and clean way to create a range of deep learning models. This course introduces you to Keras and shows you how to create applications with maximum readability. You take your first steps by getting introduced to Keras, its benefits, and its applications. As you get comfortable with Keras, you will learn how to predict business outcomes using time series data and various forecasting techniques. By learning the basic concepts of reinforcement learning, you will be able to create algorithms that can learn and adapt to environmental changes and control your robots. Then, you will learn various natural language processing techniques and use the Natural Language Toolkit to analyze, classify, and tag text. By the end of the course, you’ll have the skills and the confidence to work on existing deep learning projects or create your own applications. The code bundle for this course can be downloaded from here: https://github.com/TrainingByPackt/Keras-2.X-Projects-eLearning
Table of Contents (4 chapters)
Chapter 2
Stock Volatility Forecasting Using Long Short-Term Memory
Content Locked
Section 5
Long Short-Term Memory (LSTM) in Keras
An LSTM network consists of cells (LSTM blocks) that are linked together. Each cell is, in turn, composed of three types of ports: input gate, output gate, and forget gate. They implement the write, read, and reset functions on the cell memory, respectively. So, the LSTM modules are able to regulate what is stored and deleted. This is possible thanks to the presence of various elements called gates, which are composed of a sigmoid neural layer and a pointwise product. The output of each gate is in the range (0,1), representing the percentage of information that flows inside it. Here are the topics that we will cover now: - Long Short-Term Memory (LSTM) in Keras - Long Short-Term Memory Cell Diagram