Explore Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) in this 28-minute video tutorial. Learn how these layer types are used to build recurrent neural networks in Keras, laying the groundwork for Natural Language Processing (NLP) and time series prediction. Dive into LSTM diagrams, internals, and sigmoid functions before comparing LSTM to GRU. Follow along with practical examples, including an LSTM implementation and a sunspots prediction model. Access accompanying code on GitHub and discover additional resources to further your deep learning journey.
Overview
Syllabus
Introduction
Context Neurons
LSTM Diagram
LSTM Internals
Sigmoid Functions
GRU
LSTM
LSTM vs GRU
LSTM Example 1
Training Results
Sunspots
Training Data
SyncWences
Data Structure
Train Model
Results
Outro
Taught by
Jeff Heaton
