Automation & Systems

Deep Learning With Python

Gilad Gressel
Gilad Gressel

Gain access to this course with an INE subscription!
Choose your plan!


Course Description
Introduction to deep learning with Keras and Tensorflow- Learn the basics of deep learning by coding it yourself with Keras. Keras is a very popular user friendly deep learning framework for creating and running deep learning models. Using Keras (with a tensorflow backend) we will learn to build deep learning models by practicing together on the following tasks: image recognition, text classification, and housing price predictions. You will learn the correct way to conduct end-to-end deep learning: preprocessing the data, appropriate network architecture, optimizers, loss functions, cross-validation techniques and evaluation metrics. Prior experience with Python is required — or the ability to learn it as you go.
  • Course
    • Overview of Deep Learning & Machine Intelligence
      • Course Introduction
      • Installing Software
      • What Is Deep Learning
      • How Computers Learn
    • Mechanics of Deep Learning
      • Mechanics Of Deep Learning :: Overview
      • Loss Functions
      • Optimizers
      • Layers
      • Activation Functions
    • Data preprocessing
      • Preprocessing :: Overview
      • Scaling Your Data
      • Encodings
      • Dealing With Text
    • Evaluating Our Models
      • Evaluation & Validation
      • Metrics
      • Overfitting Vs Underfitting
      • Cross Validation Schemes
    • Conclusions
      • Be An Engineer
Course Outline:
  • Course
    • Overview of Deep Learning & Machine Intelligence
      • Course Introduction
      • Installing Software
      • What Is Deep Learning
      • How Computers Learn
    • Mechanics of Deep Learning
      • Mechanics Of Deep Learning :: Overview
      • Loss Functions
      • Optimizers
      • Layers
      • Activation Functions
    • Data preprocessing
      • Preprocessing :: Overview
      • Scaling Your Data
      • Encodings
      • Dealing With Text
    • Evaluating Our Models
      • Evaluation & Validation
      • Metrics
      • Overfitting Vs Underfitting
      • Cross Validation Schemes
    • Conclusions
      • Be An Engineer