Oreilly – Evolutionary Deep Learning, Video Edition 2023-8

Apr 18, 2025 - 18:31

0 0

Evolutionary Deep Learning Video Edition. In this edition, the narrator reads the book while the content, graphs, code, and text are displayed on the screen. This course is like an audiobook that you can also watch as a video. Evolutionary Deep Learning is your guide to improving deep learning models using AutoML enhancements based on the principles of biological evolution. This exciting new approach uses lesser-known AI approaches to increase performance without hours of data labeling or model hyperparameter tuning. In this unique guide, you’ll discover tools to optimize everything from data collection to your network architecture.

What you will learn:

Solve complex design and analysis problems using evolutionary computation.
Tune deep learning hyperparameters using evolutionary computation, genetic algorithms, and particle swarm optimization.
Reproduce sample data using a deep learning autoencoder in unsupervised learning.
Understand the principles of reinforcement learning and the Q-Learning equation.
Apply Q-Learning to deep learning to create deep reinforcement learning.
Optimize the loss function and architecture of the unsupervised self-encoding network.
Create an evolutionary agent that can play an OpenAI Gym game.

This course is suitable for people who:

This course is suitable for data scientists who are familiar with Python.

Evolutionary Deep Learning Video Edition Course Specifications

Publisher: Oreilly
Instructor: Michael Lanham
Training level: Beginner to advanced
Training duration: 9 hours and 39 minutes

Course headings

Part 1. Getting started
Chapter 1. Introducing evolutionary deep learning
Chapter 1. The why and where of evolutionary deep learning
Chapter 1. The need for deep learning optimization
Chapter 1. Automating optimization with automated machine learning
Chapter 1. Applications of evolutionary deep learning
Chapter 1. Summary
Chapter 2. Introducing evolutionary computation
Chapter 2. Simulating life with Python
Chapter 2. Life simulation as optimization
Chapter 2. Adding evolution to the life simulation
Chapter 2. Genetic algorithms in Python
Chapter 2. Summary
Chapter 3. Introducing genetic algorithms with DEAP
Chapter 3. Solving the Queen’s Gambit
Chapter 3. Helping a traveling salesman
Chapter 3. Selecting genetic operators for improved evolution
Chapter 3. Painting with the EvoLisa
Chapter 3. Summary
Chapter 4. More evolutionary computation with DEAP
Chapter 4. Particle swarm optimization with DEAP
Chapter 4. Coevolving solutions with DEAP
Chapter 4. Evolutionary strategies with DEAP
Chapter 4. Differential evolution with DEAP
Chapter 4. Summary
Part 2. Optimizing deep learning
Chapter 5. Automating hyperparameter optimization
Chapter 5. Automating HPO with random search
Chapter 5. Grid search and HPO
Chapter 5. Evolutionary computation for HPO
Chapter 5. Genetic algorithms and evolutionary strategies for HPO
Chapter 5. Differential evolution for HPO
Chapter 5. Summary
Chapter 6. Neuroevolution optimization
Chapter 6. Genetic algorithms as deep learning optimizers
Chapter 6. Other evolutionary methods for neurooptimization
Chapter 6. Applying neuroevolution optimization to Keras
Chapter 6. Understanding the limits of evolutionary optimization
Chapter 6. Summary
Chapter 7. Evolutionary convolutional neural networks
Chapter 7. Encoding a network architecture in genes
Chapter 7. Creating the mating crossover operation
Chapter 7. Developing a custom mutation operator
Chapter 7. Evolving convolutional network architecture
Chapter 7. Summary
Part 3. Advanced applications
Chapter 8. Evolving autoencoders
Chapter 8. Evolutionary AE optimization
Chapter 8. Mating and mutating the autoencoder gene sequence
Chapter 8. Evolving an autoencoder
Chapter 8. Building variational autoencoders
Chapter 8. Summary
Chapter 9. Generative deep learning and evolution
Chapter 9. The challenges of training a GAN
Chapter 9. Fixing GAN problems with Wasserstein loss
Chapter 9. Encoding the Wasserstein DCGAN for evolution
Chapter 9. Optimizing the DCGAN with genetic algorithms
Chapter 9. Summary
Chapter 10. NEAT: NeuroEvolution of Augmenting Topologies
Chapter 10. Visualizing an evolved NEAT network
Chapter 10. Exercising the capabilities of NEAT
Chapter 10. Exercising NEAT to classify images
Chapter 10. Uncovering the role of speciation in evolving topologies
Chapter 10. Summary
Chapter 11. Evolutionary learning with NEAT
Chapter 11. Exploring complex problems from the OpenAI Gym
Chapter 11. Solving reinforcement learning problems with NEAT
Chapter 11. Solving Gym’s lunar lander problem with NEAT agents
Chapter 11. Solving Gym’s lunar lander problem with a deep Q-network
Chapter 11. Summary
Chapter 12. Evolutionary machine learning and beyond
Chapter 12. Revisiting reinforcement learning with Geppy
Chapter 12. Introducing instinctual learning
Chapter 12. Generalized learning with genetic programming
Chapter 12. The future of evolutionary machine learning
Chapter 12. Generalization with deep instinctual and deep reinforcement learning
Chapter 12. Summary

Course images

Evolutionary Deep Learning Video Edition

Sample course video

Installation Guide

After Extract, view with your favorite player.

Subtitles: None

Quality: 720p

Download link

Download Part 1 – 1 GB

Download Part 2 – 198 MB

File(s) password: www.downloadly.ir

File size

1.1 GB

Oreilly – Evolutionary Deep Learning, Video Edition 2023-8