explanation
Machine Vision, GANs, and Deep Reinforcement Learning LiveLessons 2nd Edition is an intuitive introduction to deep learning training that teaches three of the most popular deep learning topics. With the introduction of automated systems, modern machine vision has surpassed human capabilities in image recognition, object recognition, and image segmentation tasks. The adversarial network forms two deep learning networks that oppose each other in a forgery-detection relationship, enabling real-time image creation and forgery with objects selected by the user.
What you’ll learn in Machine Vision, GANs, and Deep Reinforcement Learning LiveLessons 2nd Edition:
- Understand the advanced theory and core language of machine learning, reinforcement learning, and adversarial networks.
- Building state-of-the-art models for image recognition, object recognition, and image segmentation
- GAN architecture with the ability to generate attractive images in the form of human imagination
- Build deep RL helpers that can adapt to a variety of environments, like those provided by OpenAI Gym.
- Perform automated experiments to optimize deep reinforcement learning models
- Understand the current limitations of artificial intelligence and how to overcome them in the future.
Course specifications
Posted by InformIT
teacher: john crone
Language: English
Level: average
Lessons: 45
Duration: 6 hours 6 minutes
Course Topics:
Lesson 1: Orientation
subject
1.1 Running hands-on code examples in Jupyter Notebook
1.2 Review of prerequisites for deep learning theory
1.3 Sneak Peak
Lesson 2: Convolutional Neural Networks for Machine Vision
subject
2.1 Convolutional layer
2.2 Convolution filter hyperparameters
2.3 Activation pooling and smoothing
2.4 Building Convnet in Tensorflow
2.5 Convnet architecture model
2.6 Residual Network
2.7 Image Segmentation
2.8 Object detection
2.9 Transfer learning
2.10 Capsule Network
Lesson 3: Generative Adversarial Networks for Creativity
subject
3.1 Drinking all night long
3.2 Latent Space: Arithmetic of Fake Human Faces
3.3 Style Transfer: Convert Photos to Monet (and vice versa)
3.4 Applications of GAN
3.5 Essential GAN Theory
3.6 “Draw quickly! ” Dataset
3.7 Discriminator Network
3.8 Generator network
3.9 Adversarial network training
Lesson 4: Deep Reinforcement Learning
subject
4.1 Three categories of machine learning problems
4.2 When reinforcement learning becomes deeper
4.3 Application to video games
4.4 Application to board games
4.5 Practical Application
4.6 Reinforcement Learning Environment
4.7 Three categories of artificial intelligence
Lesson 5: Deep Q Learning and Beyond
subject
5.1 Cartfall Game
5.2 Essential Reinforcement Learning Theory
5.3 Deep Q-Learning Network
5.4 DQN agent definition
5.5 Interaction with the environment
5.6 Hyperparameter optimization through SLM lab
5.7 DQN and higher agents
5.8 Datasets, project ideas and resources for self-study
5.9 Approaches to artificial general intelligence
summary
Course Prerequisites:
author’s Deep learning with TensorFlow, Keras, and PyTorch LiveLesson or knowledge of the topics covered in chapters 5 through 9 of his book. Deep learning example This is a prerequisite.
movie
sample film
installation manual
After extracting, watch with your favorite players.
Subtitles: None
Quality: 720p
download link
File password: free download software
size
9.6