Oreilly – Deep Learning with R, Second Edition, Video Edition 2022-10

Published on: 2024-09-19 20:32:56

Categories: 28

Description

Deep Learning with R course, Second Edition, Video Edition. In this course you will learn:

Deep learning from the basics
Image classification and image segmentation
Time series forecasting
Text classification and machine translation
Text production, neural style transfer and image production

Deep learning has become essential for data scientists, researchers and software developers. The R language APIs for Keras and TensorFlow make deep learning accessible to all R users, even if they have no experience with advanced machine learning or neural networks. This book shows you how to get started using R for core DL tasks such as computer vision, natural language processing, and more.

What you will learn in this course

Image classification and image segmentation
Time series forecasting
Text classification and machine translation
Text production, neural style transfer and image production

This course is suitable for people who

Have intermediate skills in R.
No prior experience with Keras, TensorFlow, or deep learning is necessary.

Course details

Publisher: Oreilly
Instructor: Francois Chollet , Sigrid Keydana , Tomasz Kalinowski , JJ Allaire
Training level: beginner to advanced
Training duration: 15 hours and 28 minutes

Course headings

Chapter 1. What is deep learning?
Chapter 1. Before deep learning: A brief history of machine learning
Chapter 1. Why deep learning? Why now?
Chapter 2. The mathematical building blocks of neural networks
Chapter 2. Data representations for neural networks
Chapter 2. The gears of neural networks: Tensor operations
Chapter 2. The engine of neural networks: Gradient-based optimization
Chapter 2. Looking back at our first example
Chapter 2. Summary
Chapter 3. Introduction to Keras and TensorFlow
Chapter 3. What’s Keras?
Chapter 3. Keras and TensorFlow: A brief history
Chapter 3. Python and R interfaces: A brief history
Chapter 3. Setting up a deep learning workspace
Chapter 3. First steps with TensorFlow
Chapter 3. Tensor attributes
Chapter 3. Anatomy of a neural network : Understanding core Keras APIs
Chapter 3. Summary
Chapter 4. Getting started with neural networks: Classification and regression
Chapter 4. Classifying newswires: A multiclass classification example
Chapter 4. Predicting house prices: A regression example
Chapter 4. Summary
Chapter 5. Fundamentals of machine learning
Chapter 5. Evaluating machine learning models
Chapter 5. Improving model fit
Chapter 5. Improving generalization
Chapter 5. Summary
Chapter 6. The universal workflow of machine learning
Chapter 6. Develop a model
Chapter 6. Deploy the model
Chapter 6. Summary
Chapter 7. Working with Keras: A deep dive
Chapter 7. Different ways to build Keras models
Chapter 7. Using built-in training and evaluation loops
Chapter 7. Writing your own training and evaluation loops
Chapter 7. Summary
Chapter 8. Introduction to deep learning for computer vision
Chapter 8. Training a convnet from scratch on a small dataset
Chapter 8. Leveraging a pretrained model
Chapter 8. Summary
Chapter 9. Advanced deep learning for computer vision
Chapter 9. An image segmentation example
Chapter 9. Modern convnet architecture patterns
Chapter 9. Interpreting what convnets learn
Chapter 9. Summary
Chapter 10. Deep learning for time series
Chapter 10. A temperature-forecasting example
Chapter 10. Understanding recurrent neural networks
Chapter 10. Advanced use of recurrent neural networks
Chapter 10. Summary
Chapter 11. Deep learning for text
Chapter 11. Preparing text data
Chapter 11. Two approaches for representing groups of words: Sets and sequences
Chapter 11. The Transformer architecture
Chapter 11. Beyond text classification: Sequence-to-sequence learning
Chapter 11. Summary
Chapter 12. Generative deep learning
Chapter 12. DeepDream
Chapter 12. Neural style transfer
Chapter 12. Generating images with variational autoencoders
Chapter 12. Introduction to generative adversarial networks
Chapter 12. Summary
Chapter 13. Best practices for the real world
Chapter 13. Scaling-up model training
Chapter 13. Summary
Chapter 14. Conclusions
Chapter 14. The limitations of deep learning
Chapter 14. Setting the course toward greater generality in AI
Chapter 14. Implementing intelligence: The missing ingredients
Chapter 14. The future of deep learning
Chapter 14. Staying up-to-date in a fast-moving field
Chapter 14. Final words