At the expense of countless espresso beans, I’m proud to be releasing 18 hours of brand-new video tutorials introducing all of deep learning, including what deep neural networks are and all of their major applications: to machine vision, natural language processing, artistic creativity, and complex decision-making.
All of the previous video tutorials I’ve released have received across-the-board five-star ratings from users in the O’Reilly online learning platform, but I’m confident these new videos improve markedly upon the quality of any earlier ones.
There are three sets of video tutorials in the series:
The eponymous Deep Learning with TensorFlow, Keras, and PyTorch (released in Feb 2020)
Deep Learning for Natural Language Processing, 2nd Ed. (Feb 2020)
Machine Vision, GANs, and Deep Reinforcement Learning (Apr 2020)
The above order is the recommended sequence in which to undertake these tutorials. That said, the first in the series provides a strong foundation for either of the other two.
Taken all together, the series parallels the entirety of the content in my book Deep Learning Illustrated. This means that videos introduce all of deep learning:
What deep neural networks are and how they work, both mathematically and using the most popular code libraries
Machine vision, primarily with convolutional neural networks
Natural language processing, including with recurrent neural networks
Artistic creativity with generative adversarial networks (GANs)
Complex, sequential decision-making with deep reinforcement learning
These video tutorial also includes some extra content that is not available in the book, such as:
Detailed interactive examples involving training and testing deep learning models in PyTorch
How to generate novel sequences of natural language in the style of your training data
High-level discussion of transformer-based natural-language-processing models like BERT, ELMo, and GPT-2
Detailed interactive examples of training advanced machine vision models (image segmentation, object detection)
All hands-on code demos involving TensorFlow or Keras have been updated to TensorFlow 2
Lesson Summary, with Links to Jupyter Notebooks
There are dozens of meticulously crafted Jupyter notebooks of code associated with these videos. All of them can be found in this GitHub directory. Below is a breakdown of the lessons covered across the videos, including their duration and associated notebooks.
Deep Learning with TensorFlow, Keras, and PyTorch
Seven hours and 13 minutes total runtime
Lesson 1: Introduction to Deep Learning and Artificial Intelligence (1 hour, 47 min)
Lesson 2: How Deep Learning Works (2 hours, 16 min) — available FREE at top of this post
Lesson 3: High-Performance Deep Learning Networks (1 hour, 16 min)
Lesson 4: Convolutional Neural Networks (47 min)
Lesson 5: Moving Forward with Your Own Deep Learning Projects (1 hour, 4 min)
Deep Learning for Natural Language Processing
Five hours total runtime
Lesson 1: The Power and Elegance of Deep Learning for NLP (46 min)
Lesson 2: Word Vectors (1 hour, 7 min) — available FREE below
Lesson 3: Modeling Natural Language Data (1 hour, 43 min)
Lesson 4: Recurrent Neural Networks (25 min)
Lesson 5: Advanced Models (54 min)
Machine Vision, GANs, and Deep Reinforcement Learning
Six hours and six minutes total runtime
Lesson 1: Orientation (35 min)
Lesson 2: Convolutional Neural Networks for Machine Vision (2 hours, 2 min) — available FREE below
Lesson 3: Generative Adversarial Networks for Creativity (1 hour, 22 min)
Lesson 4: Deep Reinforcement Learning (38 min)
Lesson 5: Deep Q-Learning and Beyond (1 hour, 25 min)