Introduction to Deep Learning (with TensorFlow 2): Complete Artificial Intelligence Series
Published by Pearson
A Hands-On Primer on State-of-the-Art Deep Neural Networks
Relatively obscure a few short years ago, Deep Learning is ubiquitous today across data-driven applications as diverse as machine vision, natural language processing, and super-human game-playing.
This Deep Learning primer brings the revolutionary approach behind contemporary artificial intelligence to life with interactive demos featuring TensorFlow 2, the brand-new, major update of the most popular Deep Learning library.
To facilitate an intuitive understanding of Deep Learning’s artificial-neural-network foundations, essential theory will be introduced visually and pragmatically. Paired with tips for overcoming common pitfalls and hands-on code run-throughs provided in straightforward Jupyter notebooks, this foundational knowledge empowers you to build powerful state-of-the-art Deep Neural Network models.
This is part of Jon Krohn’s Complete Artificial Intelligence Series, a collection of interactive trainings that together comprehensively cover the foundations of modern AI approaches. The recommended progression through the Series is to take one of these two introductory sessions:
Following either of the introductory sessions (or if you’re familiar with the content covered in Chapters 1 and 5-9 of Jon Krohn’s Deep Learning Illustrated book), you’re well-prepared to specialize in any of the other Live Trainings in the Complete Artificial Intelligence Series, which can be undertaken in any order you fancy:
- Deep Learning for Machine Vision and Image Generation
- Deep Learning for Natural Language Processing
- Deep Reinforcement Learning
- Deep Dive into Deep Learning with TensorFlow 2
(Note that at any given time, only a subset of these classes will be scheduled and open for registration. To be pushed notifications of upcoming classes in the series, sign up for the instructor’s email newsletter at jonkrohn.com.)
What you’ll learn and how you can apply it
- Understand the essential theory of of artificial neural networks
- Build production-ready Deep Neural Networks in TensorFlow 2 by taking advantage of its in-built, easy-to-use Keras module
- Interpret the output of Deep Learning models to troubleshoot and improve results
This live event is for you because...
- You work with data and want to be exposed to the range of applications of Deep Learning approaches.
- You want to understand how Deep Learning works.
- You want to create state-of-the-art machine-learning models well-suited to solving a broad range of problems, including complex, non-linear problems with large, high-dimensional data sets.
Prerequisites
- Experience with an object-oriented programming language, e.g., Python (all code demos during the training will be in Python)
- Some experience with machine learning would make this Live Training easier to follow, but is by no means necessary
Materials, downloads, or Supplemental Content needed in advance:
- During class, we’ll work on Jupyter notebooks interactively in the cloud via Google Colab. This requires nearly zero setup and instructions will be provided in class. If you’d like to take a sneak peak at the notebooks we’ll be using, check out http://github.com/jonkrohn/tf2
Resources
- If you’d like to brush up on analyzing data in Python, the topics covered in Pandas Data Analysis with Python Fundamentals LiveLessons will be sufficient for this training
- If you’re the kind of person who likes to be extra-prepared or you can’t wait to get started with Deep Learning, you can read Chapter 1 and Chapters 5-9 of Jon Krohn’s Deep Learning Illustrated book.
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Segment 1: The Unreasonable Effectiveness of Deep Learning (45 min)
- Training Overview
- A Brief History of the Rise of Deep Learning
- Deep Learning vs Other Machine Learning Approaches
- Dense Feedforward Networks
- Convolutional Networks for Machine Vision
- Recurrent Networks for Natural Language Processing and Time-Series Predictions
- Deep Reinforcement Learning for Sequential Decision-Making
- Generative Adversarial Networks for Creativity
- Overview of the Leading Deep Learning Libraries, including TensorFlow 2, Keras, PyTorch, MXNet, CNTK, and Caffe
Segment 2: Essential Deep Learning Theory (75 min)
- Hands-on Jupyter Notebook Demo: An Artificial Neural Network in TensorFlow 2
- The Essential Math of Artificial Neurons
- The Essential Math of Neural Networks
- Activation Functions
- Cost Functions, including Cross-Entropy
- Stochastic Gradient Descent
- Backpropagation
- Mini-Batches
- Learning Rate
- Fancy Optimizers (e.g., Adam, Nadam)
- Glorot/He Weight Initialization
- Dense Layers
- Softmax Layers
- Dropout
- Data Augmentation
- TensorFlow Playground: Visualizing a Deep Net in Action
Segment 3: Deep Learning with Keras, TensorFlow’s High-Level API (60 min)
- Hands-on Jupyter Notebook Demo: Revisiting our Shallow Neural Network
- Hands-on Jupyter Notebook Demo: Deep Neural Nets in TensorFlow 2
- Tuning Model Hyperparameters
- Creating Your Own Deep Learning Project
- What to Study Next, Depending on Your Interests
Your Instructor
Jon Krohn
Jon Krohn is Co-Founder of the AI software firm Y Carrot and a Fellow at Lightning AI. He authored the book Deep Learning Illustrated, an instant #1 bestseller that was translated into seven languages. He is also the host of SuperDataScience, the data science industry’s most listened-to podcast. Jon is renowned for his compelling lectures, which he offers at leading universities and conferences, as well as via his award-winning YouTube channel. He holds a PhD from Oxford and has been publishing on machine learning in prominent academic journals since 2010.