I’m greatly honored to be leading the charge on ODSC’s exciting new AI+ Training platform, which brings ODSC’s world-leading ability to provide professional training to data scientists into the digital realm while nevertheless retaining an intimate and engaging experience for attendees.
My Deep Learning with TensorFlow 2 & PyTorch workshop will serve as a primer on deep learning theory that will bring the revolutionary machine-learning approach to life with hands-on demos. Critically, for the first time in any training that I’m aware of, these demos will feature both TensorFlow and PyTorch, the world’s two most popular deep learning libraries (see chart below, noting that Keras is a module within TensorFlow that we’ll use in this class).
The training will be broken down into three segments:
- The Unreasonable Effectiveness of Deep Learning
- Essential Deep Learning Theory
- TensorFlow 2 and PyTorch
- Introduce what artificial neural networks (ANNs) are and how they facilitate the uniquely effective deep learning models that have become ubiquitous in recent years
- Cover the range of deep learning families that are deployed across applications as diverse as machine vision, natural language processing, and super-human game-playing (the game of Go is illustrated below)
- Compare and contrast the relative strengths and most valuable use cases of the most popular deep learning libraries, including when TensorFlow 2 or PyTorch would be the best option for you
- In a hands-on Jupyter notebook demo run within the Colab cloud environment, design and train a preliminary ANN using TensorFlow 2 and its high-level Keras API
- Cover all of the essential theory related to deep learning, including:
- artificial neurons
- activation functions
- layer types
- cost functions
- stochastic gradient descent (illustrated across three frames below)
- fancy optimizers (e.g., Nadam)
- performance metrics
- weight initialization
- hyperparameter tuning
- avoiding overfitting (e.g., with dropout)
- Use the TensorFlow Playground to visualize the theory of a deep learning network in action
- Design a production-ready TensorFlow model that includes all of the state-of-the-art bells and whistles
- Construct a comparable PyTorch model to contrast the pros and cons of each of the leading libraries
- Build a convolutional neural network to excel at a machine vision task
In the end, you’ll come away from the training with an intuitive understanding of deep learning’s foundations. With tips on overcoming common pitfalls and best practices for designing and training ANNs provided within straightforward Jupyter notebooks (GitHub repo here), you’ll have all the knowledge you need to apply state-of-the-art deep learning models to your own data. I’m very much looking forward to getting to know you at the training!
On top of all of the above, I’m running a unique promotion that I’ve never offered before: In the spirit of in-person book-signing sessions in the COVID-lockdown era, attendees are welcome to purchase a signed copy of my book Deep Learning Illustrated that I’ll personalize with an inscription just for you! Email firstname.lastname@example.org for details.
Jon Krohn is Chief Data Scientist at the machine learning company untapt. He authored the 2019 book Deep Learning Illustrated, an instant #1 bestseller that was translated into six languages. Jon’s also the presenter of dozens of hours of popular video tutorials such as Deep Learning with TensorFlow, Keras, and PyTorch. And he’s renowned for his compelling lectures, which he offers in-person at Columbia University, New York University, and the NYC Data Science Academy. Jon holds a PhD in neuroscience from Oxford and has been publishing on machine learning in leading academic journals since 2010.
Editors note: Limited Time Offer: GET 20% OFF Deep Learning with TensorFlow 2 & PyTorch WORKSHOP