Techniques for Solving Linear Systems of Equations

Two further videos from my Machine Learning Foundations series out today! Both cover techniques for solving systems of linear equations algebraically:

• The first video (and 16th topic in the series overall) introduces substitution for solving linear systems by hand.
• The second video (17th topic in the series) uses elimination, which comes in handy in other situations where we'd like to solve linear systems by hand.

These videos wrap up Segment Two, "Common Tensor Operations". They set us up perfectly for Segment Three, "Matrix Properties", in which we'll cover computational approaches to solving linear systems.

The playlist for the entire series, which will consist of 30+ hours of videos, is here.

Common Tensor Operations: A Fresh Segment of my ML Foundations Series

As detailed on GitHub and covered in the short explanatory video above, the ML Foundations series consists of eight subjects:

1. Intro to Linear Algebra
2. Linear Algebra II
3. Calculus I: Limits & Derivatives
4. Calculus II: Partial Derivatives & Integrals
5. Probability & Information Theory
6. Statistics
7. Algorithms & Data Structures
8. Optimization

Each of the eight subjects consists of two or three segments, which group together closely related topics and make a given subject more structured and readily digestible. The Intro to Linear Algebra subject, for example, consists of three segments:

1. Data Structures for Algebra
2. Common Tensor Operations
3. Matrix Properties

All of the previously released videos in the ML Foundations YouTube playlist featured topics from the first segment, Data Structures for Algebra. Today, we released five new videos, which mark the beginning of Common Tensor Operations, the second segment:

• The first topic in the segment (and Topic 11 in the series overall) is Tensor Transposition.
• Topic 12 is Basic Tensor Arithmetic, including coverage of the Hadamard product.
• Topic 13 is Reduction from higher-dimensional tensors to lower-dimensional ones.
• Topic 14 introduces the Dot Product of two vectors.
• And, finally, video 15 provides exercises to test your comprehension of the content covered in the segment so far.

We aim to release two further videos next week, which will wrap up Segment 2, leaving us well-positioned to tackle Segment 3, Matrix Properties.

Modeling Natural Language Data

Here's a new two-hour video on:

• Preprocessing natural language data,
• Creating word vectors, and
• Designing convolutional neural networks for NLP.

Thanks to Debra Williams Cauley for believing in my vision for this video and to Erina Sanders for her always flawless editing.

These two hours come from a complete five-hour tutorial on Deep Learning for Natural Language Processing. It's available here in the O'Reilly learning platform. Or, if you'd like to purchase it, my publisher is running an extreme 75%-off sale on all my videos through September 10th. Use code LEARNDL after following this link.

Final videos of "Data Structures for Algebra" segment of ML Foundations

The final videos from the first segment of my Machine Learning Foundations series, Data Structures for Algebra, are out today:

• Video 8 in the series is on matrix tensors.
• Topic 9 is Generic Tensor Notation.
• And the tenth video is a quick one that provides three comprehension questions on the content covered thus far.

In the second, forthcoming segment of the ML Foundation series, we'll move from primarily creating static tensors to interacting with them via common tensor operations.

The playlist for the entire series, which will consist of 30+ hours of videos, is here.

These particular videos feature hands-on demos in PyTorch and TensorFlow, and all of the code is in GitHub.

Superb editing from Sangbin Lee, as always. Thank you!

Minimizing Unwanted Biases (e.g., by Gender, Ethnicity) within ML Models

Here's a new blog post I wrote on how my team eliminates unwanted biases (e.g., by gender, ethnicity) from algorithms we've deployed in the recruitment sector.

Devising algorithms that stamp out unwanted biases without skimping on accuracy or performance adds time and effort to the machine learning model-design process. When algorithms can have a considerable social impact, as ours do in the human-resources space at GQR Global Markets, investing this time and effort is essential to ensuring equitable treatment of all people.

Vectors and Norms: Three New "ML Foundations" Videos

Three further videos in my Machine Learning Foundations series out today! Taking it up a dimension, these are on vector tensors and the norm functions we use to measure them:

• Video 5 in the series is "Vectors and Vector Transposition"
• Topic 6 is "Norms and Unit Vectors"
• And topic 7 is a quick one on "Basis, Orthogonal, and Orthonormal Vectors"

The YouTube playlist for the entire series, which will consist of 30+ hours of videos, is here.

The series is full of hands-on demos in NumPy, PyTorch, and TensorFlow, and all of the code is in GitHub here.

As usual, producer/editor Sangbin Lee did some fine work here.

"Hidden in Plain Sight" Podcast

I've been a guest on many wonderful podcasts, but this one on Hidden in Plain Sight easily takes the cake in terms of production value. I highly recommend tuning in for a candid take on the impacts of A.I. today and in the years to come: It’s titled Deep Learning Illustrated with Jon Krohn and can be found here.

Thank you Chad Grills and Lacey Peace for having me on the program. I've been thoroughly impressed by your operation from start to finish! 

Next Three Videos in the ML Foundations Series are Live

I published three new videos in my Machine Learning Foundations series today, including an introduction to tensors, with a focus on handling scalar tensors in PyTorch and TensorFlow (vectors and matrices coming up next).

I hope you enjoy them! The response to the first videos in the series -- released a fortnight ago -- has blown me over. I'm excited to continue to get more of these out on YouTube ASAP.

The playlist for the entire series, which will consist of 30+ hours of videos, is here.

The series is full of hands-on demos in Python and all of the code is in GitHub here.

Thanks to Sangbin Lee for continuing to be an outstanding producer and editor.

The "Machine Learning Foundations" video series is here!

Today I released the first videos of my popular Machine Learning Foundations series onto YouTube. It covers all the math and computer science needed to be an outstanding ML practitioner. 

Since May, I've been launching the content as live 3.5-hour webinars in the O'Reilly online learning platform and the response has been overwhelmingly positive, with classes garnering over 1200 registrations each and net promoter scores above 90%. In all, the series consists of eight of these 3.5-hour classes covering linear algebra, calculus, probability, statistics, algorithms, data structures, and optimization. (More detail on the series in GitHub here.)

As of this morning, thanks to superb editing from the talented Sangbin Lee, we're rolling out all of the content in the series as free YouTube videos.

A short welcome video is featured above, while the first true tutorial, on "What Linear Algebra Is", is featured below.

The playlist for the entire series, which will consist of 30+ hours of videos, is here.

Finally, the series is full of hands-on demos in Jupyter notebooks featuring Python, PyTorch, and TensorFlow code, and all of it is available via the GitHub link above.

More videos to come soon... 

New ODSC AI+ Training Platform

The brilliant folks behind the Open Data Science Conference (ODSC) are launching a new online training platform called AI+ and I'm delivering the inaugural class — Deep Learning with TensorFlow 2 and PyTorch — on July 29th!

New 2-Hour Tutorial on Machine Vision

New two-hour video introducing all the major machine vision concepts and (TensorFlow-based) applications, including:

• Convolutional neural networks (CNNs)

• Residual networks

• Object detection

• Image segmentation

• Transfer learning

• Capsule networks

We worked hard and long through filming, production, and editing to push the standard of what's possible in a software tutorial; I'm confident it's the best video I've ever been a part of.

All of the code demos are in Python and available in GitHub here.

DataScienceGO -- wow!

Thanks to the SuperDataScience team for providing me the opportunity to open up Day 2 of the tightly-run DataScienceGO conference on Sunday! For my talk on deep learning model architectures for natural language processing, there were over 400 advanced practitioners from 93 countries. They were attentive throughout the session and asked fabulously thoughtful questions during an extensive Q&A afterward.

DataScienceGO Virtual Conference

The DataScienceGO Virtual conference is this weekend and completely free!

Floored to be sharing the stage with DJ Patil and Emily Robinson, luminaries I’ve looked up to for years.

I’ll be doing an hour-long workshop on neural-network model architectures for natural language processing on Sunday.

Sign up is here.

SuperDataScience Podcast →

Was honored to be approached by Kirill to appear on his legendary SuperDataScience podcast and, wow, had a wonderful experience as a guest on the program. Thanks again, Kirill and team!

We covered the importance of data science in medicine and epidemiology, the role of data science in recruitment, testing your models for bias, what I think the future holds for deep learning and much more.

Machine Learning Foundations

I’m very excited to announce the beginning of a new journey called the Machine Learning Foundations series. As discussed in the video announcement above, this series will initially consist of eight 3.5-hour classes offered within the O’Reilly online learning platform from late May through early September:

1. May 28th — Intro to Linear Algebra

2. June 4th — Linear Algebra II: Matrix Operations

3. June 11th — Calculus I: Limits & Derivatives

4. June 25th —Calculus II: Partial Derivatives & Integrals

5. July 8th —Probability & Information Theory

6. July 23rd —Intro to Statistics

7. August 12th —Algorithms & Data Structures

8. early September — Optimization

Each class will feature:

• Rich, full-color illustrations

• Hands-on code demos in Python

• Fully worked-through pencil-and-paper questions and solutions

There are 605 seats available in each class. At the time of posting:

• The first two classes (on algebra) have fewer than ten seats each

• The second pair of classes (on calculus) have fewer than a hundred

• Registration for the fifth and sixth class is open and seats are filling up quickly.

As I have bandwidth, I will be publishing all of this content as free YouTube video tutorials, so if you’ve missed the classes, don’t worry! I will also probably be offering the classes again at some point, and eventually all of the content will be brought together neatly as a book.

You can read more about the Machine Learning Foundations series — including a detailed syllabus for each class and the developing body of open-source code — in GitHub here.

ODSC East Virtual Conference: So much fun, I couldn't resist singing

After my 3.5-hour technical lecture on Wednesday morning, I rewarded my 300 attendees’ remarkable attention spans with a cover of Willin’ by Little Feat :)

It was impromptu but well-received so maybe I should start doing this regularly at data science conferences…?