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.
A4N Episode 3: Scaling a Global Data Business with Kirill Eremenko
The third episode of A4N — the Artificial Neural Network News Network podcast — is out (listen on my website, on Apple Podcasts, Spotify, Google Podcasts, or YouTube). In this episode, our guest host Kirill Eremenko joins us to discuss SuperDataScience, his thriving data-science education business, and Vince introduces us to machine learning projects being applied to understand -- and preserve -- marine life in the oceans.
Our special guest today is Kirill Eremenko. Kirill is Russian-born Australian, and Founder and CEO of SuperDataScience, an online educational portal for Data Scientists. Their mission is to “Make The Complex Simple,” and become the biggest learning portal for Data Science enthusiasts. Ever. He is also the Co-Founder of BlueLifeAI, Founder of the DataScienceGo conference, and hosts his own podcast, the SuperDataScience Podcast!
Click through for more detail, including reference links and a full transcript.
Read More
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:
May 28th — Intro to Linear Algebra
June 4th — Linear Algebra II: Matrix Operations
June 11th — Calculus I: Limits & Derivatives
June 25th —Calculus II: Partial Derivatives & Integrals
July 8th —Probability & Information Theory
July 23rd —Intro to Statistics
August 12th —Algorithms & Data Structures
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…?
18 Hours of Brand-New Video Tutorials Introducing All of Deep Learning
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.
For a summary of all of the lessons, links to the dozens of free, open-source Jupyter notebooks of code that accompany the videos, and six hours of free YouTube content, click “Read More” to view the whole post:
Read More
A4N Episode 2: Tackling Coronaviruses with Machine Learning, feat. Ben Taylor
The second episode of A4N — the Artificial Neural Network News Network podcast — is out (listen on my website, on Apple Podcasts, Spotify, Google Podcasts, or YouTube). In the episode, we discuss how anyone can contribute to the cure for the coronavirus pandemic, mind-controlled prosthetic limbs, and what it takes to succeed as an AI start-up.
Our special guest for the episode is Ben Taylor. Ben is the Co-Founder and Chief AI Officer of zeff.ai, an AI product company, and former Chief Data Scientist at HireVue. He is a prolific thinker and innovator, and we’re thrilled to have him as a guest on A4N!
Click through for all of the links mentioned in the episode and a full transcript.
Read MoreVideo Tutorial on the Central Limit Theorem
Brand-new video tutorial: an intro to the Central Limit Theorem, a whacky phenomenon that underlies (almost) all modern statistics and machine learning. My hands-on code demos (in Python) make it easy to grasp why the whackiness happens.
Could be the perfect thing for ya if you're avoiding the plague by working from home and/or you're looking for something new to learn!
Announcing A4N: The Artificial Neural Network News Network →
It’s my great pleasure to announce A4N — the Artificial Neural Network News Network — a new podcast series. Our show is a lighthearted vehicle for discussion of the latest developments in A.I., machine learning, and data science, in which we both introduce technical aspects of these advances as well as their social implications.
The intended audience is anyone interested in automation, A.I., or the future, with brief sections catering especially to professionals working in the fields of data science or software engineering.
The show is hosted by Andrew Vlahutin, Grant Beyleveld, Vince Petaccio II, and myself — data scientists and machine learning engineers from untapt, an A.I. company. The podcast is commercial-free and we are bent on becoming your favorite — and most entertaining — source for A.I.-related news.
Episodes are hosted on jonkrohn.com (here) and are syndicated across all of the most popular platforms: Apple Podcasts, Spotify Podcasts, and Google Podcasts.
As with the Joe Rogan Experience and many other beloved podcasts, we also provide a raw video feed of the podcast recording session, which is available on YouTube.
Click through to the Medium post provided here for all of the links and more details :)
Tutorial, Booksigning, and "Ask the Expert" Session at ODSC East in Boston in April →
On April 15th in Boston, I’ll be giving a hands-on, 3.5-hour introduction to deep learning — featuring the brand-new TensorFlow 2 library — at the Open Data Science Conference East. In addition, I’ll be giving away dozens of free copies of my book Deep Learning Illustrated during a book-signing session, as well as answering any questions you might have during an “Ask the Expert” session.
First (of Many) Free Video Tutorials
After years of producing popular data-science tutorials that exist behind paywalls, I'm delighted to announce my first (of many) 100% free videos. This first one is on "Big O Notation" -- a critical computing concept.
Deep Learning Study Group XVII: Capsule Nets, BERT & Book Launch →
For this session, Dmitri Nesterenko and Grant Beyleveld presented on Capsule Networks (slides here) and "BERT & Friends" (slides here), respectively.
This session also served as a book launch for my, Grant Beyleveld, and Aglae Bassens' book, Deep Learning Illustrated, the content of which was influenced in large part by the previous sessions of the Deep Learning Study Group. The first photo of the three authors together with their book is provided above.
Click through for all of the session details, including the recommended preparatory work and the topics we’re considering for our next session.
Open Data Science Conference West
My first experience at ODSC West exceeded my lofty expectations. Personal highlights include:
Teaching an oversubscribed four-hour tutorial on deep learning with TensorFlow (pictured above; slides here)
Meeting hundreds of wonderful fans at my Deep Learning Illustrated book-signing (pictured below)
Sharing meals with some of the biggest names in data science, including Pieter Abbeel, Kirk Borne, and Kate Strachnyi
Conversation on "Artificial Intelligence and the Brain" with Dr. Heather Berlin
Last night in New York, neuroscientist Heather Berlin and I gave a talk on artificial intelligence and the brain at a Magdalen College alumni event. We’re pictured here with charming host, Sir David Clary.
I had a lot of fun, found Heather’s content fascinating, and loved the thorough audience questions.
Wrapped Filming in San Fran
In San Francisco, having wrapped filming for a series of interactive videos using TensorFlow 2.0 and Keras for Natural Language Processing, Machine Vision, and Deep Reinforcement Learning.
All of the code is available for free now in GitHub.
"Data Science at Home" Podcast →
Another day, another podcast release!
This one is with the charismatic Francesco Gadaleta on his "Data Science at Home" podcast. We talked about:
How to deal with bias in machine learning used to match jobs to candidates
Guidelines to take into account whenever you implement a deep learning model
The future of AI