The Linear Algebra classes of my "ML Foundations" curriculum, offered via the O'Reilly Media platform, are in the rear-view mirror. Two Calculus classes are coming up soon and the Probability classes just opened for registration:
• Sep 15 — Calculus III: Partial Derivatives
• Sep 22 — Calculus IV: Gradients and Integrals
• Oct 6 — Intro to Probability
• Oct 13 — Probability II and Information Theory
• Oct 27 — Intro to Statistics
Overall, four subject areas are covered:
• Linear Algebra (3/3 classes DONE)
• Calculus (2/4 classes DONE)
• Probability and Statistics (4 classes)
• Computer Science (3 classes)
Hope to see you in class! Sign up opens about two months prior to each class. All of the training dates and registration links are provided at jonkrohn.com/talks
A detailed curriculum and all of the code for my ML Foundations series is available open-source in GitHub here.
The Line Equation as a Tensor Graph
New YouTube video today — it's meaty! In it, we get ourselves set up for applying Machine Learning from scratch by using the popular Python library PyTorch to create a Tensor Graph representation of a simple line equation.
Next week, we'll publish a massive 40-minute video that builds on the Tensor Graph representation introduced this week in order to use Automatic Differential Calculus within a Machine Learning loop and fit a Regression line to data points.
If you're familiar with differential calculus but not machine learning, this pair of videos will fill in all the gaps for you on how ML works. If you're not familiar with differential calculus, the preceding videos in my "Calculus for Machine Learning" course will provide you with all of the foundational theory you need for ML.
We publish a new video from my "Calculus for Machine Learning" course to YouTube every Wednesday. Playlist is here.
More detail about my broader "ML Foundations" curriculum and all of the associated open-source code is available in Github here.
Data Meshes and Data Reliability
The fun and brilliant Barr Moses joins me this week to detail for us what organization-transforming Data Meshes are, as well as how to track and improve the "Data Uptime" (reliability) of your production systems.
Barr is co-founder and CEO of Monte Carlo, a venture capital-backed start-up that has grown in head count by a remarkable 10x in the past year. Monte Carlo specializes in data reliability, making sure that the data pipelines used for decision-making or production models are available 24/7 and that the data are high quality.
In this SuperDataScience episode, Barr covers:
• What data reliability is, including how we can monitor for the "good pipelines, bad data" problem
• How reliable data enables the creation of a Data Mesh that empowers data-driven decision-makers across all of the departments of a company to independently create and analyze data
• How to build a data science team
• How to get a data-focused start-up off the ground, generating revenue and rapidly scaled up
In addition, Barr took time to answer questions from listeners, including those from Svetlana, Bernard, and A Ramesh. Thanks to Scott Hirleman for suggesting Barr as a guest on the show and thanks to Molly Vorwerck for ensuring everything ran perfectly.
Listen or watch here.
Tutorial on "Big O Notation"
Brand-new, hands-on intro to "Big O Notation" — an essential computer science concept. "Big O" allows us to weigh the compute-time vs memory-usage trade-offs of all algorithms, including machine learning models.
This YouTube video is a 45-minute, standalone excerpt from my six-hour "Data Structures, Algorithms, and ML Optimization" course, which focuses on code demos in Python to make understanding concepts intuitive, fun, and interactive.
If you have an O'Reilly Media subscription, the full course was recently published here.
If you'd like to purchase the course, Pearson is offering it this week (until August 28th) at a 70% discount as their "Video Deal of the Week". The URL for this unusually deep discount is here.
This "DSA and ML Optimization" course is the fourth and final quarter of my broader ML Foundations curriculum. All of the associated code is available open-source via GitHub.
How Only Beginners Know Everything
For Five-Minute Friday, I review a paradoxical pattern I've noticed in myself and in many early-career data scientists: We think we know everything. That is, until we advance past being novices and discover we're not so great.
Listen or watch here.
AI Recruitment Technology & Deep Learning - Guest Appearance on the Engineered-Mind Podcast
Thanks to Jousef Murad for having me on the popular Engineered-Mind podcast.! Jousef had deeply insightful questions and I enjoyed the experience immensely :)
I spoke with Jousef back in April 2021, where we discussed:
- untapt and how AI powered recruiting works
- My background in neuroscience
- Where to get started when learning ML
- Tips for becoming a deep learning specialist
- What is I’m most excited about in terms of AI
- How I come up with the idea of writing a book
You can listen to the podcast anywhere podcasts are available including Apple Podcasts, Spotify, and Anchor.fm. You can also check out the video directly on YouTube here.
AutoDiff with TensorFlow
PyTorch and TensorFlow are by far the two most widely-used automatic-differentiation libraries. Last week, we used PyTorch to differentiate an equation automatically and instantaneously. Today, we do it with TensorFlow.
(For an overview of the pros and cons of PyTorch versus TensorFlow, I've got a talk here. The TLDR is you should know both!)
A new video for my "Calculus for ML" course published on YouTube every Wednesday. Playlist is here.
More detail about my broader "ML Foundations" curriculum and all of the associated open-source code is available in GitHub here.
Maximizing the Global Impact of Your Career
This week, expert Benjamin Todd details how you can find purpose in your work and maximize the global impact of your career. In particular, he emphasizes how data scientists can exert a massive positive influence.
In this mind-expanding and exceptionally inspiring episode, Ben details:
• An effective process for evaluating next steps in your career
• A data-driven guide to the most valuable skills for you to obtain regardless of profession
• Specific impact-maximizing career options that are available to data scientists and related professionals, such as ML engineers and software developers.
Ben has invested the past decade researching how people can have the most meaningful and impactful careers. This research is applied to great effect via his charity 80,000 Hours, which is named after the typical number of hours worked in a human lifetime. The Y Combinator-backed charity has reached over eight million people via its richly detailed, exceptionally thoughtful, and 100% free content and coaching.
Listen or watch here.
Why The Best Data Scientists have Mastered Algebra, Calculus and Probability
Over the past year, I've published dozens of hours of video tutorials on the mathematical foundations that underlie machine learning and data science. In this talk, I explain *why* knowing this math is so essential.
Thanks to Roberto Lambertini and SuperDataScience for hosting it!
A Brain-Computer Interface Story
For Five-Minute Friday this week, I tried something different: I wrote a short sci-fi story! Let me know if you liked it or hated it and, based on your feedback, I'll either do more of it or consider never doing it again :)
Watch or listen here.
AutoDiff with PyTorch
Over the past month, we've covered all the key rules for differentiating equations by hand. In today's YouTube video, we use PyTorch to differentiate equations automatically and instantaneously.
A new video for my "Calculus for ML" course published on YouTube every Wednesday. Playlist is here.
More detail about my broader "ML Foundations" curriculum and all of the associated open-source code is available in GitHub here.
Successful AI Projects and AI Startups
This week, the rockstar Greg Coquillo fills us in on how to get a return on investment in A.I. projects and A.I. start-ups. He also introduces Quantum Machine Learning.
In addition, through responding to audience questions, Greg details:
• Element AI's maturity framework for A.I. businesses
• How A.I. startup success comes from understanding your long-term business strategy while iterating tactically
• How machines typically are much faster than people but tend to be less accurate
(Thanks to Bernard, Serg, Kenneth, Nikolay, and Yousef for the questions!)
Greg is LinkedIn's current "Top Voice for A.I. and Data Science". When he's not sharing succinct summaries of both technically-oriented and commercially-oriented A.I. developments with his LinkedIn followers, Greg's a technology manager at Amazon's global HQ in Seattle. Originally from Haiti, Greg obtained his degrees in industrial engineering and engineering management from the University of Florida before settling into a series of management-level process-engineering roles.
Listen or watch here.
A4N Episode 5: We're on Pause for Now!
In this episode of A4N, I have a special announcement! While the A4N podcast will be going on indefinite hiatus, it is because I am now hosting the SuperDataScience Podcast. If you enjoyed A4N then you're sure to enjoy the SuperDataScience podcast, which publishes twice every week on Tuesdays and Fridays!
You can check it out here.
How to Instantly Appreciate Being Alive
In today's always-connected world, it's easy to get caught up in thought after thought after thought. For Five-Minute Friday this week, here's a trick to jolt yourself into the present and bask in the simple appreciation of being alive.
Listen or watch here.
Filming ""Data Structures, Algorithms, and Machine Learning Optimization"" LiveLessons
Silly times on set filming my "Data Structures, Algorithms, and Machine Learning Optimization" videos, which — over 6.5 interactive hours — introduce critical Computer Science concepts for ML and Data Science.
These videos were recently published in the O'Reilly Media platform.
These CS-focused videos are the fourth and final quarter of the subject areas covered in my broader "ML Foundations" curriculum — the first three being Linear Algebra, Calculus, and Probability. All of the code from the curriculum is available open-source in GitHub.
And my "Math for ML" playlist on O'Reilly captures all of the videos in this curriculum in one place.
AutoDiff Explained
New YouTube video live! This one introduces what Automatic Differentiation — a technique that allows us to scale up the computation of derivatives to machine-learning scale — is.
A new video for my "Calculus for ML" course published on YouTube every Wednesday. Playlist is here.
More detail about my broader "ML Foundations" curriculum and all of the associated open-source code is available in GitHub here.
Bringing Data to the People
This week's guest is super-cool Anjali Shrivastava. Anjali makes data accessible and broadly appealing by analyzing pop culture — from TikTok mansions to Star Wars timelines — in her fun and creative YouTube videos.
Anjali is an expert in data-science visualization. She has used this skill set to engineer visualizations of data in production systems in a number of roles and recently took up a data science role at the lab technology giant Thermo Fisher Scientific.
We dig into her technical expertise, including her favorite software tools and applications for viz. We also discuss Anjali's mission to bring a face to data, which she accomplishes through journalism as well as through her brilliant and fun "Vastava" YouTube channel.
Anjali holds dual degrees from the prestigious University of California, Berkeley in data science, as well as in industrial engineering and operations research. A recent graduate, she fill us in on what a data science degree curriculum is like at a top university like Berkeley, as well as how anyone can access their world class data science lectures online.
Listen or watch here.
The World is Awful (and it’s Never Been Better)
Feel like the world is kinda poopy? Well, it is! BUT, covid pandemic not withstanding, it's also WAY better than ever before. I articulate this idea with data and charts for this week's Five-Minute Friday episode.
Thanks to Benjamin Todd for pointing me in the direction of a blog post by Max Roser (founder of Our World in Data) that formed the basis of this podcast episode.
Watch or listen here.
Automatic Differentiation – Segment 3 of Subject 3, "Limits & Derivatives" – Machine Learning Foundations
Automatic Differentiation is a computational technique that allows us to move beyond calculating derivatives by hand and scale up the calculation of derivatives to the massive scales that are common in machine learning.
The YouTube videos in this segment, which we'll release every Wednesday, introduce AutoDiff in the two most important Python AutoDiff libraries: PyTorch and TensorFlow.
My growing "Calculus for ML" course is available on YouTube here.
More detail about my broader "ML Foundations" curriculum and all of the associated open-source code is available in GitHub here.
R in Production
Dutch national-podium-level powerlifter Veerle van Leemput joins me this week to detail how R is not only an option for production, but may in fact be the *best* production option if data models are central to your application.
Over the course of the episode, Veerle runs down for us her favorite R tools for:
• Data gathering
• Model development
• Deployment into production systems
Veerle has held a number of data-science leadership roles at Dutch companies. She now serves as Managing Director and Head of Data Science at Analytic Health, a London-based firm that builds data-centric software for the healthcare industry. And she was silver medalist in the 57kg class of the 2021 Dutch national powerlifting championships with a total of 335kg (~739 pounds) across the back squat, bench press, and deadlift.
Listen or watch here.