Head to Head: The Even Bigger ML Smackdown!

Tic-Tac-Toe the Hard Way

See the agents play each other in Tic-Tac-Two!

34:07

In this insightful episode of The Innovators & Investors Podcast, host Kristian Marquez sits down with Jay Crone, Managing Director and Venture Capitalist at Deloitte Ventures, to explore the firm’s strategic approach to corporate venture capital. Jay shares Deloitte Ventures’ investment thesis, focusing on supporting innovative Canadian startups at Series A and B stages across key sectors like cybersecurity, climate tech, fintech, future of work, health tech, and AI. Listeners will gain an inside look at how Deloitte leverages its vast network of 1,500 partners and 15,000 employees to source deals and add value beyond capital by helping startups navigate Deloitte’s complex ecosystem and access enterprise clients. Jay also discusses his diverse career journey—from government and investment banking to entrepreneurship and corporate VC—and how those experiences shape his investment philosophy. The episode delves into Deloitte’s due diligence process, the importance of founder relationships, and the firm’s strategic role as a co-investor. Jay highlights emerging trends, particularly the promise of vertical AI tailored to industry-specific needs, and shares his bullish outlook on fintech innovations like stablecoins and cross-border payments. He offers candid advice for entrepreneurs on risk-taking and aligning business vision with funding goals. This episode is a must-listen for founders, investors, and anyone interested in the evolving landscape of corporate venture capital and innovation in Canada. Learn more about Jay's work at https://www.deloitte.com/ca/en/services/program/ventures.html Connect with Jay on LinkedIn at https://www.linkedin.com/in/jaycrone/ Think you'd be a great guest on the show? Apply at https://finstratmgmt.com/innovators-investors-podcast/ Want to learn more about Kristian Marquez's work? Check out his website at https://finstratmgmt.com…

5 years ago 24:26

MP3•Episode home

Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results?

For more information about the show, check out pair.withgoogle.com/thehardway/.

You can reach out to the hosts on Twitter: @dweinberger and @tafsiri.

10 episodes

#Tech #Podcasting Education #Rebecca Salois #People AI Research #Machine Learning #Human Centered #Reinforcement Learning #Supervised Learning #Tic-tac-toe #Games #Google

Head to Head: The Even Bigger ML Smackdown!

Tic-Tac-Toe the Hard Way

published 5 years ago

MP3•Episode home

Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results?

See the agents play each other in Tic-Tac-Two!

For more information about the show, check out pair.withgoogle.com/thehardway/.

You can reach out to the hosts on Twitter: @dweinberger and @tafsiri.

10 episodes

#Tech #Podcasting Education #Rebecca Salois #People AI Research #Machine Learning #Human Centered #Reinforcement Learning #Supervised Learning #Tic-tac-toe #Games #Google

All episodes

Tic-Tac-Toe the Hard Way

1
Lessons learned 33:01

5 years ago33:01

33:01

What have we learned about machine learning and the human decisions that shape it? And is machine learning perhaps changing our minds about how the world outside of machine learning — also known as the world — works? For more information about the show, check out pair.withgoogle.com/thehardway/ . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
Head to Head: The Even Bigger ML Smackdown! 24:26

5 years ago24:26

24:26

Yannick and David’s systems play against each other in 500 games. Who’s going to win? And what can we learn about how the ML may be working by thinking about the results? See the agents play each other in Tic-Tac-Two ! For more information about the show, check out pair.withgoogle.com/thehardway/ . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
Enter tic-tac-two 21:20

5 years ago21:20

21:20

David’s variant of tic-tac-toe that we’re calling tic-tac-two is only slightly different but turns out to be far more complex. This requires rethinking what the ML system will need in order to learn how to play, and how to represent that data. For more information about the show, check out pair.withgoogle.com/thehardway/ . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
Head to Head: the Big ML Smackdown! 25:19

5 years ago25:19

25:19

David and Yannick’s tic-tac-toe ML agents face-off against each other in tic-tac-toe! See the agents play each other ! For more information about the show, check out pair.withgoogle.com/thehardway/ . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .

Tic-Tac-Toe the Hard Way

1
Give that model a treat! : Reinforcement learning explained 26:04

5 years ago26:04

26:04

Switching gears, we focus on how Yannick’s been training his model using reinforcement learning. He explains the differences from David’s supervised learning approach. We find out how his system performs against a player that makes random tic-tac-toe moves. Resources: Deep Learning for JavaScript book Playing Atari with Deep Reinforcement Learning Two Minute Papers episode on Atari DQN For more information about the show, check out pair.withgoogle.com/thehardway/ . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
Beating random: What it means to have trained a model 17:14

5 years ago17:14

17:14

David did it! He trained a machine learning model to play tic-tac-toe! (Well, with lots of help from Yannick.) How did the whole training experience go? How do you tell how training went? How did his model do against a player that makes random tic-tac-toe moves? For more information about the show, check out pair.withgoogle.com/thehardway/ . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
From tic-tac-toe moves to ML model 21:37

5 years ago21:37

21:37

Once we have the data we need—thousands of sample games--how do we turn it into something the ML can train itself on? That means understanding how training works, and what a model is. Resources: See a definition of one-hot encoding For more information about the show, check out pair.withgoogle.com/thehardway . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
What does a tic-tac-toe board look like to machine learning? 23:26

5 years ago23:26

23:26

How should David represent the data needed to train his machine learning system? What does a tic-tac-toe board “look” like to ML? Should he train it on games or on individual boards? How does this decision affect how and how well the machine will learn to play? Plus, an intro to reinforcement learning, the approach Yannick will be taking. For more information about the show, check out pair.withgoogle.com/thehardway . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
Howdy, and the myth of “pouring in data” 22:01

5 years ago22:01

22:01

Welcome to the podcast! We’re Yannick and David, a software engineer and a non-technical writer. Over the next 9 episodes we’re going to use two different approaches to build machine learning systems that play two versions of tic-tac-toe. Building a machine learning app requires humans making a lot of decisions. We start by agreeing that David will use a “supervised learning” approach while Yannick will go with “reinforcement learning.” For more information about the show, check out pair.withgoogle.com/thehardway . You can reach out to the hosts on Twitter: @dweinberger and @tafsiri .…

Tic-Tac-Toe the Hard Way

1
Introducing Tic-Tac-Toe the Hard Way 2:09

5 years ago2:09