Prova Storytel gratis i 30 dagar Ett universum fyllt av ljudböcker, klicka här för att komma igång

Tic-Tac-Toe the Hard Way

En podcast av: People + AI Research

A writer and a software engineer from Google's People + AI Research team explore the human choices that shape machine learning systems by building competing tic-tac-toe agents.

Our American listeners can also listen to Tic-Tac-Toe the Hard Way at our American site

10 Avsnitt

Lessons learned
Publicerades 2020-07-22

Head to Head: The Even Bigger ML Smackdown!
Publicerades 2020-07-22
Enter tic-tac-two
Publicerades 2020-07-22
Head to Head: the Big ML Smackdown!
Publicerades 2020-07-22
Give that model a treat! : Reinforcement learning explained
Publicerades 2020-07-22
Beating random: What it means to have trained a model
Publicerades 2020-07-22
From tic-tac-toe moves to ML model
Publicerades 2020-07-22
What does a tic-tac-toe board look like to machine learning?
Publicerades 2020-07-22
Howdy, and the myth of “pouring in data”
Publicerades 2020-07-21
Introducing Tic-Tac-Toe the Hard Way
Publicerades 2020-07-21

A writer and a software engineer from Google's People + AI Research team explore the human choices that shape machine learning systems by building competing tic-tac-toe agents.

10 Avsnitt

Lessons learned

Head to Head: The Even Bigger ML Smackdown!

Enter tic-tac-two

Head to Head: the Big ML Smackdown!

Give that model a treat! : Reinforcement learning explained

Beating random: What it means to have trained a model

From tic-tac-toe moves to ML model

What does a tic-tac-toe board look like to machine learning?

Howdy, and the myth of “pouring in data”

Introducing Tic-Tac-Toe the Hard Way