Podcast Episodes

OpenAI GPT-3: Language Models are Few-Shot Learners

Season 1 Episode 9

In this episode of Machine Learning Street Talk, Tim Scarfe, Yannic Kilcher and Connor Shorten discuss their takeaways from OpenAI’s GPT-3 language model. With the help of Microsoft’s ZeRO-2 / DeepSp…

Published on 5 years, 3 months ago

Jordan Edwards: ML Engineering and DevOps on AzureML

Season 1 Episode 9

This week we had a super insightful conversation with  Jordan Edwards, Principal Program Manager for the AzureML team!  Jordan is on the coalface of turning machine learning software engineering into…

Published on 5 years, 3 months ago

One Shot and Metric Learning - Quadruplet Loss (Machine Learning Dojo)

Season 1 Episode 8

*Note this is an episode from Tim's Machine Learning Dojo YouTube channel. 

Join Eric Craeymeersch on a wonderful discussion all about ML engineering, computer vision, siamese networks, contrastive l…

Published on 5 years, 3 months ago

Harri Valpola: System 2 AI and Planning in Model-Based Reinforcement Learning

Season 1 Episode 7

In this episode of Machine Learning Street Talk, Tim Scarfe, Yannic Kilcher and Connor Shorten interviewed Harri Valpola, CEO and Founder of Curious AI. We continued our discussion of System 1 and Sy…

Published on 5 years, 3 months ago

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Season 1 Episode 6

In this episode of Machine Learning Street Talk, Tim Scarfe, Connor Shorten and Yannic Kilcher react to Yoshua Bengio’s ICLR 2020 Keynote “Deep Learning Priors Associated with Conscious Processing”. …

Published on 5 years, 3 months ago

ICLR 2020: Yann LeCun and Energy-Based Models

Season 1 Episode 5

This week Connor Shorten, Yannic Kilcher and Tim Scarfe reacted to Yann LeCun's keynote speech at this year's ICLR conference which just passed. ICLR is the number two ML conference and was completel…

Published on 5 years, 3 months ago

The Lottery Ticket Hypothesis with Jonathan Frankle

In this episode of Machine Learning Street Talk, we chat with Jonathan Frankle, author of The Lottery Ticket Hypothesis. Frankle has continued researching Sparse Neural Networks, Pruning, and Lottery…

Published on 5 years, 3 months ago

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Season 1 Episode 3

In this episode of Machine Learning Street Talk, Tim Scarfe, Yannic Kilcher and Connor Shorten chat about Large-scale Transfer Learning in Natural Language Processing. The Text-to-Text Transfer Trans…

Published on 5 years, 3 months ago

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

Season 1 Episode 2

According to Yann Le Cun, the next big thing in machine learning is unsupervised learning. Self-supervision has changed the entire game in the last few years in deep learning, first transforming the …

Published on 5 years, 4 months ago

Exploring Open-Ended Algorithms: POET

Season 1 Episode 1

Three YouTubers; Tim Scarfe - Machine Learning Dojo (https://www.youtube.com/channel/UCXvHuBMbgJw67i5vrMBBobA), Connor Shorten - Henry AI Labs (https://www.youtube.com/channel/UCHB9VepY6kYvZjj0Bgxnpb…

Published on 5 years, 4 months ago