Published Apr 10, 2023
Jonathan Frankle of MosiacML— Neural Network Pruning and Training
Jonathan Frankle, Chief Scientist at MosaicML, delves into the transformative role of customized data in neural network training while expressing skepticism about achieving AGI with current technologies, and discusses the revolutionary 'Lottery Ticket Hypothesis' that could redefine efficient model training.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Johannes Otterbach — Unlocking ML for Traditional Companies
Answers 383 questions
Richard Socher — The Challenges of Making ML Work in the Real World
Answers 383 questions
Zack Chase Lipton — The Medical Machine Learning Landscape
Answers 383 questions
Josh Tobin — Productionizing ML Models
Answers 383 questions
Piero Molino — The Secret Behind Building Successful Open Source Projects
Answers 383 questions
Nicolas Koumchatzky — Machine Learning in Production for Self-Driving Cars
Answers 383 questions
Accelerating drug discovery with AI: Insights from Isomorphic Labs
Answers 383 questions
Chip Huyen of Claypot AI— ML Research and Production Pipelines
Answers 383 questions
Jerome Pesenti — Large Language Models, PyTorch, and Meta
Answers 383 questions
Mircea Neagovici — Robotic Process Automation (RPA) and ML
Answers 383 questions
Emily M. Bender — Language Models and Linguistics
Answers 383 questions
Hamel Husain — Building Machine Learning Tools
Answers 383 questions
Chris Mattmann — ML Applications on Earth, Mars, and Beyond
Answers 383 questions
Aaron Colak — ML and NLP in Experience Management
Answers 383 questionsThe Power of AI in Search with You.com's Richard Socher
Answers 383 questions