Show Notes:

• (2:02) Josh studied Mathematics at Columbia University during his undergraduate and explained why he was not set out for a career as a mathematician.
• (3:55) Josh then worked for two years as a Management Consultant at McKinsey.
• (6:05) Josh explained his decision to go back to graduate school and pursue a Ph.D. in Mathematics at UC Berkeley.
• (7:23) Josh shared the anecdote of taking a robotics class with professor Pieter Abbeel and switching to a Ph.D. in the Computer Science department at UC Berkeley.
• (8:50) Josh described the period where he learned programming to make the transition from Math to Computer Science.
• (10:46) Josh talked about the opportunity to collaborate and then work full-time as a Research Scientist at OpenAI - all during his Ph.D.
• (12:40) Josh discussed the sim2real problem, as well as the experiments conducted in his first major work "Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model".
• (17:43) Josh discussed his paper "Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World", which has been cited more than 600 times up until now.
• (20:51) Josh unpacked the OpenAI’s robotics system that was trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once (Read the blog post “Robots That Learn” and watch the corresponding video).
• (24:01) Josh went over his work on Hindsight Experience Replay - a novel technique that can deal with sparse and binary rewards in Reinforcement Learning (Read the blog post “Generalizing From Simulation").
• (28:41) Josh talked about the paper "Domain Randomization and Generative Models for Robotic Grasping”, which (1) explores a novel data generation pipeline for training a deep neural network to perform grasp planning that applies the idea of domain randomization to object synthesis; and (2) proposes an autoregressive grasp planning model that maps sensor inputs of a scene to a probability distribution over possible grasps.
• (32:27) Josh unpacked the design of OpenAI's Dactyl - a reinforcement learning system that can manipulate objects using a Shadow Dexterous Hand (Read the paper “Learning Dexterous In-Hand Manipulation” and watch the corresponding video).
• (35:31) Josh reflected on his time at OpenAI.
• (36:05) Josh investigated his most recent work called “Geometry-Aware Neural Rendering” - which tackles the neural rendering problem of understanding the 3D structure of the world implicitly.
• (28:21) Check out Josh's talk "Synthetic Data Will Help Computer Vision Make the Jump to the Real World" at the 2018 LDV Vision Summit in New York.
• (28:55) Josh summarized the mental decision tree to debug and improve the performance of neural networks, as a reference to his talk "Troubleshooting Deep Neural Networks” at Reinforce Conf 2019 in Budapest.
• (41:25) Josh discussed the limitations of domain randomization and what the solutions could look like, as a reference to his talk "Beyond Domain Randomization” at the 2019 Sim2Real workshop in Freiburg.
• (44:52) Josh emphasized the importance of working on the right problems and focusing on the core principles in machine learning for junior researchers who want to make a dent in the AI research community.
• (48:30) Josh is a co-organizer of Full-Stack Deep Learning, a training program for engineers to learn about production-ready deep learning.
• (50:40) Closing segment.

His Contact Information:

• Website
• LinkedIn
• Twitter
• GitHub
• Google Scholar

His Recommended Resources:

• Full-Stack Deep Learning
• Pieter Abbeel
• Ilya Sutskever
• Lukas Biewald
• “Thinking Fast and Slow” by Daniel Kahneman

This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit datacast.substack.com/subscribe