Robots Must Be Ephemeralized
Eric Jangby noreply@blogger.com (Unknown)20 Sept 2021
In a previous blog post, I also discussed how iterating in simulation solves some tricky problems around new code changes invalidating old data.
Eric Jang
blog.evjang.comadded August 2026
27%Stonks are What You Can Get Away With: NFTs and Financial Nihilism
Eric Jangby noreply@blogger.com (Unknown)19 Jun 2021
Andy Warhol once said, “Art is what you can get away with.” I interpret the quote as a nihilistic take on “beauty is in the eye of the beholder” — a urinal you found in the junkyard can be...
Sovereign Arcade: Currency as High-Margin Infrastructure
Eric Jangby noreply@blogger.com (Unknown)27 May 2021
Money allows goods, services, and everything else under the sun to be assigned a value using the same unit of measurement. Without money, society reverts to bartering, which is highly inefficient.
Science and Engineering for Learning Robots
Eric Jangby noreply@blogger.com (Unknown)14 Mar 2021
This is the text version of a talk I gave on March 12, 2021, at the Brown University Robotics Symposium. As always, all views are my own, and do not represent those of my employer.
Don't Mess with Backprop: Doubts about Biologically Plausible Deep Learning
Eric Jangby noreply@blogger.com (Unknown)13 Feb 2021
Biologically Plausible Deep Learning (BPDL) is an active research field at the intersection of Neuroscience and Machine Learning, studying how we can train deep neural networks with a "learning...
How to Understand ML Papers Quickly
Eric Jangby noreply@blogger.com (Unknown)26 Jan 2021
The nice thing about reading most ML papers is that you can cut through the jargon by asking just five simple questions. I try to answer these questions as quickly as I can when skimming papers.
My Criteria for Reviewing Papers
Eric Jangby noreply@blogger.com (Unknown)27 Sept 2020
Xiaoyi Yin (尹肖贻) has kindly translated this post into Chinese (中文) Accept-or-reject decisions for the NeurIPS 2020 conference are out, with 9454 submissions and 1900 accepted papers (20% acceptance...
Free Office Hours for Non-Traditional ML Researchers
Eric Jangby noreply@blogger.com (Unknown)20 Jun 2020
This post was prompted by a tweet I saw from my colleague, Colin: I'm currently a researcher at Google with a "non-traditional background", where non-traditional background means "someone who...
Three Questions that Keep Me Up at Night
Eric Jangby noreply@blogger.com (Unknown)2 Apr 2020
Q1: Can we imitate "thinking" from only observing behavior? Suppose you have a large fleet of autonomous vehicles with human operators driving them around diverse road conditions.
Selected Quotes from "The Dark Ages of AI Panel Discussion"
Eric Jangby noreply@blogger.com (Unknown)26 Dec 2019
In 1984, a panel at the AAAI conference discussed whether the field was approaching an "AI Winter".
Differentiable Path Tracing on the GPU/TPU
Eric Jangby noreply@blogger.com (Unknown)29 Nov 2019
This blog post is a tutorial on implementing path tracing, a physically-based rendering algorithm, in JAX.
Robinhood, Leverage, and Lemonade
Eric Jangby noreply@blogger.com (Unknown)6 Nov 2019
The Content is for informational purposes only, you should not construe any such information or other material as legal, tax, investment, financial, or other advice.
Tips for Training Likelihood Models
Eric Jangby noreply@blogger.com (Unknown)5 Jul 2019
This is a tutorial on common practices in training generative models that optimize likelihood directly, such as autoregressive models and normalizing flows.
Lessons from AI Research Projects: The First 3 Years
Eric Jangby noreply@blogger.com (Unknown)24 May 2019
I've been at Google Brain robotics (now referred to as Robotics @ Google) for nearly 3 years. It's helpful to reflect, from time to time, on the scientific, engineering and personal productivity...
Fun with Snapchat's Gender Swapping Filter
Eric Jangby noreply@blogger.com (Unknown)13 May 2019
I was so duly impressed that I signed up for Snapchat and fiddled around with it this morning to try and figure out what's going on under the hood and how I might break it.
What I Cannot Control, I Do not Understand
Eric Jangby noreply@blogger.com (Unknown)10 Mar 2019
I often hear the remark around the proverbial AI watering hole that there are no examples of reinforcement learning (RL) deployed in commercial settings that couldn’t be replaced by simpler...
Thoughts on the BagNet Paper
Eric Jangby noreply@blogger.com (Unknown)6 Feb 2019
Disclaimer: I wasn't a reviewer of this paper for ICLR. I think it was worthy of acceptance to the conference, and hope it prompts further investigation by the research community.
Uncertainty: a Tutorial
Eric Jangby noreply@blogger.com (Unknown)28 Dec 2018
Chinese translation by Xiaoyi Yin Notions of uncertainty are tossed around in conversations around AI safety, risk management, portfolio optimization, scientific measurement, and insurance.
Dijkstra's in Disguise
Eric Jangby noreply@blogger.com (Unknown)8 Aug 2018
Dijkstra's, Bellman-Ford, Johnson's, Floyd-Warshall are good algorithms for solving the shortest paths problem.