Ian Goodfellow (@goodfellow

Ian Goodfellow

2,996 posts

Ian Goodfellow

@goodfellow_ian

Co-founder of stealth startup. Inventor of GANs. Lead author of deeplearningbook.org Founding chairman of @pubhealthaction

San Francisco, CA

iangoodfellow.com

Joined September 2016

Ian Goodfellow
@goodfellow_ian
Jul 6, 2022
I'm excited to announce that I've joined DeepMind! I'll be a research scientist in @OriolVinyalsML 's Deep Learning team.
Ian Goodfellow
@goodfellow_ian
Dec 3, 2017
One of my favorite samples from the Progressive GANs paper is this one from the "cat" category. Apparently some of the cat training photos were memes with text. The GAN doesn't know what text is so it has made up new text-like imagery in the right place for a meme caption.
Ian Goodfellow
@goodfellow_ian
Jan 9, 2018
I never heard back from MIT. I got rejected from CMU. I was accepted to U of T but not to work with the PI I wanted there. I got "honorable mention" for NSF GRFP but not actual money. Don't let temporary failures discourage you.
Ian Goodfellow
@goodfellow_ian
Jan 15, 2019
4.5 years of GAN progress on face generation. arxiv.org/abs/1406.2661 arxiv.org/abs/1511.06434 arxiv.org/abs/1606.07536 arxiv.org/abs/1710.10196 arxiv.org/abs/1812.04948
Ian Goodfellow
@goodfellow_ian
Apr 9, 2017
CycleGAN turning a horse video into a zebra video ( github.com/junyanz/CycleG… )
GIF
Ian Goodfellow
@goodfellow_ian
Oct 16, 2025
More of what my colleagues and I have been working on in AI for fusion is public now
Google DeepMind
@GoogleDeepMind
Oct 16, 2025
We’re announcing a research collaboration with @CFS_energy, one of the world’s leading nuclear fusion companies. Together, we’re helping speed up the development of clean, safe, limitless fusion power with AI. ⚛️
288K
Ian Goodfellow
@goodfellow_ian
Mar 3, 2018
4 years of GAN progress (source: eff.org/files/2018/02/… )
Ian Goodfellow
@goodfellow_ian
Oct 3, 2020
This exciting new PyTorch library includes quite a lot of the GANs I've featured in my talks over the past few years, all in one place!
Ian Goodfellow
@goodfellow_ian
Apr 15, 2019
OctConv is a simple replacement for the traditional convolution operation that gets better accuracy with fewer FLOPs export.arxiv.org/abs/1904.05049
Ian Goodfellow
@goodfellow_ian
Jul 11, 2019
I’m in Fortune’s 40 under 40: fortune.com/40-under-40/20…
Ian Goodfellow
@goodfellow_ian
Dec 14, 2024
When Schmidhuber interrupted my talk on GANs in 2016, he did so at the time I was giving credit to relevant prior work: noise contrastive estimation. Schmidhuber isn’t about proper about academic credit assignment, he’s about self-aggrandizement.
755K
Ian Goodfellow
@goodfellow_ian
Nov 29, 2017
ML researchers, reviewers, and press coverage of ML need to get a lot more serious about statistically robustness of results and the effect of hyperparameters. This study shows that many papers over the last year or so were just observing sampling error, not true improvement.
Karol Kurach
@karol_kurach
Nov 29, 2017
Are GANs Created Equal? A Large-Scale Study arxiv.org/abs/1711.10337
Ian Goodfellow
@goodfellow_ian
Nov 24, 2024
Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread
370K
Ian Goodfellow
@goodfellow_ian
Feb 24, 2018
By looking at this image, you can see how sensitive your own eyes are to contrast at different frequencies (taller apparent peaks=more sensitivity at that frequency). It's like a graph that is made by perceiving the graph itself. h/t @catherineols fourier.eng.hmc.edu/e180/lectures/…