Adam Coates

Has AI made the world better yet? Let's get on that. Director at Apple. Fmr Stanford PhD, Director Baidu SVAIL, @khoslaventures. #deeplearning #HPC #AI

[Pieter Abbeel @pabbeel]

All materials of @berkeley_ai Deep Unsupervised Learning now up:

https://t.co/pzJQptPAdN

Great semester w/@peterxichen,@Aravind7694,@hojonathanho, and guest inst. @AlecRad,@ilyasut,A Efros,@avdnoord

Covers: AR / PixelCNN, Flow models, VAE, GAN, self-supervised learning, etc...

[Chelsea Finn @chelseabfinn]

@ankesh_anand @egrefen @ylecun I posted the slides for my model-based RL tutorial today here: https://t.co/YskkYXYWqK
Content is similar to the DRL bootcamp video 1 yr ago, but updated.

[Quoc Le @quocleix]

Bigger models are better models so we built GPipe to enable training of large models. Results: 84.3% on ImageNet with AmoebaNet (big jump from other state-of-art models) and 99% on CIFAR-10 with transfer learning. Link: https://t.co/SE7Dz2cA0g

[Bryan Catanzaro @ctnzr]

WaveGlow: A non-autoregressive generative model for speech synthesis. Our unoptimized @PyTorch inverts mel-spectrograms at 500 kHz on a V100 GPU, and is easy to train. Paper: https://t.co/E4t6avhlar Samples: https://t.co/lriR2xv3G4 Work with @DeepPrenger and @RafaelValleArt

[Adam Coates @adampaulcoates]

@MelMitchell1 So, something is surely missing; I don't know what it is; but supervised learning might be a huge part of finding it. Hence, it continues to be underestimated, even by me. 😅

[Adam Coates @adampaulcoates]

It turns out that DL's ability to make great predictions of just about anything is a still underestimated superpower. "Curve fitting" is doing some nifty things these days. 👇👇👇

[Greg Brockman @gdb]

An agent which learned to play Mario without rewards. Instead, it was incentivized to avoid "boredom" (that is, getting into states where it can predict what will happen next). Discovered warp levels, how to defeat bosses, etc. More details: https://t.co/lGw3rZUbv3

[Adam Coates @adampaulcoates]

@MelMitchell1 IMO, the lesson of DL is that we're not as clever as we think. Somehow, machines need to build the ultimate solution. Today, "supervised learning" (as a subroutine for RL, unsupervised, or meta-learning) is one heckuva tool to find solutions we could never imagine.

[Sara Hooker @sarahookr]

I have put together some thoughts about the article here: https://t.co/m1HGFQZdMj. I am concerned that the story in the Economist not only displaces my own narrative but also sets unrealistic expectations for anyone setting out in the field.

[Sara Hooker @sarahookr]

Our field needs more diversity. There must be more people like me who feel welcome and who are given the tools to succeed. However, part of preparing people to succeed is to be candid about how challenging it can be and how many failures there are along the way.

[Silectis @Silectis]

Good piece on managing competing priorities that are common to data projects

https://t.co/4hK2p8VE15 via @EmmanuelAmeisen of @InsightDataSci and @adampaulcoates of @khoslaventures
#BigData #MachineLearning #DataScience #AI #ApacheSpark

[Zico Kolter @zicokolter]

Got the "do I use an RNN or CNN for sequence modeling" blues? Use a TrellisNet, an architecture that connects these two worlds, and works better than either! New paper with @shaojieb and Vladlen Koltun.

Paper: https://t.co/PUEd2ZiFbh
Code: https://t.co/b9HUBt3JhE

[Thomas Wolf @Thom_Wolf]

I've spent most of 2018 training models that could barely fit 1-4 samples/GPU.
But SGD usually needs more than few samples/batch for decent results.
I wrote a post gathering practical tips I use, from simple tricks to multi-GPU code & distributed setups: https://t.co/oLe6JlxcVw

[Adam Coates @adampaulcoates]

This is one of the things about bias in ML that I fear the most. Many companies will build these systems innocently and have *no idea* that the algorithm has found a way to discriminate unfairly. *Everyone* in company has to stay vigilant, not just ML team.

[Peter Aldhous @paldhous]

This is being reported as a problem with machine learning, but there's another way of looking at it: The algorithm exposed bias in their *existing* hiring practices

[Chaz Firestone @chazfirestone]

The Extinction Illusion: The left side and the right side have the same number of black dots

https://t.co/meoGBt13Kn

[Yann LeCun @ylecun]

So many papers applying deep learning to theoretical and experimental physics!
Fascinating. https://t.co/F8YfsFQaDL

[Adam Coates @adampaulcoates]

I appear to be using GMail's "sentence auto-complete" feature to actively avoid low-information-content sentences. 🤔