Your Daily AI Research tl;dr — 2022–09–19

https://miro.medium.com/max/1200/0*H9hBbu8j8Tq4dZEQ

Original Source Here

Welcome to your official daily AI research tl;dr (often with code and news) for AI professionals where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating.

1️⃣ Human-level Atari 200x faster

A new deepmind paper:

“Agent57 was the first agent to surpass the human benchmark on all 57 games, but this came at the cost of poor data-efficiency, requiring nearly 80 billion frames of experience to achieve.”

Starting with Agent57, they employ a diverse set of strategies to achieve a 200-fold reduction of experience needed to outperform the human baseline.

2️⃣ Brain Imaging Generation with Latent Diffusion Models 

Using Latent Diffusion Models to generate synthetic images from high-resolution 3D brain images.

Comment by the creator of Keras, François Chollet: It’s faster, it’s more concise, the code is elegant. You can add TPU and multi-GPU inference in 1 line. You can export the model to TF.js or TFLite for on-device inference.

Quick summary of the Tensorflow implementation:

– Converted pre-trained models

– Easy to understand code

– Minimal code footprint

Please subscribe and share the newsletter with your AI techy friends if it was helpful and join our 4’000+ readers. Feel free to follow my weekly newsletter where I go in-depth into one of the papers shared, and our newsletter at Towards AI, sharing the most exciting news, papers, articles, and memes weekly.

Thank you for reading,

Louis

AI/ML

Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: