discover machine learning

sharing hidden gems, announcements, and latest news in machine learning • by @duygu_islakoglu

[discover machine learning @discover_ml]

Self-attention and Transformers https://t.co/VmNlWaX4Bx

[Jim Fan @DrJimFan]

Another blockbuster AI startup in town! Congrats David @hardmaru & Llion @YesThisIsLion on launching https://t.co/cKPGb3ZL5k!

David's got a very unique & refreshing research taste. He also writes inspiring blogs like @karpathy does.

My favorites:
- World Model: coauthored w/ @SchmidhuberAI, world model is an AI agent's "dream space" of possible future outcomes. It's one of the OG self-supervised sequence models for decision making. https://t.co/tWDuQRNTRh
- SketchRNN: teaching an RNN to draw, not by generating pixels like Stable Diffusion, but by controlling a virtual pen to paint each stroke like a human kid. https://t.co/7Vopp13w4Z
- HyperNetwork: a smaller NN generates the weights for a larger NN. If NN compresses the training data, HyperNet basically does a 2nd order compression. https://t.co/gGYwh2Ut5k
- Weight-agnostic NN: instead of using SGD to find the best parameters, use search to find the best NN architecture configuration while keeping the weights fixed. Quite a radical approach.
https://t.co/fEBKuMRx8H
- Visualization of evolution strategies, an alternative to reinforcement learning. https://t.co/SoEHhqdnn5
- Collective intelligence: how globally intelligent behaviors emerge if you scale up simple, local interactions massively. Lots of cool examples: https://t.co/jv8wxEiZxd
- Many more posts here: https://t.co/u14IF8ldde

Academia abounds with incremental papers, and creative perspectives are increasingly rare.

[discover machine learning @discover_ml]

https://t.co/mhwtKjHLSF

[discover machine learning @discover_ml]

https://t.co/AvcHGyzs0Z

[Eliya Nachmani @NachmaniEliya]

Our new paper at @GoogleResearch gives your LLM the ability to talk 🔊!

Paper: https://t.co/WamqjqSQpw
Audio Samples: https://t.co/Z1PiwMupwM

[Boris Power @BorisMPower]

State of GPT by @karpathy - a wonderful intro and overview of the state of LLMs 🚀 https://t.co/aEwvW457lO

[discover machine learning @discover_ml]

8. [Prompt Papers]
https://t.co/suQCO7lrHK

[discover machine learning @discover_ml]

7. [Awesome ChatGPT Prompts] https://t.co/SttIREUad5

[Google AI @GoogleAI]

Watch the first episode of #ResearchRetrospectives, where @katherine1ee and @savvyRL interview @ZoubinGhahrama1, VP of Google Research. Learn about his career background and insights on how to navigate the field of research ↓ https://t.co/bhcn0znwzI

[discover machine learning @discover_ml]

https://t.co/suQCO7lrHK

[discover machine learning @discover_ml]

The easiest way to work with large language models | Learn LangChain in 10min
https://t.co/6H1nYD05bi

[discover machine learning @discover_ml]

https://t.co/jMhadMR90H

[Pranav Rajpurkar @pranavrajpurkar]

I am truly excited to launch my e-book, AI Research Experiences.

Features 250+ pages of comprehensive notes and insights from my Harvard course, CS197.

Covers technical AI toolkits and research skills to take your AI journey to the next level.
It's free.
https://t.co/Nl9TGXkbut

[Michael Black @Michael_J_Black]

I asked #Galactica about some things I know about and I'm troubled. In all cases, it was wrong or biased but sounded right and authoritative. I think it's dangerous. Here are a few of my experiments and my analysis of my concerns. (1/9)