ML Review

Latest Machine Learning Papers, Lectures, Projects etc.

[ML Review @ml_review]

✨🎓🏆 Machine Learning Digest №11 🏆🎓✨

Highlighted Research Papers, Projects, Articles, and Videos.

https://t.co/PRgeC22juG

[ML Review @ml_review]

Elegant idea

@AndrzOdrz shows standard elementary functions can be built from just

EML(x,y)=exp(x)-ln(y) and 1

Boolean logic - NAND
Elementary math - EML. @PMocz built a two-button calc - https://t.co/XN24EctM81

Useful for symbolic-regression grammar
https://t.co/hYKOCRC8yp

[ML Review @ml_review]

5/ Adversarial Attacks

🔹LLM-Inherited: jailbreaks, prompt injections, data extraction
🔹Agent-Specific: knowledge poisoning, untrusted tool call, backdoor insertion, environment injection

🔓 Jailbreak Methods: Universal suffix gradient search, AutoDAN, and Crescendo

[ML Review @ml_review]

1/ "Language Agents: Foundations, Prospects, and Risks" #emnlp2024

Tutorial by @ysu_nlp @Diyi_Yang @ShunyuYao12 @taoyds

📑 Slides: https://t.co/cyxzjkH5YN
🎥 Video: https://t.co/judRGfOzzz

[ML Review @ml_review]

4/ RAG → HippoRAG (RAG + Knowledge Graph + PageRank) by @bernaaaljg

Outperforms SoTA multi-hop QA by up to 20%
While being 10-30x faster and 6-13x cheaper.

📄 Paper: https://t.co/3vyPAxL9Hj
🐙 Code: https://t.co/jLJtNSbUvl

[ML Review @ml_review]

"The Little Book of Deep Learning" 140 pp📖
Book by @francoisfleuret 🫡

https://t.co/j5J2PTxEDW

[ML Review @ml_review]

@unsorsodicorda @solvay_1927 GPT4All, Dolly, Flan-Alpaca, and ChatRWKV as "no commercial use" instruct-tuned LLMs

And OpenChatKit as the only true Apache 2.0. This time I'd also include FLAN-T5

[ML Review @ml_review]

@solvay_1927 Plausible, if so I was misled by Alpaca release: "the instruction data is based on OpenAI’s text-davinci-003, whose terms of use prohibit developing models that compete with OpenAI"

Sadly, all of the above models still suffer from LLaMa or Alpaca restrictive license

[ML Review @ml_review]

@dezhou @DivGarg9 @markchen90 @giffmana @adityagrover_ @barret_zoph @drew_jaegle @aidangomezzz @ch402 Hope not from the movie, there is only One True "Transformers"

[ML Review @ml_review]

"Stanford CS25 - Transformers United"

Seminar by @DivGarg9 @markchen90 @giffmana @adityagrover_ @barret_zoph @drew_jaegle @aidangomezzz @ch402 Geoffry Hinton

Covers Transformers in Language, Vision, Decision-Making, Audio

https://t.co/DuSJM2m2us

[Shubhendu Trivedi @_onionesque]

Pen and Paper Exercises in Machine Learning by Michael U. Gutmann https://t.co/HsuWvJO6qs kudos to the author for putting these online -- surely will be a valuable resource for educators of all stripes (but especially for TAs and those who teach privately).

[ML Review @ml_review]

🔮Nixtla - Forecasting Pipeline as a Service
By @fede_gr
– 25% better accuracy than Amazon Forecast
– 20% more accurate than fbprophet
– 4x faster than Amazon Forecast & less expensive

https://t.co/Sbmhhr2wPG

[ML Review @ml_review]

Close The Sky Over Ukraine

[ML Review @ml_review]

Bayesian Modeling and Computation in Python
Online Book by @aloctavodia @canyon289 @junpenglao
Powered by Jupyter Book

https://t.co/Faag2LayEq

[ML Review @ml_review]

glum - fast, maintainable, Python-first library for fitting GLMs with an extensive feature set.
By @tbenthompson

-L1/L2/Tichonov
–Normal,Poisson,Tweedie etc
–Box/linear inequality constraints,sample weights, offsets
–scikit-learn compatible

https://t.co/9oI3LsbLIi

[ML Review @ml_review]

"Deep Learning for Molecules and Materials. 2021"
Online book by @andrewwhite01

https://t.co/bIOF8ILvIm

[ML Review @ml_review]

The Roadmap of Mathematics for Machine Learning
By @TivadarDanka

https://t.co/0ahqmCrzDO

[ML Review @ml_review]

An Elementary Introduction to Information Geometry
Survey by @FrnkNlsn
[2020, 56 pp]

- Basics of Differential Geometry
- Information Manifolds
- Applications

abs https://t.co/CpzQ7zroXq
pdf https://t.co/BrXvIBRKpW

[Zijie Jay Wang @Jay4w]

Excited to announce Dodrio, an interactive visualization tool designed to help NLP researchers and practitioners analyze and compare attention weights in transformer-based models with linguistic knowledge!

Try Dodrio in your browser: https://t.co/jnZDyygoWr

#ACL2021NLP #NLProc