Machine Learning
1297 Threads
Can you pre-train and fine-tune your VLMs in FP8? Can you get more than 2x efficiency with some simple tricks? Nvidia presents NVILA, an efficient frontier VLM that achieves all of...
Part 2: Why do boosted trees outperform deep learning on tabular data?? @Jeffaresalan &I suspected that answers are obfuscated by the 2 being considered very different algs Inste...
Let's build a predictive ML system π©π½βπ»π¨βπ»βββ
Machine Learning cheatsheets form Stanford's CS 229:
3 years ago I struggled to land my first freelance ML engineering contract. Then I discovered this β https://t.co/VLa3IrITnU
K-Means has two major problems: - Number of clusters must be known - Doesn't handle outliers But there's a solution! Introducing DBSCAN, a Density based clustering algorithm. π...
The must-have machine learning technique for financial market data analysis: https://t.co/Q5zrVpXffK
How do machines see? ππ€ Join me in this thread to learn how AIs βseeβ and classify images. Let's see what Convolutional Neural Networks (CNN) areπ§΅π§΅ https://t.co/4GBsE6vrQF
5 GitHub repositories that will give you superpowers as an AI/ML Engineer:
Microsoft is offering FREE courses in following areas: - AI - IOT - Data Science - Machine Learning A project-based pedagogy that allows you to learn while building! π Read More...
Brilliant new paper, HUGE for LLM's internalized knowledge π₯ Out Of Context Learning > In Context Learning | Fine-tuning can teach new concepts better than ICL π Finds a surprisin...
This 76-page paper on Prompting Techniques has become quite popular. A nice read for your weekend. - "The Prompt Report: A Systematic Survey of Prompting Techniques": β¨ Explores...
A theory of why Claude 3.5 Sonnet is insane at coding: mechanistic interpretability. Anthropic showed that there are clever ways to understand what the weights of LLMs do and "ste...
π Algunos de mis libros favoritos sobre #stats #datascience #analytics #rstats #dataviz 𧡠R fod Data Science https://t.co/b6PMubwwuK An introduction to statistical learning https...
A key to making your LLMs work better: just throw everything into the context window π‘ For many datasets, for most of the time, the long-context ICL (in-context learning) outperfo...
K-Nearest Neighbors clearly explained π https://t.co/U0irGMyzLE
Logistic Regression clearly explained π https://t.co/Uq3huEYyq9
No more high gas fees, no more inefficiencies. @0xverisynclabs is solving the challenges in the current Zero-Knowledge (ZK) ecosystem. How? ~ 𧡠https://t.co/r8nbj2eNVF
5 github repositories you should definitely check as a Machine Learning Engineer:
Use machine learning to detect market regimes: https://t.co/aeICU1DDHY
There's a stunning, simple explanation behind matrix multiplication. This is the first time this clicked on my brain, and it will be the best thing you read all week. Here is a b...
We've all dealt with activation functions while working with neural nets. - Sigmoid - Tanh - ReLu & Leaky ReLu - Gelu Ever wondered why they are so importantβπ€ Let me explain it...
Why Machine Learning in Finance? This is why. 𧡠https://t.co/ZX4mfwMLov
Iβve worked in Data Science for a while. My journey into that field has been almost completely self taught. In my learning I have prioritized what is effective and works best, rath...
