Machine Learning
1297 Threads
Everyone is talking about #ChatGPT & #GPT3, but did you know there were many alternatives? Here are 10 of them! 🔥👇 1. BLOOM 2. GLaM 3. Gopher 4. Megatron-Turing NLG 5. Chinchill...
Our algorithm just finished ranking the 805 AI papers published in the last week (Jan 2-Jan 10) 🧵Here are the top 3 must-read, with TLDRs: https://t.co/NLM2fX1y1m
I work a lot with datasets of images, and analyzing and exploring the data it's always a mess. Kangas is an open-source library that helps tremendously! It only takes a few lines...
🐙 ML Papers of the Week Excited to share a new repo where we highlight the top ML papers of the week. https://t.co/gxXB1LInPR https://t.co/q9xaHaqgFp
532-page #Python #coding book by @TedPetrou >> "Pandas Cookbook: Recipes for Scientific Computing, #TimeSeries Analysis, and Data Visualization" at https://t.co/jUqK3uRcb2 ————— #1...
To learn Machine Learning fast you need to use the power of constraints. Here is what they are and how you can use them to learn 12x faster:
Boost your odds of landing a Data Science job in 2023 with these projects 🚀 A Thread 🧵 👇
ultra-modern generative ai🗨️: • AI2 • AI21 • mdm • gpt-J • gpt-3 • x-clip • bloom • cohere • gopher • dall•e 2 • craiyon • tabnine • jukebox • chatGPT *** • anthropic • codegee...
Deploying large generative AI models like Stable Diffusion for real-world applications will require low-cost training, fine-tuning, and inference. Colossal-AI is an open-source li...
There’s now a Python library for RLHF called TRLX! (The same reinforcement learning strategy used in training ChatGPT) It works well with Hugging Face models, supports multiple R...
Here's how I would study deep learning if I had to do it all over again. #deeplearning #machinelearning 👇🏽 🧵
Hot Take: People seem to think models like GPT and DALL-E imply deep learning models are special but I don't think this makes sense given what people claim about deep learning. He...
Free certifications in 2023: Python, Data Science, ML, AI: ~ https://t.co/cwZyia9NCq ~ https://t.co/UTmBk1cfiW ~ https://t.co/BkOUHsMGxX ~ https://t.co/TM1PreZsY7 Software Engine...
🗄️🗄️Will the next generation of LLMs have native data structures for storing insights? Pre-LLM era research has some interesting ideas here. Two of my favorite, both exactly what...
There is a lot of potential in retrieval-enhanced large language models. This new paper shows the potential of enhancing LLMs by retrieving relevant external knowledge based on d...
GoogleAI just released "Muse", a text-to-image generation/editing model via Masked Generative Transformers: - Achieves new SOTA - Zero-shot, Mask-free editing - Zero-shot Inpaint...
Kornia is a Differentiable Library based on PyTorch. 💫 Build a 𝑭𝒂𝒄𝒆 𝑫𝒆𝒕𝒆𝒄𝒕𝒐𝒓 in just a few lines of Python code using Kornia. A Thread 🧵👇 @kornia_foss https://t.co/7VsCUox8ws
Can we compress large language models for better perf? "SparseGPT: Massive Language Models can be Accurately Pruned in One Shot" Eliminates the need to use/store 50% of weights f...
I started my career in Data Science back in 2016 ⏳ Here's a detailed roadmap to learn Data Science/ Machine Learning in 2023! ✨ -- A Thread --
I have been solving problems using ML for 6 years now. ⏳ Here are the Books that have helped me during this journey! 📚 A Thread 🧵👇 https://t.co/OTjGQq7jGL
If you want to Learn Data Science / ML in 2023, follow this roadmap :
There are elements of linear algebra that are fundamental to understanding how neural networks work. But this is nuanced, and many people get the wrong message. Here are two dif...
Day 60 of #60daysOfMachineLearning 🔷 Model Serving 🔷 Model serving refers to the process of deploying a trained machine learning model in a production environment and using it to...
Quants use principal component analysis to find alpha. Blackrock uses it to manage $100s of billions in factor funds. Northfield uses it to earn $10s of millions selling factors...
