Here is a great summary or glossary doc about LLM by Aman Chadha. This long doc provides a summary of some of the main concepts related to LLM. This includes topics such as:
✅ Embeddings
✅ Vector database
✅ Prompt engineering
✅ Token
✅ RAG
✅ LLM performance evaluation
✅ Review main LLMs
Version 1.7.1 of the NeuralForecast #Python library was released last month by Nixtla. The NeuralForecast library, as the name implies, provides a neural network framework for time series forecasting. 🧵👇🏼
Very nice picture that was shared by Ronald van Loon on X, you can discuss if the categories are complete and correct, but it illustrates that the field of AI is much more then just transformers/LLMs. #AI#Machinelearning#neuralnetworks#deeplearning#LLM#Transfomers
Meta released today Llama 3, the next generation of the Llama model. LLama 3 is a state-of-the-art open-source large language model. Here are some of the key features of the model: 🧵👇🏼
Google released a new repo with a collection of guides and examples for the Gemini API. This includes a set of guides for prompt engineering and examples of the API features 👇🏼
(1/2) Models Demystified - A Practical Guide from t-tests to Deep Learning 🚀👇🏼
The Models Demystified is a new book by Michael Clark and Seth Berry that focuses on the mechanizing of core data science algorithms. That includes the following topics:
✅ Linear and logistic regression
✅ Generalized Linear Models
✅ Regularization methods
✅ Model training approaches
✅ Deep learning and neural networks
✅ Causal Modeling
Whenever I see OpenAI's Sam Altman with his pseudo-innocent glance, he always reminds me of Carter Burke from Aliens (1986), who deceived the entire spaceship crew in favor of his corporation, with the aim of getting rich by weaponizing a newly discovered intelligent lifeform.
Andrej Karpathy just released a new repo with an implementation of training LLM with pure C/Cude with a few lines of code 🚀. This repo, according to Andrej Karpathy, is still WIP, and the first working example is of GPT-2 (or the grand-daddy of LLMS 😅) 👇🏼
Malt: A Deep Learning Framework for Racket by Dan Friedman and Anurag Mendhekar
We discuss the design of a #DeepLearning toolkit, Malt, that has been built for Racket. Originally designed to support the pedagogy of The Little Learner—A Straight Line to Deep Learning, it is used to build deep neural networks with a minimum of fuss using tools like higher-order automatic differentiation and rank polymorphism. The natural, functional style of AI programming that Malt enables can be extended to much larger, practical applications. We present a roadmap for how we hope to achieve this so that it can become a stepping stone to allow #Lisp / #Scheme / #Racket to reclaim the crown of being the language for Artificial Intelligence (perhaps!).
The Neural Networks from Scratch in #Python 🐍 course by Harrison Kinsley introduces neural networks by coding them from scratch. The course is based on Harrison's book (along with Daniel Kukiela), and it covers the following topics:
✅ Core linear algebra and math operators
✅ Neural network architecture
✅ Different loss functions
✅ Optimization and derivatives
(1/2) Moirai - Salesforce's Foundation Forecasting Model 🚀
Salesforce recently released Moirari - a new #Python 🐍 library with a foundation model for time series forecasting applications. According to the release blog - the model comes with universal forecasting capabilities and can handle multiple scenarios and different frequencies.
The below course by Dhaval Patel is a beginner-level course for Deep Learning in Python with Tensorflow 2.0 and Kares. The course covers the foundations of neural network and deep learning, which includes the following topics: 🧵👇🏼
Only 2 days left to get your student application in!! Neuromatch Academy can be a huge career boost for people looking to improve their computational skills. #neuroscience#neuroai#deeplearning
Registration is open, but act fast! 🚨🚨
Sunday, March 24th (every time zone on Earth) is our Priority Deadline. While applications will be accepted until March 31st, those who register by the priority deadline will receive higher consideration for acceptance. Don't delay! Secure your spot and be part of our amazing courses. Register on neuromatch.io #neuroscience#deeplearning#neuroai
If I need to describe data science in one word, it would be optimization, and in two words, convex optimization. Convex optimization is the mathematical mechanizing beyond many data science algorithms, from least squares to neural network. The Convex Optimization course by Prof. Stephen Boyd (Stanford University) focuses on methods for identifying and solving convex optimization problems.
This tutorial by Felix Köhler provides a step-by-step guide for setting up a DeepONet architecture with JAX and Equinox frameworks for deep learning. The DeepONet is used to evaluate a nonlinear operator on discrete inputs.