Unpacking the multilayer perceptrons in a transformer, and how they may store facts. Grant explores the inner workings of large language models, specifically focusing on how they predict and encode information. Understanding the storage and retrieval of facts in AI relies on complex neural architectures and high-dimensional spaces.

Demystifying attention, the key mechanism inside transformers and LLMs. Grant delves into the inner workings of transformers in large language models, focusing on the attention mechanism and its data processing capabilities.

Grant provides an in-depth visual explanation of transformers in AI, discussing their structure, function, and the process of generating text using GPT models. Transformers use attention mechanisms and vast data to revolutionize text generation in AI.

Grant discusses the application of calculus in machine learning, specifically the back propagation algorithm and its calculations. Back propagation is essential for optimizing neural networks through detailed calculus applications.

What's actually happening to a neural network as it learns? Grant discusses back propagation, a key algorithm behind how neural networks learn, using the example of recognizing handwritten numbers.

A visual explanation of how neural networks learn through a process called gradient descent. Understanding and optimizing neural networks involves mastering gradient descent, cost functions, and network architectures.

What are the neurons, why are there layers, and what is the math underlying it? Understanding and adjusting neural network structures and functions is crucial for effective pattern recognition and learning.

A visual and simplified exploration of the Transformer model in machine learning.

This post provides an intuitive introduction to the core concepts of deep learning. It covers the most important deep learning concepts and aims to provide an understanding of each concept rather than its mathematical and theoretical details. While the mathematical terminology is sometimes necessary and can further understanding, these posts use analogies and images whenever possible to provide easily digestible bits comprising an intuitive overview of the field of deep learning.

Interactive deep learning book with code, math, and discussions. Implemented with PyTorch, NumPy/MXNet, JAX, and TensorFlow. Adopted at 500 universities from 70 countries.

A course by Andrej Karpathy on building neural networks, from scratch, in code. We start with the basics of backpropagation and build up to modern deep neural networks, like GPT. In my opinion language models are an excellent place to learn deep learning, even if your intention is to eventually go to other areas like computer vision because most of what you learn will be immediately transferable. This is why we dive into and focus on languade models.

Design, train, and deploy models from A to Z. This is also a great resource for those struggling with the machine learning system design questions in interviews.

Taught by one of the most influential (and most down-to-earth) researcher, Christopher Manning, this is must-take course for anyone interested in natural language processing. The course is well organized, well taught, and up-to-date with the latest NLP research.

An authoritative, accessible, and up-to-date treatment of deep learning that strikes a pragmatic middle ground between theory and practice.

An in-depth exploration of the theory and practice of deep learning, a powerful subset of machine learning.

LSTMs are crucial for learning long-term dependencies in recurrent neural networks.

Explore the magical outputs and robustness of Recurrent Neural Networks in various data formats.

Annotated version of a transformer with comments adds explanation to the model architecture.

A book intended to teach you how to build neural networks on your own, without any libraries, so you can better understand deep learning and how all of the elements work. This is so you can go out and do new/novel things with deep learning as well as to become more successful with even more basic models.

A 12-week, 24-lesson curriculum for Artificial Intelligence from Microsoft. It includes practical lessons, quizzes, and labs. The curriculum is beginner-friendly and covers tools like TensorFlow and PyTorch, as well as ethics in AI.

This modern and comprehensive Data Science and Machine Learning course on Udemy teaches you the latest skills using Python, TensorFlow 2.0, and other libraries. It covers everything from basic Python programming to advanced topics like Neural Networks, Deep Learning, and Transfer Learning. You'll build real-world projects, gain hands-on experience, and learn to work with popular tools such as Pandas, Scikit-learn, and Matplotlib. By the end, you'll have a portfolio of projects and the skills needed to become a professional Data Scientist, ready for the job market.

This book explores the full breadth and depth of the field of artificial intelligence (AI). The 4th Edition brings readers up-to-date on the latest technologies, presents concepts in a more unified manner, and offers new or expanded coverage of machine learning, deep learning, transfer learning, multi agent systems, robotics, natural language processing, causality, probabilistic programming, privacy, fairness, and safe AI.

Everything you need to know, from the basics, to image classification with Convolutional Neural Networks, to the state of the art transformers used for large language models like ChatGPT, presented one step at a time so that it is easily understood.

A free course from fast.ai designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems.

A course focused on specializing in Deep Learning taught by Andrew Ng, one of the industry leaders in Artificial Intelligence. This course covers neural networks and deep learning, improving neural networks, structuring machine learning projects, convolutional neural networks and sequence models.