Trillion Parameter Models Are Here
Explore ZeRO-Infinity's breakthrough in training trillion-parameter ML models with limited GPUs, revolutionizing large-scale deep learning and expanding possibilities for AI researchers and practitioners.
Recreate Google Translate - Model Training
Explore model training and testing for Neural Machine Translation, recreating Google Translate using mT5 and Hugging Face. Practical implementation and demo of multilingual translations.
Let's Build GPT - From Scratch, in Code, Spelled Out
Comprehensive tutorial on building a GPT model from scratch, covering key concepts like self-attention, multi-headed attention, and transformer architecture. Includes practical coding examples and insights into modern language models.
Building Makemore - Building a WaveNet
Dive deep into building a WaveNet-like convolutional neural network, exploring torch.nn, and understanding the typical deep learning development process through hands-on implementation.
Building Makemore - Becoming a Backprop Ninja
Hands-on tutorial on manual backpropagation through a 2-layer MLP, enhancing understanding of gradient flow in neural networks for confident innovation and debugging.
Building Makemore - Activations & Gradients, BatchNorm
Explore MLP internals, activations, gradients, and BatchNorm. Learn to diagnose deep networks, understand training challenges, and implement modern techniques for improved performance.
Building Makemore - MLP
Implement a multilayer perceptron character-level language model, covering machine learning basics like model training, hyperparameter tuning, evaluation, and addressing under/overfitting.
The Spelled-Out Intro to Language Modeling - Building Makemore
Comprehensive tutorial on building a bigram character-level language model, covering tensor operations, neural networks, and PyTorch fundamentals for natural language processing tasks.
DALL-E - Zero-Shot Text-to-Image Generation - Paper Explained
Explore OpenAI's DALL-E: a groundbreaking AI model that generates images from text descriptions, combining concepts in plausible ways and showcasing emergent image-to-image capabilities.
VQ-GAN - Taming Transformers for High-Resolution Image Synthesis - Paper Explained
Explore VQ-GAN's innovative approach to high-resolution image synthesis, combining modified VQ-VAEs with GPT-2 for impressive results. Learn about perceptual loss, adversarial techniques, and comparisons with other models.
Build a Simple Language Translation App Using Python for Beginners
Learn to build a language translation app using Python, Hugging Face Transformers, and Gradio. Covers installation, text translation with deep learning, and creating a lightweight ML app interface.
Build a Grammar Correction Python App with Gramformer and Gradio
Learn to create a Python app for grammar correction using Gramformer and Gradio. Develop skills in deep learning, natural language processing, and app deployment for improved writing assistance.
Live Speech to Text with Watson Speech to Text and Python
Learn to implement live speech-to-text transcription using Watson's free API and Python. Set up the service, access code, install dependencies, and run real-time transcription from your microphone.
Automate Stocks and Crypto Research with Python and Deep Learning - Full Python Project
Learn to automate stock and crypto research using Python, web scraping, and deep learning. Build a pipeline to gather, summarize, and analyze financial news for various assets.
Generate Blog Posts with GPT2 and Hugging Face Transformers - AI Text Generation GPT2-Large
Learn to generate blog posts using GPT2 and Hugging Face Transformers. Master text encoding, AI-powered content creation, and output decoding for efficient writing and content production.
Speech Command Recognition With Tensorflow.JS and React.JS - Javascript AI
Learn to integrate AI-powered speech command recognition into your React.JS app using Tensorflow.JS. Build a web app that detects and displays speech commands in just 26 minutes.
NLP Powered Q&A with React.js and Tensorflow.js BERT
Build a Q&A web app using React.js and TensorFlow.js BERT in under 30 minutes. Learn to implement NLP-powered question answering for extracting insights from text passages.
ROME - Locating and Editing Factual Associations in GPT - Paper Explained & Author Interview
Explores mechanisms for storing and editing factual knowledge in GPT models, revealing key roles of mid-layer feed-forward modules and proposing targeted editing techniques with implications for model understanding and control.
More Is Different for AI - Scaling Up, Emergence, and Paperclip Maximizers
Explore AI scaling, emergence, and safety with Jacob Steinhardt. Discuss qualitative changes in AI systems, implications for alignment, and thought experiments like the Paperclip Maximizer. Gain insights on future AI challenges and potential solutions.
OpenAI DALL·E - Creating Images from Text - Blog Post Explained
Explore OpenAI's DALL·E model, its architecture, capabilities, and limitations in generating high-quality images from text descriptions. Learn about its potential impact on AI applications combining text and visuals.
Language Models Are Open Knowledge Graphs
Explore how pre-trained language models can be used to construct knowledge graphs without human supervision, uncovering new relations and outperforming existing methods in automated KG construction.