A new technical paper titled “TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings” was published by researchers at Google. Abstract: “In response to innovations in machine learning (ML) models, production workloads changed…
Sponsored Feature: Training an AI model takes an enormous amount of compute capacity coupled with high bandwidth memory. Because the model training can be
Start with Autoencoders to better understand GANs
I explain what is so unique about the RWKV language model.
Mike Wheatley / SiliconANGLE: Cerebras open sources seven GPT-based LLMs, ranging from 111M to 13B parameters and trained using its Andromeda supercomputer for AI, on GitHub and Hugging Face
Who Is publishing the most Impactful AI research right now? With the breakneck pace of innovation in AI, it is crucial to pick up some signal as soon as possible. No one has the time to read everything, but these 100 papers are sure to bend the road as to where our AI technology…
Dead simple way to run LLaMA on your computer
A list of artificial intelligence used in semiconductor manufacturing tools from February 2023.
A new technical paper titled “APOSTLE: Asynchronously Parallel Optimization for Sizing Analog Transistors Using DNN Learning” was published by researchers at UT Austin and Analog Devices. Abstract “Analog circuit sizing is a high-cost process in terms of the manual effort…
LLaMA-13B reportedly outperforms ChatGPT-like tech despite being 10x smaller.
Posted by Sanjiv Kumar, VP and Google Fellow, Google Research (This is Part 4 in our series of posts covering different topical areas of research a...
Many new Transformer architecture improvements have been proposed since my last post on “The Transformer Family” about three years ago. Here I did a big refactoring and enrichment of that 2020 post — restructure the hierarchy of sections and improve many sections with more…
A critical analysis of Google’s impressive new text-to-image generation tool
The regurgitation of training data exposes image diffusion models to a number of privacy and copyright risks.
Find it here, via Ryan Watkins. Further improvement is required, but the pace of current breakthroughs is remarkable.
During the last two years there has been a plethora of large generative models such as ChatGPT or Stable Diffusion that have been published. Concretely, these models are able to perform tasks such...
Here, I provide an in-depth analysis of GPUs for deep learning/machine learning and explain what is the best GPU for your use-case and budget.
An example use case of using Variational Autoencoders (VAE) to detect anomalies in all types of data
Wasserstein distance helps WGANs outperform vanilla GANs and VAEs. This post explains why so using some easy math.
Many developers who use Python for machine learning are now switching to PyTorch. Find out why and what the future could hold for TensorFlow.
Geoffrey Hinton, professor at the University of Toronto and engineering fellow at Google Brain, recently published a paper on the Forward-Forward algorithm (FF), a technique for training neural networks that uses two forward passes of data through the network, instead of…
Judea Pearl, a pioneering figure in artificial intelligence, argues that AI has been stuck in a decades-long rut. His prescription for progress? Teach machines to understand the question why.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch - lucidrains/vit-pytorch
The wave of enthusiasm around generative networks feels like another Imagenet moment - a step change in what ‘AI’ can do that could generalise far beyond the cool demos. What can it create, and where are the humans in the loop?
Alphabet's DeepMind has built an AI tool that can help generate rough film and stage scripts Engadget's Kris Holt reports: Dramatron is a so-called "co-writing" tool that can generate character descriptions, plot points, location descriptions and dialogue. The idea is that human…
Adapting federated learning to your own datasets
The first obvious casualty of large language models is homework: the real training for everyone, though, and the best way to leverage AI, will be in verifying and editing information.
An intuitive understanding of how AI-generated art is made by Stable Diffusion, Midjourney, or DALL-E
Everything you need to know to use YOLOv7 in custom training scripts
Introduction to reinforcement learning terminologies, basics, and concepts (model-free, model-based, online, offline RL)
The world's largest chip scales to new heights.
Scientist Gary Marcus argues that “deep learning” is not the only path to true artificial intelligence.
Pure python implementation of product quantization for nearest neighbor search - matsui528/nanopq
The best indexing approach for billion-sized vector datasets
Find out how the inverted file index (IVF) is implemented alongside product quantization (PQ) for a fast and efficient approximate nearest…
Efficient vector quantization for machine learning optimizations (eps. vector quantized variational autoencoders), better than straight…
If you thought text-to-image AI was unbelievable, wait until you see how it compresses images.
Attention, Self-Attention, Multi-head Attention, Masked Multi-head Attention, Transformers, BERT, and GPT
Attention, Self-Attention, Multi-head Attention, and Transformers
Two scientists inadvertently open the Pandora’s Box of WMDs. What now?
this post is explaining how permutation importance works and how we can code it using ELI5
To mark the occasion of the eighth Federated Logic Conference (FloC), Amazon’s Byron Cook, Daniel Kröning, and Marijn Heule discussed automated reasoning’s prospects.
AI for complex data
The brain, the mathematics, and DL — research frontiers in 2022
The fastai book, published as Jupyter Notebooks.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge. - d2l-ai/d2l-en
An overview of DCGAN architecture with a step-by-step guide to building it yourself