deep-learning
Why AI Inference Will Remain Largely On The CPU
Sponsored Feature: Training an AI model takes an enormous amount of compute capacity coupled with high bandwidth memory. Because the model training can be
Hands-on Generative AI with GANs using Python: Autoencoders
Start with Autoencoders to better understand GANs
Hacker News
I explain what is so unique about the RWKV language model.
Cerebras open sources seven GPT-based LLMs, ranging from 111M to 13B parame
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
Must read: the 100 most cited AI papers in 2022
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…
Dalai
Dead simple way to run LLaMA on your computer
Deep Learning (DL) Applications In Photomask To Wafer Semiconductor Manufac
A list of artificial intelligence used in semiconductor manufacturing tools from February 2023.
?Top ML Papers of the Week - by elvis - NLP Newsletter
The top ML Papers of the Week (Mar 6 - Mar 12)
Asynchronously Parallel Optimization Method For Sizing Analog Transistors U
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…
Meta unveils a new large language model that can run on a single GPU
LLaMA-13B reportedly outperforms ChatGPT-like tech despite being 10x smaller.
Google Research, 2022 & beyond: Algorithms for efficient deep learning
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...
Hacker News
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…
Paper Review: A Deep Dive into Imagen
A critical analysis of Google’s impressive new text-to-image generation tool
AI Spits Out Exact Copies of Training Images, Real People, Logos, Researche
The regurgitation of training data exposes image diffusion models to a number of privacy and copyright risks.
Text-to-4D dynamic scene generation
Find it here, via Ryan Watkins. Further improvement is required, but the pace of current breakthroughs is remarkable.
ChatGPT is not all you need. A State of the Art Review of large...
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...
Hacker News
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.
Uncovering Anomalies with Variational Autoencoders (VAE): A Deep Dive into
An example use case of using Variational Autoencoders (VAE) to detect anomalies in all types of data
Why WGANs beat GANs: A journey from KL divergence to Wasserstein loss
Wasserstein distance helps WGANs outperform vanilla GANs and VAEs. This post explains why so using some easy math.
Why TensorFlow for Python is dying a slow death
Many developers who use Python for machine learning are now switching to PyTorch. Find out why and what the future could hold for TensorFlow.
Deep Learning Pioneer Geoffrey Hinton Publishes New Deep Learning Algorithm
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…
To Build Truly Intelligent Machines, Teach Them Cause and Effect | Quanta M
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.
lucidrains/vit-pytorch: Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single…
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch - lucidrains/vit-pytorch
ChatGPT and the Imagenet moment — Benedict Evans
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?
2212.03551.pdf
DeepMind Created An AI Tool That Can Help Generate Rough Film and Stage Scr
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…
A Quick Start on Your Journey to Federated Learning
Adapting federated learning to your own datasets
AI Homework – Stratechery by Ben Thompson
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.
Beginner’s Guide to Diffusion Models
An intuitive understanding of how AI-generated art is made by Stable Diffusion, Midjourney, or DALL-E
YOLOv7: A deep dive into the current state-of-the-art for object detection
Everything you need to know to use YOLOv7 in custom training scripts
6 Reinforcement Learning Algorithms Explained
Introduction to reinforcement learning terminologies, basics, and concepts (model-free, model-based, online, offline RL)
Cerebras Reveals Andromeda, a 13.5 Million Core AI Supercomputer
The world's largest chip scales to new heights.
Interview: Why Mastering Language Is So Difficult for AI
Scientist Gary Marcus argues that “deep learning” is not the only path to true artificial intelligence.
matsui528/nanopq: Pure python implementation of product quantization for nearest neighbor search
Pure python implementation of product quantization for nearest neighbor search - matsui528/nanopq
IVFPQ HNSW for Billion-scale Similarity Search | by Peggy Chang | Towards
The best indexing approach for billion-sized vector datasets
Similarity Search with IVFPQ
Find out how the inverted file index (IVF) is implemented alongside product quantization (PQ) for a fast and efficient approximate nearest…
NSVQ: Improved Vector Quantization technique for Neural Networks Training
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
If you thought text-to-image AI was unbelievable, wait until you see how it compresses images.
All you need to know about ‘Attention’ and ‘Transformers’ — In-depth Unders
Attention, Self-Attention, Multi-head Attention, Masked Multi-head Attention, Transformers, BERT, and GPT
All you need to know about ‘Attention’ and ‘Transformers’ — In-depth Unders
Attention, Self-Attention, Multi-head Attention, and Transformers
40,000 Recipes for Murder
Two scientists inadvertently open the Pandora’s Box of WMDs. What now?
Demystifying Object Detection and Instance Segmentation for Data Scientists - MLWhiz
this post is explaining how permutation importance works and how we can code it using ELI5
Automated reasoning at Amazon: A conversation
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.
A Brief Introduction to Geometric Deep Learning
AI for complex data
Rethinking Thinking: How Do Attention Mechanisms Actually Work?
The brain, the mathematics, and DL — research frontiers in 2022
fastai/fastbook: The fastai book, published as Jupyter Notebooks
The fastai book, published as Jupyter Notebooks.
d2l-ai/d2l-en: Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70…
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
Dive into Deep Learning — Dive into Deep Learning 0.14.4 documentation
Deep Convolutional GAN — How to Use a DCGAN to Generate Images in Python
An overview of DCGAN architecture with a step-by-step guide to building it yourself