121
From scratch: reverse-mode automatic differentiation (in Python)
The site of Sid
New
The latest blog posts to take off on Hacker News. 212 posts.
122
How much did AlphaGo Zero cost? (2018)
Answer: probably around $35 million.
123
A one-year moratorium on police use of Rekognition
We’re implementing a one-year moratorium on police use of Amazon’s facial recognition technology. We will continue to allow organizations like Thorn, the International Center for Missing and Exploited Children, and Marinus Analytics to use Amazon Rekognition to help rescue human trafficking victims…
124
YOLOv5: State-of-the-art object detection at 140 FPS
YOLOv5 license and commercial-use guide: AGPL-3.0 terms, specs, resources, and alternatives. Compare YOLOv5 against other vision models free.
125
A complete 4-year course plan for an AI undergraduate degree
I describe in-depth the courses necessary for a 4-year undergraduate degree in artificial intelligence, assuming you step onto campus tomorrow.
126
How to build your own feature store for ML
We have many conversations with companies and organizations who are deciding between building their own feature store and buying one....
127
Why is AI so useless for business?
AI research has structural problems that limit how much it can impact business. But understanding why gives a way to determine what will work and what won't, as well as reveal new business opportunities.
128
Self Supervised Learning in NLP
An overview of self-supervised pretext tasks in Natural Language Processing
129
Pac-Man recreated with a GAN trained on 50k game episodes
Bringing together the world’s brightest minds and the latest accelerated computing technology leads to powerful breakthroughs that help tackle some of the biggest research problems....
130
Siri, What Time Is It in London?
Every other service that tries to answer “What time is it in London?” gets it right. Only Siri gets it wrong.
131
The What-If Tool: Code-Free Probing of Machine Learning Models (2018)
Posted by James Wexler, Software Engineer, Google AI Building effective machine learning (ML) systems means asking a lot of questions. It's not eno...
132
133
A highly efficient, real-time text-to-speech system deployed on CPUs
Text-to-speech systems across the industry typically rely on GPUs or specialized hardware to generate state-of-the-art speech in real-time production. We solved core efficiency challenges to process one second of audio in 500 milliseconds — using only CPUs.
134
Nvidia CEO Introduces Nvidia Ampere Architecture, Nvidia A100 GPU
NVIDIA Corporate Blog Post Archive
135
136
Full Autopilot in GTA Using TensorFlow
student, nomad in machine learning
137
138
Deep Learning for Guitar Effect Emulation
Since the 1940s, electric guitarists, keyboardists, and other instrumentalists have been using effects pedals, devices that modify the sound of the original audio source. Typical effects include distortion, compression, chorus, reverb, and delay. Early effects pedals consisted of basic analog circuits, often along…
139
Ray Tracing Essentials Part 7: Denoising for Ray Tracing
This post is about the seventh and final video in this series, Denoising for Ray Tracing.
140
A commit history of BERT and its forks
What a commit history of version-controlled research papers could look like?
141
Researchers unveil a pruning algorithm to shrink deep learning models
MIT researchers have proposed a technique for shrinking deep learning models that they say is simpler and produces more accurate results than state-of-the-art methods. It works by retraining the smaller, pruned model at its faster, initial learning rate.
142
A visual explanation for regularization of linear models
A deep dive into exactly how regularization works, using visualizations rather than (just) mathematics. This article also dispels some myths and answer some important questions about Lasso and Ridge regression.
143
Using Neural Networks to Find Answers in Tables
Posted by Thomas Müller, Software Engineer, Google Research Much of the world’s information is stored in the form of tables, which can be found o...
144
My First Year as a Freelance AI Engineer
This week marks my one-year anniversary of quitting my full-time job and becoming a freelance AI engineer. I’m writing down my thoughts and experience here so that this might be useful if you are even vaguely interested.
145
146
Jukebox
We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.
147
We Need DevOps for ML Data
What is MLOps?
148
149
Creating ad hoc microphone arrays from personal devices (2019)
Researchers in the Microsoft Speech and Dialog Research Group have made an ad hoc microphone array by allowing meeting participants to join their phones together to enable more accurate meeting transcriptions. Explore how this array outperforms a single-device system.
150
Generating MIDI Music with GPT-2
Generating Irish/folk/classical music in ABC format using GPT-2-117M, with good results.