181
CuPy Accelerates NumPy on the GPU? Hold My Cider, Here's Clojure
Everyone knows that Java is slow and Clojure is not a great choice for number crunching, but as soon as I dig anywhere with my software, I discover that the ...
182
How to put machine learning models into production
The goal of building a machine learning model is to solve a problem, and a machine learning model can only do so when it is in production and actively in use by consumers. As such, model deployment is as important as model building.
183
Starting a Business Around GPT-3 Is a Bad Idea
(Update 2023-03: I wrote this in 2020 when GPT-3 was highly hyped, but ultimately made only <1% of the splash that the monstrous ChatGPT made 3 years later. If I had to rewrite this today, I’d 1) think more kindly about defensibility, especially through deep product, user experience, and marketing/distribution (see…
184
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.
185
GPT-3 Explorer
A power tool for experimenting with GPT-3
186
187
188
189
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....
190
From scratch: reverse-mode automatic differentiation (in Python)
The site of Sid
191
JPEG Committee releases a call for evidence for image compression based on AI
The 86th JPEG meeting was held in Sydney, Australia. Among the different activities that took place, the JPEG Committee issued a Call for Evidence on learning-based image coding solutions. In addition, a First Call for Evidence on Point Cloud Coding was issued in the framework of JPEG Pleno Point Cloud Coding…
192
A Sober Look at Bayesian Neural Networks
by Carles Gelada and Jacob Buckman WARNING: This is an old version of this blogpost, and if you are a Bayesian, it might make you angry. Click here for an updated post with the same content. Context: About a month ago Carles asserted on Twitter that Bayesian Neural Networks make...
193
PyMC: Theano Is Dead, Long Live Theano
© 2020, The PyMC Development Team
194
AI predicts effective depression treatment based on brainwave patterns
Tracking brainwave patterns and symptoms in patients with depression, researchers used artificial intelligence to predict best treatment options.
195
Computation Graphs and Graph Computation
Research has begun to reveal many algorithms can be expressed as matrix multiplication, suggesting an unrealized connection between linear algebra and computer science. I speculate graphs are the missing piece of the puzzle. Graphs are not only useful as cognitive aides, but are suitable data structures for a wide…
196
ScaNN: Efficient Vector Similarity Search
Posted by Philip Sun, Software Engineer, Google Research Suppose one wants to search through a large dataset of literary works using queries that r...
197
The Next Leap in Self-Driving: Prediction
Why prediction has overtaken perception as the biggest challenge in the field.
198
Deep Learning Algorithms: The Complete Guide
All the essential Deep Learning Algorithms you need to know including models used in Computer Vision and Natural Language Processing
199
A round-up of topology-based papers at ICML 2020
With this year’s International Conference on Machine Learning (ICML) being over, it is time to have another instalment of this series. Similar to last year’s post , I shall cover several papers that caught my attention because of their use of topological concepts—however, unlike last year, I shall not restrict the…
200
Benchmarking TensorFlow on Nvidia GeForce RTX 3090
We benchmarked the deep learning performance of the latest NVIDIA RTX 3090 GPU.
201
202
Signal processing is key to embedded machine learning
When we hear about ML - whether it’s about machines learning to play Go or computers generating plausible human language - we often think about deep learning.
203
Boston Dynamics' Handle Robot Recreated with Raspberry Pi
Maker Harry was inspired by Handle, Boston Dynamics' research robot, yo build his own mini version named MABEL.
204
A commit history of BERT and its forks
What a commit history of version-controlled research papers could look like?
205
Robot Disinfects Greater Boston Food Bank
MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), in collaboration with Ava Robotics and the Greater Boston Food Bank, designed a robot that disinfects surfaces and neutralizes aerosolized coronavirus with UV-C light. The approach uses a custom UV-C light fixture designed at CSAIL that is…
206
JetBrains to reimagine IntelliJ as text editor, add machine learning
This is the second part of the roadmap of IntelliJ IDEA and IntelliJ-based IDEs for 2020. The first part of the roadmap was focused mostly on low-level features in the platform. In this post we’ll be
207
Neural Supersampling for Real-Time Rendering
Real-time rendering in virtual reality presents a unique set of challenges — chief among them being the need to support...
208
Using neural networks to solve advanced mathematics equations
Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems.
209
Using JAX, numpy, and optimization techniques to improve separable image filters
By the end of this blog post, we aim to improve the results of my previous blog post of approximating circular bokeh with a sum of 4 separable filters and reducing its artifacts (left) through an o…
210
Named Tensors
Named tensors for better deep learning code.