121
An Opinionated Guide to Machine Learning Research
I originally wrote this guide in back in December 2017 for the OpenAI Fellows program
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 212 posts.
122
Deep learning to translate between programming languages
TransCoder is the first self-supervised neural transcompiler system for migrating code between programming languages. It can translate code from Python to C++, for example, and it outperforms rule-based translation programs.
123
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.
124
AI that mistook a bald head for a soccer ball
Second-tier Scottish football club Inverness Caledonian Thistle doesn’t have a camera operator for matches at their stadium so the club uses an AI-controlled ca
125
Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
In this article we take performance of the SSD300 model even further, leaving Python behind and moving towards true production deployment technologies: TorchScript, TensorRT and DeepStream. We also identify and understand several limitations in Nvidia’s DeepStream framework, and then remove them by modifying how the…
126
Using ‘radioactive data’ to detect if a data set was used for training
Facebook AI has developed a new technique to mark the images in a dataset, so that researchers can then determine if a particular machine learning model...
127
Sci-fi story coauthored by GPT-3, including in-character human/AI chats
Short stories about the singularity written in collaboration with GPT-3.
128
129
Reformer, the Efficient Transformer
Posted by Nikita Kitaev, Student Researcher, UC Berkeley and Łukasz Kaiser, Research Scientist, Google Research Understanding sequential data — s...
130
Interactive C++ for Data Science
Interactive C++ for Data Science In our previous blog post “Interactive C++ with Cling” we mentioned that exploratory programming is an effective way to reduce the complexity of the problem. This post will discuss some applications of Cling developed to support data science researchers.
131
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.
132
Training GPT-2 to Play Chess
Almost 25 years after Kasparov vs. Deep Blue, another seminal man vs. machine matchup: Neither competitor has much to be proud of here. White has a poor opening. Black screws up and loses his queen…
133
Logistic regression from scratch
Deep dives into Cryptography and Privacy.
134
Algorithms Are Now Commodities
When I first started writing software, developers had to implement most of the algorithms they used; yes, hardware vendors provided libraries, but the culture was one of self-reliance (except for maths functions, which were technical and complicated).
135
Table Detection and Extraction Using Deep Learning
Extract table from image with Nanonets table detection OCR. Learn OCR table Deep Learning methods to detect tables in images or PDF documents.
136
TaBERT: A new model for understanding queries over tabular data
TaBERT is the first model that has been pretrained to learn representations for both natural language sentences and tabular data.
137
Let’s build a high-performance fuzzer with GPUs
TL;DR: Can we use GPUs to get 10x performance/dollar when fuzzing embedded software in the cloud? Based on our preliminary work, we think the answer is yes! Fuzzing is a software testing technique that supplies programs with many randomized inputs in an attempt to cause unexpected behavior. It’s an important, […]
138
Classifying 200k articles in 7 hours using NLP
Sculpt AI was built by a team of machine learning experts and SALT.agency and is a code-free AI platform. Keep reading to learn more about the benefits of this.
139
PyTorch 1.5
Today, we’re announcing the availability of PyTorch 1.5, along with new and updated libraries. This release includes several major new API additions and improvements. PyTorch now includes a significant update...
140
Gradient Boosted Decision Trees
From zero to gradient boosted decision trees
141
Pixelopolis, a self-driving car demo from Google I/O built with TensorFlow-Lite
Pixelopolis is an interactive installation that showcases self-driving miniature cars powered by TensorFlow Lite. Each car is outfitted with its own Pixel phone, which used its camera to detect and understand signals from the world around it. In order to sense lanes, avoid collisions and read traffic signs, the phone…
142
Do NLP Beyond English
7000+ languages are spoken around the world but NLP research has mostly focused on English. This post outlines why you should work on languages other than English.
143
Computational predictions of protein structures associated with COVID-19
The scientific community has galvanised in response to the recent COVID-19 outbreak, building on decades of basic research characterising this virus family. Labs at the forefront of the outbreak response shared genomes of the virus in open access databases, which enabled researchers to rapidly develop tests for this…
144
145
Cloud AI Platform Pipelines
AI Platform Pipelines provides enterprise-ready infrastructure for deploying and running structured ML workflows, and pipeline tools for building, debugging, and sharing pipelines and components.
146
Differentiable Dithering
Problem Let's say we want to reduce the number of colors in an image. For example consider the picture of fruit below:
147
Generating MIDI Music with GPT-2
Generating Irish/folk/classical music in ABC format using GPT-2-117M, with good results.
148
Machine Learning, Kolmogorov Complexity, and Squishy Bunnies (2019)
Computer Science, Machine Learning, Programming, Art, Mathematics, Philosophy, and Short Fiction
149
150
Understanding Convolution in Deep Learning (2015)
Convolution is probably the most important concept in deep learning right now. It was convolution and convolutional nets that catapulted deep learning to the forefront of almost any machine learning task there is. But what makes convolution so powerful? How does it work? In this blog post I will explain convolution…