121
Facebook Trains ImageNet in 1 Hour
Facebook published a paper today detailing how they are able to train nearly 1.3 million images in under an hour using 256 Tesla P100 GPUs that previously took days on a single system.
Topics /
AI & Machine Learning
The most popular blog posts about ai & machine learning on Hacker News. 205 posts.
122
123
124
125
Neural Network-Generated Illustrations in Allo
Posted by Jennifer Daniel, Expressions Creative Director, Allo Taking, sharing, and viewing selfies has become a daily habit for many — the car sel...
126
Enabling Continual Learning in Neural Networks
Computer programs that learn to perform tasks also typically forget them very quickly. We show that the learning rule can be modified so that a program can remember old tasks when learning a new one. This is an important step towards more intelligent programs that are able to learn progressively and adaptively.
127
SLING: A Natural Language Frame Semantic Parser
Posted by Michael Ringgaard, Software Engineer and Rahul Gupta, Research ScientistUntil recently, most practical natural language understanding (NL...
128
129
130
Making a Neural Synthesizer Instrument
In a previous post, we described the details of NSynth (Neural Audio Synthesis), a new approach to audio synthesis using neural networks. We hinted at furthe...
131
Fathom: a framework for understanding web pages
Meet Fathom, a mini-language for writing semantic extractors, that you can use client- or server-side to extract meaning from the content of a web page. Scoop up all those ideas ...
132
How to Escape Saddle Points Efficiently
The BAIR Blog
133
Using Deep Learning to model personal visual aesthetics
Visual aesthetics are very personal, often subconscious, and hard to express. In a world with an overload of photographic content, a lot of time and effort is spent manually curating photographs…
134
Second version of HoloLens HPU will incorporate AI coprocessor
By Marc Pollefeys, Director of Science, HoloLens It is not an exaggeration to say that deep learning has taken the world of computer vision, and many other recognition tasks, by storm. Many of the most difficult recognition problems have seen gains over the past few years that are astonishing. Opens in a new tab…
135
136
Interpreting neurons in an LSTM network
A few months ago, we showed how effectively an LSTM network can perform text transliteration .
137
Where machine learning meets rule-based systems
Summary: This post addresses some high-level questions like: Longer term, how much of the verification of Intelligent Autonomous Systems can be done with just Machine Learning (ML)? Should most req…
138
ReBreakCaptcha: Breaking Google’s ReCaptcha v2 Using Google
TL;DR A logic vulnerability, dubbed ReBreakCaptcha, which lets you easily bypass Google’s ReCaptcha v2 anywhere on the web. Overview Back in 2016, I started poking around to see how hard it w…
139
Lessons Learned from Benchmarking Fast Machine Learning Algorithms
Access to this page requires authorization. You can try signing in or changing directories .
140
How are PCA and SVD related?
Exploring the relationship between singular value decomposition and principal component analysis.
141
142
Tutorial on Deep Learning
Lecture 1: Tutorial on Deep Learning I Lecture 2: Tutorial on Deep Learning II Lecture 3: Tutorial on Deep Learning III Lecture 4: Tutorial on Deep Learning IV
143
The World’s Largest Street-Level Imagery Dataset for Teaching Machines to See
Mapillary Vistas, the world’s largest and most diverse publicly available, pixel-accurately and instance-specifically annotated street-level imagery dataset, will empower autonomous mobility and transport at the global scale.
144
Caffe2 adds 16 bit floating point training support on the NVIDIA Volta platform
After open sourcing Caffe2 at F8 last month, today we are are excited to share our recent work on low precision 16 bit floating point (FP16) training in collaboration with NVIDIA.
145
Machine Learning: A Summary on Feature Engineering Using R Language
Access to this page requires authorization. You can try signing in or changing directories .
146
147
Teaching Robots to Understand Semantic Concepts
Posted by Sergey Levine, Faculty Advisor and Pierre Sermanet, Research Scientist, Google Brain TeamMachine learning can allow robots to acquire com...
148
Google Research and Daydream Labs: Seeing eye to eye in mixed reality
Virtual reality lets you experience amazing things—from exploring new worlds, to painting with trails of stars, to defending your fleet to save the world. But, headsets …
149
Transitioning entirely to neural machine translation
Visit the post for more.
150