31
Why squared error? (2014)
its computational convenience • connections to the Gaussian distribution • differentiability and basis independence • why not squared error • absolute-error methods
New
The latest blog posts to take off on Hacker News. 250 posts.
32
33
Zero-Shot Translation with Multilingual Neural Machine Translation System
Posted by Mike Schuster (Google Brain Team), Melvin Johnson (Google Translate) and Nikhil Thorat (Google Brain Team)In the last 10 years, Google Tr...
34
35
Reinforcement learning with unsupervised auxiliary tasks
Our primary mission at DeepMind is to push the boundaries of AI, developing programs that can learn to solve any complex problem without needing to be taught how. Our reinforcement learning agents have achieved breakthroughs in Atari 2600 games and the game of Go. Such systems, however, can require a lot of data and a…
36
37
38
How Quid uses deep learning with small data
Enhance your consumer & market intelligence knowledge with our resource library. Discover the role of Generative AI in transforming the digital landscape.
39
OpenAI and Microsoft
We’re working with Microsoft to start running most of our large-scale experiments on Azure.
40
Who Will Command the Robot Armies?
This is the text version of a talk I gave on November 11, 2016, at the Direction conference in Sydney.
41
Found in translation: More accurate, fluent sentences in Google Translate
In 10 years, Google Translate has gone from supporting just a few languages to 103, connecting strangers, reaching across language barriers and even helping people find …
42
GPUs for Google Cloud Platform
CPU-based machines in the cloud are terrific for general purpose computing, but certain tasks such as rendering or large-scale simulations are much faster on specialized processors. Graphics Processing Units (GPUs) contain hundreds of times as many computational cores as CPUs and are great at accelerating risk…
43
44
RAISR Sharp Images with Machine Learning
Posted by Peyman Milanfar, Research Scientist Everyday the web is used to share and store millions of pictures, enabling one to explore the world, ...
45
46
Embed, encode, attend, predict: the new deep learning formula for NLP models
Over the last six months, a powerful new neural network playbook has come together for Natural Language Processing. The new approach can be summarised as a simple four-step formula: embed, encode, attend, predict. This post explains the components of this new approach, and shows how they're put together in two recent…
47
48
49
DeepMind and Blizzard to release StarCraft II as an AI research environment
Today at BlizzCon 2016 in Anaheim, California, we announced our collaboration with Blizzard Entertainment to open up StarCraft II to AI and Machine Learning researchers around the world.
50
51
Denser 3D Point Clouds in OpenSfM
We've improved OpenSfM—the technology we use to create 3D reconstructions from images. By adding post-processing, we get denser 3D point clouds resulting in better visualization, positioning, and much more.
52
Engines of Evidence – A Conversation with Judea Pearl
In the early 1960s, every company had a huge investment in the future of computers. I fell into a device-oriented research group, wherein the goal was to find new phenomena that we could turn into computer memory. Magnetic core memories were already becoming a nuisance. Some people worked on photochromic phenomena…
53
Supercharging Style Transfer
Posted by Vincent Dumoulin*, Jonathon Shlens and Manjunath Kudlur, Google Brain TeamPastiche. A French word, it designates a work of art that imita...
54
55
56
SpaCy v1.0: Deep Learning with custom pipelines and Keras
I'm pleased to announce the 1.0 release of spaCy, the fastest NLP library in the world. By far the best part of the 1.0 release is a new system for integrating custom models into spaCy. This post introduces you to the changes, and shows you how to use the new custom pipeline functionality to add a Keras-powered LSTM…
57
58
59
Towards deep symbolic reinforcement learning
Towards deep symbolic reinforcement learning Garnelo et al, 2016 Every now and then I read a paper that makes a really strong connection with me, one where I can’t stop thinking about the imp…
60
Intel will add deep-learning instructions to its processors
Some of the latest Intel processors support the AVX-512 family of vector instructions. These instructions operate on blocks of 512 bits (or 64 bytes). The benefit of such wide instructions is that even without increasing the processor clock speed, systems can still process a lot more data. Most code today operators…