Tags » Neural Networks

Google feeds its AI machines steamy romance novels to improve natural language processing

Over the past couple of years, Google has been implementing a number of AI, or machine-learning technologies, in to its products. Whether it’s intuitive search within the Photos… 460 more words

Google Corporate

Neural Networks Are Impressively Good At Compression

I’m trying to get into neural networks. There have been a couple big breakthroughs in the field in recent years and suddenly my side project of messing around with programming languages seemed short sighted. 2,484 more words


Plug in a USB Stick and you have a neural network

All technologies are huge, bulky and expensive at first, and over time, they become smaller, denser and more affordable. Decades ago we had computers that filled rooms, now we have more powerful ones smaller than a credit card. 270 more words

Company Announcement

Variational Hamiltonian Monte Carlo via Score Matching

This is an arXival (maybe by now ICML paper?) by Zhang, Shahbaba and Zhao. It suggest fitting an emulator/surrogate to the target density via score matching and then use the gradients of  rather than those of  for generating proposal with HMC. 187 more words

Monte Carlo

On The Horizon - Part Five (... Side A)

This is Part Five of a six part mini series on Predicting the Future. If you’re just tuning in, catch up on our foolishness with  3,613 more words


IBM’s resistive computing could massively accelerate AI — and get us closer to Asimov’s Positronic Brain

April 23, 2016

With the recent rapid advances in machine learning has come a renaissance for neural networks — computer software that solves problems a little bit like a human brain, by employing a complex process of pattern-matching distributed across many virtual nodes, or “neurons.” Modern compute power has enabled neural networks to recognize images, speech, and faces, as well as to pilot self-driving cars, and win at Go and Jeopardy. 1,126 more words

Computer Science