Tags » Neural Networks

Google's short film examines the science of voice recognition

I came across a short video by Google where they talk a little bit about voice recognition.

It’s an interesting video where some well known people in the field of voice recognition, give some insights into the evolution of the technology. 67 more words

Tech News

Xenomelia or altered body self-consciousness - some studies and a blog

Xeonemlia is the feeling that one of your limbs is foreign and the desire to amputate it. It is also known as body identity integrity disorder (BIID). 232 more words

Cortical Thickness

Link Roundup, 10/13/14: Deep Neural Networks

Deep Neural Networks

 “At some fundamental level, no one understands machine learning.” —Christopher Olah

“Neural networks are one of the most beautiful programming paradigms ever invented.” — 215 more words

Software Architecture

This company says it can fix the sales process using lots of data science, and even more data

Salt Lake City, Utah, and the surrounding area are home to an under-appreciated number of technology companies, including one that’s using an immense amount of data to help salespeople put their energies in the right places. 697 more words

How to Parallelize Deep Learning on GPUs Part 1/2: Data Parallelism

In my last blog post I showed what to look out for when you build a GPU cluster. Most importantly, you want a fast network connection between your servers and using MPI in your programming will make things much easier than to use the options available in CUDA itself. 1,379 more words

Deep Learning

Can Companies Learn Your Secrets

Description:  “If we wanted to figure out if a customer is pregnant, even if she didn’t want us to know, can you do that? ” 205 more words

Business Model

Derivation: Maximum Likelihood for Boltzmann Machines

In this post I will review the gradient descent algorithm that is commonly used to train the general class of models known as Boltzmann machines. Though the primary goal of the post is to supplement another post on restricted Boltzmann machines, I hope that those readers who are curious about how Boltzmann machines are trained, but have found it difficult to track down a complete or straight-forward derivation of the maximum likelihood learning algorithm for these models (as I have), will also find the post informative. 815 more words