neural network

29 posts
What a neural network sees

Neural networks can feel like a black box, because, well, for most people they are. Supply input and a computer spits out results. The trouble with not understanding what goes on under the hood is that it’s hard to improve on what we know. It’s also a problem when someone uses the tech for malicious purposes, as people are prone to do. So, folks from Google Brain break down the...

0 0
Sentence gradients to see the space between two sentences

In a project he calls Sentence Space, Robin Sloan implemented a neural network so that you can enter two sentences and get a gradient of the sentences in between. I’d never even bothered to imagine an interpolation between sentences before encountering the idea in a recent academic paper. But as soon as I did, I found it captivating, both for the thing itself—a sentence… gradient?—and for the larger artifact it...

0 0
Handwriting with a neural network

Continuing the neural network explorations, Shan Carter and team of Google Brain and Cloud, look at how a network deals with handwriting by placing them in the same space. The black box reputation of machine learning models is well deserved, but we believe part of that reputation has been born from the programming context into which they have been locked into. The experience of having an easily inspectable model available...

0 0
Emoji semantic space

Dango is an Android app that predicts relevant emojis as you type. Xavier Snelgrove, the CTO for the group, explains how they use neural networks to make that happen. Recently, neural networks have become the tool of choice for a variety of tough computer-science problems: Facebook uses them to identify faces in photos, Google uses them to identify everything in photos. Apple uses them to figure out what you’re saying...

0 0