Search Box

Monday, June 22, 2015

Google Builds "Hallucinating" Neural Network

Inceptionism: Going Deeper into Neural Networks

Alexander Mordvintsev, Christopher Olah & Mike Tyka | June 17, 2015


Artificial Neural Networks have spurred remarkable recent progress in image classification and speech recognition. But even though these are very useful tools based on well-known mathematical methods, we actually understand surprisingly little of why certain models work and others don’t. So let’s take a look at some simple techniques for peeking inside these networks.
...Instead of exactly prescribing which feature we want the network to amplify, we can also let the network make that decision. In this case we simply feed the network an arbitrary image or photo and let the network analyze the picture. We then pick a layer and ask the network to enhance whatever it detected. Each layer of the network deals with features at a different level of abstraction, so the complexity of features we generate depends on which layer we choose to enhance. For example, lower layers tend to produce strokes or simple ornament-like patterns, because those layers are sensitive to basic features such as edges and their orientations.

<more at http://googleresearch.blogspot.com/2015/06/inceptionism-going-deeper-into-neural.html; related link: http://www.csmonitor.com/Technology/2015/0619/Google-builds-neural-network-makes-it-hallucinate-video (Google builds neural network, makes it hallucinate (+Video)>

No comments:

Post a Comment