Dream to Learn is shutting down...

We are very sorry to say that Dream to Learn will be shutting down as of December 28th, 2019. If you have content that you wish to keep, you should make a copy of it before that date.


Canadian Politicians - #deepdreaming

POSTED IN: Data Analytics & Visualization Blog

Deep Dreaming - Google’s artificial neural networks (ANNs)  - 


FROM POPSCI: Google opened the source code up to developers under the name "DeepDream," and now, a couple new websites have sprung up, including a recent one from Psychic VR Lab and (h/t: Prosthetic Knowledge ) and earlier, one from entrepreneur Zain Shah called Deep Neural Net Dreams, or #DeepDream for short.

Both take code from Google's AI and let you upload your own photos, transforming them into eerie, computerized dreamscapes. You can see examples of these images below. Google’s artificial neural networks (ANNs) are used to discern and process the millions of photos scraped by the search giant and organized in Google Images. In the case of the Google Images ANN, Google's developers taught this artificial intelligence hive mind how to recognize certain objects by showing them repeated examples of said object.


I was curious how our Canadian Politicians might look through the lens of the Neural Network - so uploaded a few images - the results are below....

As noted in the Google Blog http://googleresearch.blogspot.com/2015/06/inceptionism-going-deeper-into-neural.html :

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.

We train an artificial neural network by showing it millions of training examples and gradually adjusting the network parameters until it gives the classifications we want. The network typically consists of 10-30 stacked layers of artificial neurons. Each image is fed into the input layer, which then talks to the next layer, until eventually the “output” layer is reached. The network’s “answer” comes from this final output layer


This technique gives us a qualitative sense of the level of abstraction that a particular layer has achieved in its understanding of images. We call this technique “Inceptionism” in reference to the neural net architecture used. See our Inceptionism gallery for more pairs of images and their processed results, plus some cool video animations."



This one is titled:

"Harper's Surprise at Chihuahua in Burrito"


Many thanks to the folks who open-sourced this technology, and to those who made it accessible through blogs and web UI.  #deepdreaming #deepdreams #canadianpolitics


Interested in more content by this author?

About the Author

Ryan Anderson

Ryan Anderson

Hi! I like to play with data, analytics and hack around with robots and gadgets in my garage. Lately I've been learning about machine learning.

About this blog

Description is...<br/>Data Analytics & Visualization Blog - Generating insights from Data since 2013

Created: July 25, 2014


Up Next