Tag Archives: Technology

Philly kills hitchhiking robot


A hitchhiking robot that successfully navigated its way through Canada has been destroyed. In America. In Philadelphia.

According to HitchBot’s creators:

hitchBOT’s trip came to an end last night in Philadelphia after having spent a little over two weeks hitchhiking and visiting sites in Boston, Salem, Gloucester, Marblehead, and New York City. Unfortunately, hitchBOT was vandalized overnight in Philadelphia; sometimes bad things happen to good robots. We know that many of hitchBOT’s fans will be disappointed, but we want them to be assured that this great experiment is not over. For now we will focus on the question “what can be learned from this?” and explore future adventures for robots and humans.

Why Philly? Do we always have to be known as the assholes of the east coast? I can’t wait to see what the lovely residents of the “City of Brotherly Love” will do the thousands of visitors coming to see The Pope.

Update via the CBC:

Some of the robot’s followers went to the area to retrieve the remains after the incident, and its “brain” containing the software is still intact, Smith said. His team is now arranging for the parts to be shipped back to Canada to determine the next step of the experiment.

Tagged , ,

What is Google’s artificial neural network


As a fan of Hunter S. Thompson, I recently came across this article about someone putting Fear and Loathing in Las Vegas in Google’s artificial neural network to create trippy effects.

The results are quite trippy.

After I got over the insane images, I started to wonder what this neural network was:

In machine learning and cognitive science, artificial neural networks (ANNs) are a family of statistical learning models inspired by biological neural networks (the central nervous systems of animals, in particular the brain) and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Artificial neural networks are generally presented as systems of interconnected “neurons” which send messages to each other. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning.

Google’s specific spin on images:

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.

Tagged , , ,