Banner Archive

Marvel Comics Timeline
Godzilla Timeline



« I Thought of Transmetropolitan | Main | XKeyscore »

The Machines are Learning

I got really excited when i read this. I started thinking about how kewl it would be to build my own AI computer and teach it to perform simple tasks. And then reality set in, and i realized that was a crazy idea for a couple of reasons. Because i don't know the first thing about coding for one. Or building shit for another. Also, i just saw 2001: A Space Odyssey.

The brain performs its canonical task -- learning -- by tweaking its myriad connections according to a secret set of rules. To unlock these secrets, scientists 30 years ago began developing computer models that try to replicate the learning process. Now, a growing number of experiments are revealing that these models behave strikingly similar to actual brains when performing certain tasks. Researchers say the similarities suggest a basic correspondence between the brains' and computers' underlying learning algorithms.
The synapses in the network start out with a random distribution of weights, and the weights are gradually tweaked according to a remarkably simple procedure: The neural firing pattern generated while the machine is being fed data (such as images or sounds) is compared with random firing activity that occurs while the input is turned off.

Each virtual synapse tracks both sets of statistics. If the neurons it connects fire in close sequence more frequently when driven by data than when they are firing randomly, the weight of the synapse is increased by an amount proportional to the difference. But if two neurons more often fire together during random firing than data-driven firing, the synapse connecting them is too thick and consequently is weakened.

Besides moving us closer to someone building Ultron, this work furthers understanding of the human brain which means a better understanding of mental illnesses and finding ways to overcome eye injuries (or other brain/body connection injuries, i would imagine).

I'm so ready for my bionic body.

By min | July 31, 2013, 6:27 PM | Science