A revolutionary new 3D digital brain atlas : McGill Reporter

A revolutionary new 3D digital brain atlas : McGill Reporter:

Cool.

By Anita Kar,

"Imagine being able to zoom into the brain to see various cells the way we zoom into Google maps of the world and to look at houses on a street. Although the brain is considered the most complex structure in the universe with 86 billion neurons, zooming in on it is now possible thanks to a new brain atlas with unprecedented resolution."

What do memories look like? | KurzweilAI

What do memories look like? | KurzweilAI:

"imaged through cranial windows"

oi..

Creating a IWin32Window from a Win32 Handle

Creating a IWin32Window from a Win32 Handle: "Creating the IWin32Window wrapper class"

Thank you Sir. Here's my code based from yours.

public class WindowWrapper : IWin32Window {
public static WindowWrapper CreateWindowWrapper( IntPtr handle ) {
return new WindowWrapper( handle );
}

private WindowWrapper( IntPtr handle ) {
this.Handle = handle;
}

public IntPtr Handle { get; private set; }
}


Crowdfunded project to create "world's smartest robot" - Boing Boing

Crowdfunded project to create "world's smartest robot" - Boing Boing:

Well, it's a start at least.

CHRIS 4th year demo, Scenario 1b - YouTube

CHRIS 4th year demo, Scenario 1b - YouTube:

Description:

Excerpt of the EU FP7 CHRIS project 4th year demo.
The robot is able to segment the object using motion and learn to associate a given name to it through an interactive phase with the user. To successfully grasp the novel object the robot is trained via a kinesthetic teaching.

Credits: Ciliberto C., Lalleé S., Natale L., Pattacini U., Tikhanoff V.

人工

人工知能ヒトの脳について

33rd Square | Verbal IQ of a Four-Year Old Achieved in AI System

33rd Square | Verbal IQ of a Four-Year Old Achieved in AI System:

'via Blog this'

Again, a cool concept (no pun intended) but this is still preloading an AI with information and rules.
A truer-AI should be able to learn like a child does.

AI MadeOf  紙.

Artificial intelligence ‘sees’ visual illusion « Mind Hacks

Artificial intelligence ‘sees’ visual illusion « Mind Hacks:

Artificial intelligence ‘sees’ visual illusion

A study just published in PLoS Computational Biology has reported that an artificial intelligence system trained to make sense of a simulated natural environment is susceptible to some of the same visual illusions that humans fall for.

In one of these, the ‘Herman grid‘ illusion – illustrated on the right, you may be able to ‘see’ fuzzy patches of grey in the white stripes, despite the fact that there is no grey in the image (click for a bigger version if it’s not clear).

David Corney and Beau Lotto, researchers working in the Lotto Lab (which has a wonderful website by the way), have been training artificial intelligence systems to distinguish surfaces in a simulated natural environment with lots of ‘dead leaf’-like shapes.

When training these sorts of systems, the idea is not to program them with specific rules, but to present an image and let the neural network make a guess.

The researchers then ‘tell’ the AI system whether it is correct in its guess, and it adjusts itself to try and reduce the extent of the error on the next guess. After many learning trials, these sorts of ‘back propagation‘ neural networks can make distinctions between quite complex stimuli.

In this case, Corney and Lotto decided that once the system was fully trained to complete its task successfully, they would test it with some visual illusions experienced by humans.

Interestingly, the AI system was susceptible to the Herman Grid illusion, sensing ‘grey’ where there was none. Other illusions produced similar results.

The fact that both humans and AI system ‘fall’ for the same illusions, suggests that they take advantage of visual abilities that have been shaped by our experience of the visual world.

Link to paper in PLoS Computational Biology (thanks Matt!).
Link to study write-up from the university’s news site.
Link to Lotto Lab website (with loads of cool images and demos).