@Disembodied: Good news :)

[Lestradae]

Have a look at this:

http://blogs.zdnet.com/emergingtech/?p=1009&tag=nl.e550

No more need for legs, arms ... etc.

[DaddyHoggy]

Nice post - thanks for spotting it and sharing it with us. What I found distrurbing were many of the comments from people who clearly hadn't either fully read and/or understood the article...

[Disembodied]

[Lestradae]

What I found distrurbing were many of the comments from people who clearly hadn't either fully read and/or understood the article...

Sadly, there will always be luddites, choosing death over life ...

Myself, having a look at the kind of converging bio-, cyber- and computer technology that is advancing and growing together, more have a small flame of hope for the following in our lifetimes:

http://www.youtube.com/watch?v=DXktzI4tST0

[DaddyHoggy]

[JohnnyBoy]

Have a look at this:

http://blogs.zdnet.com/emergingtech/?p=1009&tag=nl.e550

No more need for legs, arms ... etc.

I wonder how long it will be before that robot's available as a kit from Tandy. What does the pin-out diagram for a culture of neurons look like?

[DaddyHoggy]

If it's coming from Tandy/RS then there will be a critical part missing that will lead to a self configuration of your incomplete device which will lead to it taking over the world and using humans as batteries...

Can't imagine playing with real neurons - I had enough problems playing with simulated ones - specifically back-propagation Multi-layer-Perceptrons (MLP) networks - for battlefield (shape) ID (i.e. "Durr - it's a tank", "Durr, I fink its an APC") - never did get it to work properly but I still got an MSc out of it - phew!

[Disembodied]

Can't imagine playing with real neurons - I had enough problems playing with simulated ones - specifically back-propagation Multi-layer-Perceptrons (MLP) networks - for battlefield (shape) ID (i.e. "Durr - it's a tank", "Durr, I fink its an APC") - never did get it to work properly but I still got an MSc out of it - phew!

DH, was it anything like this?

[DaddyHoggy]

That's just precious!

My project was related in particular to this gritty problem:

Verification

[Tank: yes!] But the scientists were worried: had it actually found a way to recognize if there was a tank in the photo, or had it merely memorized which photos had tanks and which did not? This is a big problem with neural networks, after they have been trained you have no idea how they arrive at their answers, they just do. The question was did it understand the concept of tanks vs. no tanks, or had it merely memorized the answers? So the scientists took out the photos they had been keeping in the vault and fed them through the computer. The computer had never seen these photos before -- this would be the big test. To their immense relief the neural net correctly identified each photo as either having a tank or not having one.

My project, extracted the weightings from the neural network and built a map that showed precisely how it learned to ID the pictures. While it was only "ok" at spotting the stuff in the images - the technique itself worked like a dream. It couldn't get any better because there was only so much imagery the MOD was prepared to release to me for the study...

It's based on this work by Vaughn - my supervisor: http://www.marilyn-vaughn.co.uk/

[polyh]

The military was now the proud owner of a multi-million dollar mainframe computer that could tell you if it was sunny or not.

Great! Why is the weather report still wrong sometimes?

[Disembodied]

The military was now the proud owner of a multi-million dollar mainframe computer that could tell you if it was sunny or not.

Great! Why is the weather report still wrong sometimes?

"Was" sunny, not "will be"... Good grief, man, do you expect miracles?

[FSOneblin]

I understand how it works; magic! Kevin Warwick is a witch! Burn the witch! I will find out how it works later.

Don't Panic: FSOneblin