Group items tagged

nice biomimetic approach ...

A key technical barrier to furthering our understanding of complex neural networks has been the lack of tools for the simultaneous spatiotemporal control and detection of activity in a large number of neurons.

Alternative data distributing concept

The ambition of this forum is to create a network, from where ideas and insights can be shared and projects/collaboration can be raised.

Social networking in companies (german only)

Facebook for scientists

be happy and infect your neighbors with it :-) ....

I like the far-thinking approach...

can we use this for our planned network and also host it on our server?? (LS)

nice graphs ... and nice stats

thanks - I was already wondering several times what had happened to this technique that he used at the talk we looked at several times when it was first uploaded ... good that they have made it open source! are they easy to use?

the easiest way to use them is: Google Docs > open/create a spreadsheet > Insert > Gadget > Charts > Motion Chart !! :) You have here a tutorial describing all the steps to get it running.

"Yammer is a tool for making companies and organizations more productive through the exchange of short frequent answers to one simple question: What are you working on?" Have you tried it yet?

Other possible study: get a textbook example of an image of a pen, evolve it just enough so NN can't recognize it anymore, while minimizing the distance between the original and evolved images. EDIT: Its been done already: http://cs.nyu.edu/~zaremba/docs/understanding.pdf

Of course, you can't really use them to extrapolate. The unknown unknown is always the trickiest :P They should just make another class "random bullshit", really and dump all of this stuff in there. I think there's a potential paper right there

A personal interest of mine that I want to explore a bit more in the future. I just bought a ZigBee electricity monitor and I am wondering whether from the signal of the mains one could detect (reliably) the oven turning on, lights, etc. Probably requires Neural Network training. The idea would be to make a simple device which basically saves you money by telling you how much electricity you are wasting. Then again, its probably already done by Google...

Randomly I found this: http://spectrum.ieee.org/view-from-the-valley/consumer-electronics/gadgets/curb-startup-home-electricity-tracking Isn't it a similar kind of stuff Thijs?

haha, yep, that's it... but we can do better than that right! :)

hard to choose ....

There you go, the latest-and-greatest chip is there. Now the only remaining tiny detail - program it.

Let's buy it first and we'll figure the rest out later :P

I mainly see neural networks in this... maybe some evolutionary stuff :))

A hybrid image classification method was employed for this specific purpose by incorporating the advantages of both pixel-based and object-based image classification approaches. This was performed in two steps: firstly, a pixel-based image classification method, i.e., artificial neural network was applied to classify potential targets with similar spectral reflectance at pixel level; and then an object-based image classification method was used to further differentiate animal targets from the surrounding landscapes through the applications of expert knowledge. As a result, the large animals in two pilot study areas were successfully detected with an average count error of 8.2%, omission error of 6.6% and commission error of 13.7%. The results of the study show for the first time that it is feasible to perform automated detection and counting of large wild animals in open savannahs from space

And Paul, it includes neural networks!

I kept telling you guys but you just laughed and laughed :))

Neural Networks to analyse sleeplessness.

Taking out the trial and error network design and adding ensembles.

"A paper posted online in January takes theoretical computer scientists halfway toward proving one of the biggest conjectures in their field. The new study, when combined with three other recent papers, offers the first tangible progress toward proving the Unique Games Conjecture since it was proposed in 2002 by Subhash Khot, a computer scientist now at New York University. Over the past decade and a half, the conjecture - which asks whether you can efficiently color networks in a certain way - has inspired discoveries in topics as diverse as the geometry of foams and the stability of election systems. And if the conjecture can be proved, its implications will reach far beyond network-coloring: It will establish what is the best algorithm for every problem in which you're trying to satisfy as many as possible of a set of constraints - the rules in a sudoku puzzle, or the seating preferences of a collection of wedding guests, for instance."