Skip to main content

Home/ Advanced Concepts Team/ Group items tagged ai

Rss Feed Group items tagged

alekenolte

Research Blog: Inceptionism: Going Deeper into Neural Networks - 0 views

  •  
    Deep neural networks "dreaming" psychedelic images
  • ...2 more comments...
  •  
    Although that's not technically correct. The networks don't actually generate the images, rather the features that get triggered in the network already get amplified through some heuristic. Still fun tho`
  •  
    Now in real time:
    http://www.twitch.tv/317070
  •  
    Yes, true for the later images, but for the first images they start with random noise and a 'natural image' prior, no?
    But I guess calling it "hallucinating" might have been more accurate ;)
krzysieknowak

Scientists Are Turning Their Backs on Algorithms Inspired By Nature - 2 views

  •  
    "Over the past couple of decades, the research literature has filled up with endless new nature-based metaphors for algorithms. You can find algorithms based on the behaviour of cuckoos, bees, bats, cats, wolves, galaxy formation and black holes. (...) All researchers have been doing is wasting time on developing new approaches that are probably little better than existing ones. And the language of each metaphor then invades the literature, distracting people from using the already sufficiently expressive terminology of mathematics and, above all, working together to find the best way forward."

    The golden era of fireworks-like algorithm is about to end
  •  
    Lies, lies, all lies. They will never go away. Papers need to be published.
jcunha

Training and operation of an integrated neural network based on memristors - 0 views

  •  
    Almost in time for the workshop last week!
    This new Nature paper (e-mail me for full paper) claims training and usage of neural network implemented with metal-oxide memristors, without selector CMOS. They used it to implement a delta-rule algorithm for classification of 3x3 pixel black and white letters. Very impressive work!!!!
  •  
    For those not that much into the topic, see the Nature's News and View section www.nature.com/nature/journal/v521/n7550/full/521037a.html?WT.ec_id=NATURE-20150507 where they feature this article.
Dario Izzo

Study maps extroversion types in the brain's anatomy - 6 views

  •  
    Anna will rule the world!!!!
  •  
    So... start preparing to be required to attach your brain scan along with your job application...
Juxi Leitner

Game-playing software holds lessons for neuroscience : Nature News & Comment - 4 views

  •  
    DeepMind actually got a comp-sci paper into nature...
jcunha

AI system teachs itself to play 49 classic computer games - 3 views

shared by jcunha on 26 Feb 15 - No Cached
Paul N and Heha Zant liked it
  •  
    In this paper published on Nature, AI researchers used deep Q-network with very good adaptability and obtained performances comparable to those of a human games tester.
  •  
    Bastards! And that was to be my next idea.
    Still no recurrency as I see it so far, so this is just some fancy way to do a markov model.
    Not sure if this is that particular paper or an earlier version but here it is for those interested:
    http://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
Thijs Versloot

Advanced AI May Be Coming to Smartphones | MIT Technology Review - 2 views

  •  
    Software that roughly mimics the way the brain works could give smartphones new smarts-leading to more accurate and sophisticated apps for tracking everything from workouts to emotions. The software exploits an artificial-intelligence technique known as deep learning, which uses simulated neurons and synapses to process data.
Thijs Versloot

Artificially-intelligent Robot Scientist 'Eve' could boost search for new drugs - 4 views

  •  
    Eve, an artificially-intelligent 'robot scientist' could make drug discovery faster and much cheaper, say researchers writing in the Royal Society journal Interface. The team has demonstrated the success of the approach as Eve discovered that a compound shown to have anti-cancer properties might also be used in the fight against malaria.
  •  
    Unfortunately, "make drug discovery faster and much cheaper" actually means "increase profit margin for pharmaceutical companies"...
LeopoldS

A way forward to solve the hard problem of consciousness - 5 views

  •  
    enjoy ....
  •  
    ok, but if we first have to define consciousness before starting dealing with any physics, isn't a large pause looming ahead, proposed by the author?
  •  
    I kind of subscribe to Tononi's information theory approach to consciousness:
    http://www.biolbull.org/content/215/3/216.full

    And of course the watered down wikipedia version for whoever lacks the patience to read the whole treatise
    http://en.wikipedia.org/wiki/Integrated_information_theory
Marcus Maertens

Computer Scientists Generate A Self-Aware Mario That Can Learn And Feel | IFLScience - 2 views

  •  
    Here we go! AI for Mario has arrived. What is still missing is the Italian accent in his robo-voice though. To compensate for that, we have a lot of German accent in the Youtube-video. Make sure to check it out if you always liked the background music from the games. Putting the trolling aside, I honestly like the idea! There is still some way to go, but maybe we will watch and even pay to be able to see twitch-streams of self-ware bots one day?
  •  
    I'm actually considering doing an twitch-bot channel. Why pay when you can cash in?
    Kind of lazy tho`
jcunha

Artifitial Intelligence to predict solar flares - 0 views

  •  
    A team from Stanford showing possibility of solar flare prediction using AI techniques and data from the NASA SDO observatory.
krzysieknowak

Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable ... - 4 views

  •  
    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
Ma Ru

Shop which knows your name - 6 views

  •  
    I'm sure Leo will love it. Yet another argument not to have a facebook account or a smartphone.
  • ...1 more comment...
  •  
    absolutely ... so you ditched yours also already?
  •  
    Ditched? I never had either!

    But then on the other hand a recent Dilbert summarised me pretty well...
  •  
    so you also don't have a mobile phone? I thought I knew only one person of my age who does not have one yet ... congratulations
LeopoldS

physicists explain what AI researchers are actually doing - 5 views

  •  
    love this one ... it seems to take physicist to explain to the AI crowd what they are actually doing ...

    Deep learning is a broad set of techniques that uses multiple layers of representation to automatically learn relevant features directly from structured data. Recently, such techniques have yielded record-breaking results on a diverse set of difficult machine learning tasks in computer vision, speech recognition, and natural language processing. Despite the enormous success of deep learning, relatively little is understood theoretically about why these techniques are so successful at feature learning and compression. Here, we show that deep learning is intimately related to one of the most important and successful techniques in theoretical physics, the renormalization group (RG). RG is an iterative coarse-graining scheme that allows for the extraction of relevant features (i.e. operators) as a physical system is examined at different length scales. We construct an exact mapping from the variational renormalization group, first introduced by Kadanoff, and deep learning architectures based on Restricted Boltzmann Machines (RBMs). We illustrate these ideas using the nearest-neighbor Ising Model in one and two-dimensions. Our results suggests that deep learning algorithms may be employing a generalized RG-like scheme to learn relevant features from data.
Marcus Maertens

Magic tricks created using artificial intelligence for the first time - 3 views

  •  
    Let an AI develop your magic tricks! (The one with the smart phone is actually neat)
  •  
    They published it in Frontiers of Psychology...?
Marcus Maertens

The Grid - 1 views

  •  
    Let an AI build up your web page for just 96$ per year!
  •  
    Amazing!
    Not even coding jobs are safe from AI anymore!
    AI programming will be the last bastion in the struggle against automation. Get ready :)
Juxi Leitner

Convolutional Neural Networks for Visual Recognition - 3 views

  •  
    pretty impressive stuff!
  • ...3 more comments...
  •  
    Amazing how some guys from some other university also did pretty much the same thing (although they didn't use the bidirectional stuff) and published it just last month. Just goes to show you can dump pretty much anything into an RNN and train it for long enough and it'll produce magic.
    http://arxiv.org/pdf/1410.1090v1.pdf
  •  
    Seems like quite the trend.
    And the fact that google still tries to use LSTMs is even more surprising.
  •  
    LSTMs: that was also the first thing in the paper that caught my attention! :)
    I hadn't seen them in the wild in years... My oversight most likely. The paper seems to be getting ~100 citations a year. Someone's using them.
  •  
    There are a few papers on them. Though you have to be lucky to get them to work. The backprop is horrendous.
Christophe Praz

Brain decoder can eavesdrop on your inner voice - 4 views

  •  
    "As you read this, your neurons are firing - that brain activity can now be decoded to reveal the silent words in your head TALKING to yourself used to be a strictly private pastime. That's no longer the case - researchers have eavesdropped on our internal monologue for the first time. The achievement is a step towards helping people who cannot physically speak communicate with the outside world."

    Or alternatively, a step towards snooping into individuals' privacy.
  •  
    Soon we'll be able to see movies about our dreams!
  •  
    Only if you are willing to have a chip implanted into/onto your brain though ^^
1 - 20 of 269 Next › Last »
Showing 20 items per page