Skip to main content

Home/ Advanced Concepts Team/ Group items matching "neural" in title, tags, annotations or url

Group items matching
in title, tags, annotations or url

Sort By: Relevance | Date Filter: All | Bookmarks | Topics Simple Middle
Juxi Leitner

Convolutional Neural Networks for Visual Recognition - 3 views

cs.stanford.edu/...deepimagesent

ai computer vision learning classification deep university INF

shared by Juxi Leitner on 28 Nov 14 - No Cached
Paul N liked it
  • Juxi Leitner on 28 Nov 14
     
    pretty impressive stuff!
  • ...3 more comments...
  • Paul N on 28 Nov 14
     
    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
  • Luís F. Simões on 01 Dec 14
  • Paul N on 04 Dec 14
     
    Seems like quite the trend. And the fact that google still tries to use LSTMs is even more surprising.
  • Luís F. Simões on 04 Dec 14
     
    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.
  • Paul N on 05 Dec 14
     
    There are a few papers on them. Though you have to be lucky to get them to work. The backprop is horrendous.
Tom Gheysens

The ABC's of animal speech: Not so random after all -- ScienceDaily - 3 views

www.sciencedaily.com/...140819200209.htm

animal speech BIO science

shared by Tom Gheysens on 22 Aug 14 - No Cached
  • Paul N on 23 Aug 14
     
    maybe we can use some neural networks to do animal "speech" recognition? :P
Luís F. Simões

AI, Robotics, and the Future of Jobs | Pew Research Center's Internet & American Life Project - 0 views

www.pewinternet.org/...future-of-jobs

AI robotics

shared by Luís F. Simões on 05 Sep 14 - No Cached
Paul N liked it
  • Some 1,896 experts responded to the following question: The economic impact of robotic advances and AI—Self-driving cars, intelligent digital agents that can act for you, and robots are advancing rapidly. Will networked, automated, artificial intelligence (AI) applications and robotic devices have displaced more jobs than they have created by 2025?
  • Paul N on 08 Sep 14
     
    I mainly see neural networks in this... maybe some evolutionary stuff :))
Thijs Versloot

ESA APP CAMP - Enter the Challenge! - 1 views

www.app-camp.eu

big data esa app challenge

shared by Thijs Versloot on 27 Nov 14 - No Cached
  • Thijs Versloot on 27 Nov 14
     
    Another Appathon with the aim to allow access to vast amounts of 'space data' and then play around.. In other words, a neural network's guy wet dream, so Paul, what are you waiting for?
  • Paul N on 28 Nov 14
     
    I'm not really an app developer :P But I'll think about it
Daniel Hennes

Google Just Open Sourced the Artificial Intelligence Engine at the Heart of Its Online Empire - 2 views

www.wired.com/...artificial-intelligence-engine

technology AI

shared by Daniel Hennes on 10 Nov 15 - No Cached
  • Daniel Hennes on 10 Nov 15
     
    TensorFlow is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well.
  • Paul N on 11 Nov 15
     
    And the interface even looks a bit less retarded than theano
zoervleis

Google's Go AI Beats Professional Player - 0 views

www.nature.com/...nature16961.html

shared by zoervleis on 27 Jan 16 - No Cached
  • zoervleis on 27 Jan 16
     
    This is the biggest breakthrough in game AI (and one of the biggest in AI in general) since Deep Blue beat Kasparov in chess: For the first time, a human professional player was defeated in the game of Go. The approach was a combination of tree search and deep neural networks. Very proud of a former colleague on the team at Google Deepmind!
  • Paul N on 29 Jan 16
     
    Funny enough, facebook also had a very similar paper around the same time.
mkisantal

Better Language Models and Their Implications - 1 views

blog.openai.com/better-language-models

AI

shared by mkisantal on 15 Feb 19 - No Cached
  • mkisantal on 15 Feb 19
     
    Just read some of the samples of text generated with their neural networks, insane.
  • ...3 more comments...
  • mkisantal on 15 Feb 19
     
    "Pérez and his friends were astonished to see the unicorn herd. These creatures could be seen from the air without having to move too much to see them - they were so close they could touch their horns. While examining these bizarre creatures the scientists discovered that the creatures also spoke some fairly regular English. Pérez stated, "We can see, for example, that they have a common 'language,' something like a dialect or dialectic."
  • Marcus Maertens on 15 Feb 19
     
    Shocking. I assume that this could indeed have severe implications if it gets in the "wrong hands".
  • marliesarnhof on 18 Feb 19
     
    "Feed it the first few paragraphs of a Guardian story about Brexit, and its output is plausible newspaper prose, replete with "quotes" from Jeremy Corbyn, mentions of the Irish border, and answers from the prime minister's spokesman." https://www.youtube.com/watch?time_continue=37&v=XMJ8VxgUzTc "Feed it the opening line of George Orwell's Nineteen Eighty-Four - "It was a bright cold day in April, and the clocks were striking thirteen" - and the system recognises the vaguely futuristic tone and the novelistic style, and continues with: "I was in my car on my way to a new job in Seattle. I put the gas in, put the key in, and then I let it run. I just imagined what the day would be like. A hundred years from now. In 2045, I was a teacher in some school in a poor part of rural China. I started with Chinese history and history of science." (https://www.theguardian.com/technology/2019/feb/14/elon-musk-backed-ai-writes-convincing-news-fiction)
  • marliesarnhof on 18 Feb 19
     
    It's really lucky that it was OpenAI who made that development and Elon Musk is so worried about AI. This way at least they try to assess the whole spectrum of abilities and applications of this model before releasing the full research to the public.
  • mkisantal on 18 Feb 19
     
    They released a smaller model, I got it running on Sandy. It's fairly straight forward: https://github.com/openai/gpt-2
dharmeshtailor

Opening the Black Box of Deep Neural Networks via Information Theory - 1 views

www.youtube.com/watch

technology AI

shared by dharmeshtailor on 09 Apr 18 - No Cached
Dario Izzo liked it
dharmeshtailor

Comeback for Genetic Algorithms...Deep Neuroevolution! - 5 views

eng.uber.com/deep-neuroevolution

AI technology

shared by dharmeshtailor on 27 Feb 18 - No Cached
  • dharmeshtailor on 27 Feb 18
     
    Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. For paper see: https://arxiv.org/pdf/1712.06567.pdf
  • Marcus Maertens on 28 Feb 18
     
    Interesting pointers in this one! I would like to explore neuroevolution as well, although it seems extremely resource-demanding?
  • Dario Izzo on 06 Mar 18
     
    Not necessarily, I think it can be made to be much faster hybridizing it with backprop and Taylor maps. Its one ideas in the closet we still have not explored (Differential Intelligence: accelerating neuroevolution).
jcunha

Alibaba is making its own neural network chip - 3 views

technode.com/...alibaba-npu

AI chips

shared by jcunha on 22 Apr 18 - No Cached
  • jcunha on 22 Apr 18
     
    The race for the AI chips intensifies.
  • jcunha on 22 Apr 18
darioizzo2

Scientists Have Trained an AI to Spot Obesity From Space - 5 views

www.sciencealert.com/e-deep-learning-neural-network

shared by darioizzo2 on 19 Mar 19 - No Cached
LeopoldS and microno95 liked it
  • darioizzo2 on 19 Mar 19
     
    If it can be done for obesity, I guess noise is also an option right? :)
  • LeopoldS on 21 Mar 19
     
    love it
mkisantal

Robots Made Out of Branches Use Deep Learning to Walk - IEEE Spectrum - 1 views

spectrum.ieee.org/...ee-branches-deep-learning-walk

AI BIO

shared by mkisantal on 05 Jul 19 - No Cached
  • mkisantal on 05 Jul 19
     
    Random branches are collected, scanned to 3D, and connected with servos. Then a neural network is trained to control this "robot".
microno95

Introducing LCA: Loss Change Allocation for Neural Network Training | Uber Engineering Blog - 2 views

eng.uber.com/loss-change-allocation

AI

shared by microno95 on 10 Sep 19 - No Cached
  • microno95 on 10 Sep 19
     
    Fascinating insight into the question of how networks learn.
jcunha

HBP Neuromorphic Computing Platform Guidebook (WIP) - 0 views

electronicvisions.github.io/hbp-sp9-guidebook

neuromorphic technology Human Brain Project neural

shared by jcunha on 09 Mar 17 - No Cached
  • jcunha on 09 Mar 17
     
    "The Neuromorphic Computing Platform allows neuroscientists and engineers to perform experiments with configurable neuromorphic computing systems. The platform provides two complementary, large-scale neuromorphic systems built in custom hardware at locations in Heidelberg, Germany (the "BrainScaleS" system, also known as the "physical model" or PM system) and Manchester, United Kingdom (the "SpiNNaker" system, also known as the "many core" or MC system)."
marenr

NeuroNex - Odor2Action - 0 views

www.odor2action.org

biomimetics chemoreception neuroscience olfactory BIO odor localization

shared by marenr on 05 Jan 21 - No Cached
  • marenr on 05 Jan 21
     
    Let's keep a eye on this... Animals use odor cues to navigate through their environments, helping them locate targets and assess danger. Much of how animal brains organize, read out, and respond to odor stimuli across spatial and temporal scales is not well understood. To tackle these questions, Odor2Action uses a highly interdisciplinary team science approach. Our work uses fruit fly, honeybee, and mouse models to determine how neural representations of odor are generated, reformatted, and translated to generate useful behaviors that guide how animals interact with their environment.
  • LeopoldS on 07 Jan 21
     
    reminds me of the methan smelling source finding study we did ...
eblazquez

Intel launches its next-generation neuromorphic processor-so, what's that again? | Ars Technica - 1 views

arstechnica.com/...nd-why-intels-excited-about-it

technology AI

shared by eblazquez on 04 Oct 21 - No Cached
  • eblazquez on 04 Oct 21
     
    Seems to be a fun playground for Spiking Neural Networks right (from my newbie PoV)?
dodo47

Plenoxels: Radiance Fields without Neural Networks - 1 views

arxiv.org/2112.05131

shared by dodo47 on 11 Dec 21 - No Cached
  • dodo47 on 11 Dec 21
pablo_gomez

Introducing Triton: Open-Source GPU Programming for Neural Networks - 1 views

www.openai.com/triton

INF AI

shared by pablo_gomez on 28 Jul 21 - No Cached
  • pablo_gomez on 28 Jul 21
     
    Might be of interest for torchquad and other projects
« First ‹ Previous 61 - 79 of 79
Showing 20▼ items per page