Artificial Neocortex

@ANeocortex

From Von Neumann architecture to neuromorphic, transistors to memristors. Narrow AI to AGI.

Vrijeme pridruživanja: svibanj 2014.

Tweetovi

Blokirali ste korisnika/cu @ANeocortex

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @ANeocortex

  1. Prikvačeni tweet
    21. pro 2019.
    Prikaži ovu nit
    Poništi
  2. Poništi
  3. proslijedio/la je Tweet
    prije 16 sati

    The Akida Neuromorphic System-on-Chip (NSoC) is the first in a new breed of neuromorphic computing chips that puts artificial intelligence at the edge and the enterprise.

    Poništi
  4. proslijedio/la je Tweet
    prije 21 sat

    Very nice article on computing needs, negative environmental impacts and the promise of neuromorphic computing by Florence Greatrix. It covers some of the work we do at UCL.

    Poništi
  5. proslijedio/la je Tweet
    4. velj

    Presenting our glorious poster on brain-inspired controllers running on hardware SpiNNakee with my PhD buddy

    Poništi
  6. 4. velj
    Poništi
  7. proslijedio/la je Tweet
    3. velj

    'We built a five-layer memristor-based CNN to perform MNIST10 image recognition, & achieved a high accuracy of more than 96 per cent...The memristor-based CNN neuromorphic system has an energy efficiency > two orders of magnitude greater than that of state-of-the-art GPUs.'

    Poništi
  8. 1. velj
    Poništi
  9. proslijedio/la je Tweet
    28. sij

    BNC researcher, Peide Ye, the Richard J. and Mary Jo Schwartz Professor of and team have created a more feasible way to combine transistors and memory on a chip, potentially bringing faster computing.

    Poništi
  10. proslijedio/la je Tweet
    31. sij

    New 2D materials made into synapse-like devices for future chips.

    Poništi
  11. 31. sij
    Poništi
  12. proslijedio/la je Tweet
    30. sij

    Neuromorphic Chip Maker Takes Aim At The Edge - Neuromorphic computing has garnered a lot of attention over the past few years, largely driven by its potential to deliver low-power.

    Poništi
  13. proslijedio/la je Tweet
    30. sij

    Novel memristor-enabled computation in memory architecture could revolutionize artificial-intelligence hardware

    Poništi
  14. proslijedio/la je Tweet
    28. sij

    Our research project Astrosite™ - a world first space imaging method - is an example of neuromorphic engineering technology we are working on here at 's International Centre for Neuromorphic Systems

    Poništi
  15. 29. sij

    Organismic materials for beyond von Neumann machines

    Prikaži ovu nit
    Poništi
  16. 29. sij
    Poništi
  17. proslijedio/la je Tweet
    28. sij

    Bioinspired: co-locating logic and memory, low precision computation, avoiding multiplication altogether, accepting some errors without formal ECC

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    29. sij

    New Research: LAO-NCS: Laser Assisted Spin Torque Nano Oscillator-Based Neuromorphic Computing System: Dealing with big data, especially the videos and images, is the biggest challenge of existing Von-Neumann machines while the human brain,…

    Poništi
  19. proslijedio/la je Tweet
    28. sij

    New paper with and , our first hybrid CMOS/RRAM chip! In-memory implementation of Binarized Neural Networks, and how you can deal with bit errors.

    Prikaži ovu nit
    Poništi
  20. 26. sij
    Poništi
  21. proslijedio/la je Tweet
    24. sij

    The Akida NSoC provides a low-power, high throughput solution for complex object classification applications. It can directly connect to a variety of sensor inputs, including Lidar, pixels, dynamic vision sensors (DVS), as well as others -More info:

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·