Michael Kiselev
CEO @ Megaputer Intelligence
Cheboksary

Pulsed neural networks and neural chips. What separates us from computation capacity of the human brain?

  • Auditorium: ARCHIVE
  • Category: Development
  • Level: Professional
  • Section: Machine learning

Description:

  • Development of computational system with capacities approximated to those of the human brain.
  • Pulsed neural networks as physiologically similar models. Their peculiarities and advantages in comparison with traditional neural networks.
  • Prospective of pulsed neural networks implementation in form of specialized neuromorphic computers.
  • Key moment is learning algorithms for pulsed neural networks.
  • The most prospective approach is based on Hebb’s Law of synaptic plasticity. Algorithm L2TP as an example.
  • Synthesis of a network with necessary properties. Processes of network self-organization.

  • О спикере

    Michael Kiselev

    CEO @ Megaputer Intelligence
    Cheboksary

    Director of Megaputer Intelligence LLC, one of the largest producers of data & text mining systems in Russia, Candidate of Technical Sciences. Beside development of commercial systems of data mining I also conduct researches in the sphere of pulsed neural networks and computational linguistics. The greatest interest has lately been risen by development of different approaches to implementation of pulsed neural networks on specialized neuromorphic computers for processing of big flows of multimodal sensory data and construction of taught control systems. The latest achievement in computational linguistics is development of an efficient and accurate syntax analyzer and a dependency parser for Russian language sentences.


    Похожие доклады