• Corpus ID: 8490872

A theoretical basis for efficient computations with noisy spiking neurons

  title={A theoretical basis for efficient computations with noisy spiking neurons},
  author={Zeno Jonke and Stefan Habenschuss and Wolfgang Maass},
Network of neurons in the brain apply - unlike processors in our current generation of computer hardware - an event-based processing strategy, where short pulses (spikes) are emitted sparsely by neurons to signal the occurrence of an event at a particular point in time. Such spike-based computations promise to be substantially more power-efficient than traditional clocked processing schemes. However it turned out to be surprisingly difficult to design networks of spiking neurons that are able… 

Figures from this paper

On the Algorithmic Power of Spiking Neural Networks

A dual view of the SNN dynamics is seen, under which SNN can be viewed as a new natural primal-dual algorithm for the l1 minimization problem, which is of independent interest and may potentially find interesting interpretation in neuroscience.

To Spike or Not to Spike: That Is the Question

  • W. Maass
  • Computer Science, Biology
    Proc. IEEE
  • 2015
Recent progress in understanding how complex computations can be carried out with such stochastically spiking neurons is discussed, and the viability of such a merger is examined.

Brain-Inspired Models and Systems for Distributed Computation

The purpose of this thesis is to investigate key characteristics of biological nervous systems and suggest ways of incorporating these principles in artificial systems and demonstrate how a non-trivial network topology, featuring predominantly local connectivity, can be achieved by taking into account these principles.

Integrating Temporal Information to Spatial Information in a Neural Circuit

This paper designs three networks that solve three problems -- "first consecutive spikes counting", "total spikes counting" and "$k-spikes temporal to spatial encoding" -- to model how brains extract temporal information into spatial information from different neural codings.

Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors

It is shown that in discrete time and in the absence of noise, the class of positive neural networks captures the so-called monotone-regular behaviors, which are based on regular languages.

Spiking analog VLSI neuron assemblies as constraint satisfaction problem solvers

This work shows how stochasticity can be achieved by implementing deterministic models of integrate and fire neurons using subthreshold analog circuits that are affected by thermal noise and presents an efficient implementation of spike-based CSP solvers using a reconfigurable neural network VLSI device, and the device's intrinsic noise as a source of randomness.



Neural Dynamics as Sampling: A Model for Stochastic Computation in Recurrent Networks of Spiking Neurons

A neural network model is proposed and it is shown by a rigorous theoretical analysis that its neural activity implements MCMC sampling of a given distribution, both for the case of discrete and continuous time.

Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons

Ubiquitous stochastic features of networks of spiking neurons, such as trial-to-trial variability and spontaneous activity, are necessary ingredients of the underlying computational organization and can be scaled up to neural emulations of probabilistic inference in fairly large graphical models.

Networks of Spiking Neurons: The Third Generation of Neural Network Models

  • W. Maass
  • Computer Science
    Electron. Colloquium Comput. Complex.
  • 1996

A million spiking-neuron integrated circuit with a scalable communication network and interface

Inspired by the brain’s structure, an efficient, scalable, and flexible non–von Neumann architecture is developed that leverages contemporary silicon technology and is well suited to many applications that use complex neural networks in real time, for example, multiobject detection and classification.

Solving nonlinear optimization problems using networks of spiking neurons

  • R. MalakaSebastian Buck
  • Computer Science
    Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
  • 2000
The goal of this paper is to prove that neural networks like the SRM (Spike Response Model) are able to solve nonlinear optimization problems and to demonstrate this for the traveling salesman problem.

Stochastic Computations in Cortical Microcircuit Models

It is shown that the inherent stochastic dynamics of generic cortical microcircuits enables them to quickly generate approximate solutions to difficult constraint satisfaction problems, where stored knowledge and current inputs jointly constrain possible solutions.

Predicting spike timing of neocortical pyramidal neurons by simple threshold models

Neurons generate spikes reliably with millisecond precision if driven by a fluctuating current—is it then possible to predict the spike timing knowing the input? We determined parameters of an

Decorrelation of Neural-Network Activity by Inhibitory Feedback

It is shown that inhibitory feedback efficiently suppresses pairwise correlations and, hence, population-rate fluctuations, thereby assigning inhibitory neurons the new role of active decorrelation.

Six Networks on a Universal Neuromorphic Computing Substrate

This study presents a highly configurable neuromorphic computing substrate and uses it for emulating several types of neural networks, including a mixed-signal chip, which has been explicitly designed as a universal neural network emulator.

A Large-Scale Model of the Functioning Brain

A 2.5-million-neuron model of the brain (called “Spaun”) is presented that bridges the gap between neural activity and biological function by exhibiting many different behaviors and is presented only with visual image sequences.