Racing to learn: statistical inference and learning in a single spiking neuron with adaptive kernels

  title={Racing to learn: statistical inference and learning in a single spiking neuron with adaptive kernels},
  author={Saeed Afshar and Libin George and Jonathan C. Tapson and Andr{\'e} van Schaik and Tara Julia Hamilton},
  journal={Frontiers in Neuroscience},
This paper describes the Synapto-dendritic Kernel Adapting Neuron (SKAN), a simple spiking neuron model that performs statistical inference and unsupervised learning of spatiotemporal spike patterns. SKAN is the first proposed neuron model to investigate the effects of dynamic synapto-dendritic kernels and demonstrate their computational power even at the single neuron scale. The rule-set defining the neuron is simple: there are no complex mathematical operations such as normalization… 

Turn Down That Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron

The resulting neuron model is the first to perform synaptic encoding of afferent signal-to-noise ratio in addition to the unsupervised learning of spatio-temporal spike patterns, and may also offer insights into biological systems.

CONE: Convex-Optimized-Synaptic Efficacies for Temporally Precise Spike Mapping

This paper presents a novel technique to obtain the weights of spiking neurons by formulating the problem in a convex optimization framework, and shows how the existence of a solution can be determined and assess memory capacity limits of a neuron model using synthetic examples.

Emergence of Optimal Decoding of Population Codes Through STDP

This theory identifies a class of optimal STDP learning rules with homeostatic plasticity, for which the autonomous emergence of optimal readouts can be explained on the basis of a rigorous learning theory, and finds that this optimal functionality can be well approximated by a variety of STDP rules beyond those predicted by theory.

Event-Based Computation for Touch Localization Based on Precise Spike Timing

This work proposes a neuromorphic model inspired by the sand scorpion to explore the benefits of temporal coding, and argues that the models presented are optimal for spatio-temporal pattern classification using precise spike timing in a task that could be used as a standard benchmark for evaluating event-based sensory processing models based on temporal coding.

Robotic implementation of classical and operant conditioning within a single SNN architecture

This work presents the implementation of operant conditioning (OC) and classical conditioning (CC) with a single spiking neural network (SNN) architecture, thus suggesting that the two types of

Robotic implementation of classical and Operant Conditioning as a single STDP learning process

An architecture with an important potential for very large scale time-dependent parallel data analysis, with high capacity of adaptation in a dynamic environment is validates.

Approximate, Computationally Efficient Online Learning in Bayesian Spiking Neurons

An online learning algorithm is presented that is more computationally efficient than the benchmark ML-EM for a fixed number of time steps as the number of inputs to a BSN increases, and gives very good average estimation accuracy, despite its approximate nature.

Single SNN Architecture for Classical and Operant Conditioning using Reinforcement Learning

This work contributes to the engineering field by proposing a scalable low resource demanding architecture for adaptive systems, and the cognitive field by suggesting that both CC and OC can be modeled as a single cognitive architecture.

FPGA minimal components SKAN model for classical and operant conditioning

The modified CC architecture, new OC architecture, adapted SKAN model and new STDP-inspired process represent the four contributions presented here, along with simulation results on a FPGA which shows their adequacy in supporting CC and OC learning behaviors.

Event-Based Feature Extraction Using Adaptive Selection Thresholds

A novel event-based feature extraction method which operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds.



Real-Time Classification of Complex Patterns Using Spike-Based Learning in Neuromorphic VLSI

Experimental data is presented that demonstrate how the VLSI neural network can learn to classify patterns of neural activities, also in the case in which they are highly correlated.

Competitive STDP-Based Spike Pattern Learning

These results illustrate how the brain could easily encode and decode information in the spike times, a theory referred to as temporal coding, and how STDP could play a key role by detecting repeating patterns and generating selective response to them.

Predictive Coding of Dynamical Variables in Balanced Spiking Networks

The approach suggests that spikes do matter when considering how the brain computes, and that the reliability of cortical representations could have been strongly underestimated.

Noise as a Resource for Computation and Learning in Networks of Spiking Neurons

  • W. Maass
  • Computer Science
    Proceedings of the IEEE
  • 2014
Why recent theoretical results are paving the way for a qualitative jump in the computational capability and learning performance of neuromorphic networks of spiking neurons with noise are described, and for other future computing systems that are able to treat noise as a resource are described.

The Synaptic Kernel Adaptation Network

The SKAN circuit is a dynamic circuit that implements Spike Timing Dependent Plasticity (STDP), not by adjusting synaptic weights but via dynamic synaptic kernels, and is fast, accurate and robust to noise and jitter.

Synaptic and nonsynaptic plasticity approximating probabilistic inference

The model provides a biophysical realization of Bayesian computation by reconciling several observed neural phenomena whose functional effects are only partially understood in concert, and support the view that neurons can represent information in the form of probability distributions.

Hebbian learning with winner take all for spiking neural networks

  • Ankur GuptaL. Long
  • Computer Science, Biology
    2009 International Joint Conference on Neural Networks
  • 2009
This work proposes and implements an efficient Hebbian learning method with homeostasis for a network of spiking neurons, similar to STDP, where timing between spikes is used for synaptic modification.

Bayesian Computation Emerges in Generic Cortical Microcircuits through Spike-Timing-Dependent Plasticity

The results suggest that the experimentally observed spontaneous activity and trial-to-trial variability of cortical neurons are essential features of their information processing capability, since their functional role is to represent probability distributions rather than static neural codes.

Spike-Based Synaptic Plasticity in Silicon: Design, Implementation, Application, and Challenges

The ability to carry out signal processing, classification, recognition, and computation in artificial spiking neural networks (SNNs) is mediated by their synapses. In particular, through