Frontiers in Neuromorphic Engineering

Indiveri, Giacomo; Horiuchi, Timothy K.

doi:10.3389/fnins.2011.00118

Cited by 205 publications

(154 citation statements)

References 8 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…The alternative, neuromorphic, approach to information processing strives to capture in complementary metal-oxide semiconductor (CMOS) very large-scale integration (VLSI) electronic technology the more distributed, asynchronous, and limited precision nature of biological intelligent systems (1,4).…”

mentioning

confidence: 99%

Synthesizing cognition in neuromorphic electronic systems

Neftci

Binas

Rutishauser

et al. 2013

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

127

122

View full text Add to dashboard Cite

The quest to implement intelligent processing in electronic neuromorphic systems lacks methods for achieving reliable behavioral dynamics on substrates of inherently imprecise and noisy neurons. Here we report a solution to this problem that involves first mapping an unreliable hardware layer of spiking silicon neurons into an abstract computational layer composed of generic reliable subnetworks of model neurons and then composing the target behavioral dynamics as a "soft state machine" running on these reliable subnets. In the first step, the neural networks of the abstract layer are realized on the hardware substrate by mapping the neuron circuit bias voltages to the model parameters. This mapping is obtained by an automatic method in which the electronic circuit biases are calibrated against the model parameters by a series of population activity measurements. The abstract computational layer is formed by configuring neural networks as generic soft winner-take-all subnetworks that provide reliable processing by virtue of their active gain, signal restoration, and multistability. The necessary states and transitions of the desired high-level behavior are then easily embedded in the computational layer by introducing only sparse connections between some neurons of the various subnets. We demonstrate this synthesis method for a neuromorphic sensory agent that performs real-time context-dependent classification of motion patterns observed by a silicon retina.decision making | sensorimotor | working memory | analog very large-scale integration | artificial neural systems U nlike digital simulations, in which the dynamics of neuronal models are encoded and calculated on general purpose digital hardware, "neuromorphic" emulations express the dynamics of the neural systems directly on an analogous physical substrate (1). Digital simulations have the advantage that they can be exactly and reliably programmed using numerical operations of very high precision. However, they suffer the disadvantage that they are cast on abstract binary electronic circuits whose operation is entirely divorced from the physical processes being simulated. Consequently, such simulations do not readily advance our understanding of how biological neural systems are able to attain their extraordinary physical performance, using only large numbers of apparently unreliable, slow, and imprecise neural components, a problem first recognized by von Neumann more than a half century ago (2). Furthermore, the reliability of digital systems comes at high cost of the circuit complexity necessary for the orchestration of communication and processing, an overhead that declares itself also in the costs of system construction and power dissipation (3).The alternative, neuromorphic, approach to information processing strives to capture in complementary metal-oxide semiconductor (CMOS) very large-scale integration (VLSI) electronic technology the more distributed, asynchronous, and limited precision nature of biological intelligent systems (1, 4).†, ‡ Research...

show abstract

mentioning

confidence: 99%

Synthesizing cognition in neuromorphic electronic systems

Neftci

Binas

Rutishauser

et al. 2013

Proc. Natl. Acad. Sci. U.S.A.

Self Cite

127

122

View full text Add to dashboard Cite

show abstract

“…One way is to combine the local learning of synaptic weights with global optimisation of SNN parameters. Three approaches can be investigated: evolutionary computation methods [18]; gene regulatory network (GRN) model [19], [20]; using both together. Neurogenetic models are promising for cognitive robotic systems and for the prognosis of neurodegenerative diseases such as Alzheimers disease [19] especially when probabilistic neuronal models are employed [21].…”

Section: Discussionmentioning

confidence: 99%

Online spatio-temporal pattern recognition with evolving spiking neural networks utilising address event representation, rank order, and temporal spike learning

Dhoble

Nuntalid

Indiveri

et al. 2012

The 2012 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Evolving spiking neural networks (eSNN) are computational models that evolve new spiking neurons and new connections from incoming data to learn patterns from them in an on-line mode. With the development of new techniques to capture spatio-and spectro-temporal data in a fast on-line mode, using for example address event representation (AER) such as the implemented one in the artificial retina and the artificial cochlea chips, and with the available SNN hardware technologies, new and more efficient methods for spatio-temporal pattern recognition (STPR) are needed. The paper introduces a new eSNN model dynamic eSNN (deSNN), that utilises both rank-order spike coding (ROSC), also known as time to first spike, and temporal spike coding (TSC). Each of these representations are implemented through different learning mechanisms -RO learning, and temporal spike learning -spike driven synaptic plasticity (SDSP) rule. The deSNN model is demonstrated on a small scale moving object classification problem when AER data is collected with the use of an artificial retina camera. The new model is superior in terms of learning time and accuracy for learning. It makes use of the order of spikes input information which is explicitly present in the AER data, while a temporal spike learning rule accounts for any consecutive spikes arriving on the same synapse that represent temporal components in the learned spatio-temporal pattern. Abstract-Evolving spiking neural networks (eSNN) are computational models that evolve new spiking neurons and new connections from incoming data to learn patterns from them in an on-line mode. With the development of new techniques to capture spatio-and spectro-temporal data in a fast on-line mode, using for example address event representation (AER) such as the implemented one in the artificial retina and the artificial cochlea chips, and with the available SNN hardware technologies, new and more efficient methods for spatio-temporal pattern recognition (STPR) are needed. The paper introduces a new eSNN model dynamic eSNN (deSNN), that utilises both rankorder spike coding (ROSC), also known as time to first spike, and temporal spike coding (TSC). Each of these representations are implemented through different learning mechanisms -RO learning, and temporal spike learning -spike driven synaptic plasticity (SDSP) rule. The deSNN model is demonstrated on a small scale moving object classification problem when AER data is collected with the use of an artificial retina camera. The new model is superior in terms of learning time and accuracy for learning. It makes use of the order of spikes input information which is explicitly present in the AER data, while a temporal spike learning rule accounts for any consecutive spikes arriving on the same synapse that represent temporal components in the learned spatio-temporal pattern.

show abstract

“…An increasing number of neuroscientists, computer scientists and engineers are now converging their efforts in designing VLSI "neuromorphic" devices and systems (Mead, 1989;Indiveri & Horiuchi, 2011). In particular, a large subset of the neuromorphic engineering field focusses on the emulation of the properties of biological neurons in VLSI circuits (Mead, 1989;Mahowald & Douglas, 1991;.…”

Section: Application To Neuromorphic Systemsmentioning

confidence: 99%

Dynamic State and Parameter Estimation Applied to Neuromorphic Systems

2012

Self Cite

View full text Add to dashboard Cite

Neuroscientists often propose detailed computational models to probe the properties of their studied neural systems. With the advent of neuromorphic engineering, there * emre@ini.phys.ethz.ch † btoth@physics.ucsd.edu 1 is an increasing number of hardware electronic analogs of biological neural systems being proposed as well. However, for both biological and hardware systems, it is often difficult to estimate the parameters of the model such that they are meaningful to the studied experimental system, especially when these models involve a large number of states and parameters which cannot be simultaneously measured. We have developed a procedure to solve this problem in the context of interacting neural populations using a recently developed Dynamic State and Parameter Estimation (DSPE) technique.This technique uses synchronization as a tool for dynamically coupling experimentally measured data to its corresponding model to determine its parameters and internal state variables. While in its conventional use, the experimental data is obtained from the biological neural system, and the model is simulated in software, here we show that this technique is also efficient in validating proposed network models for neuromorphic spike-based Very Large Scale Integration (VLSI) chips, and that it is able to systematically extract network parameters such as synaptic weights, time constants and other variables which are not accessible by direct observation. Our results suggest that this method can become a very useful tool for model-based identification and configuration of neuromorphic multi-chip VLSI systems.

show abstract

Frontiers in Neuromorphic Engineering

Cited by 205 publications

References 8 publications

Synthesizing cognition in neuromorphic electronic systems

Synthesizing cognition in neuromorphic electronic systems

Online spatio-temporal pattern recognition with evolving spiking neural networks utilising address event representation, rank order, and temporal spike learning

Dynamic State and Parameter Estimation Applied to Neuromorphic Systems

Contact Info

Product

Resources

About