Pulse-stream VLSI neural networks mixing analog and digital techniques

Murray, Alan F.; Corso, D. Del; Tarassenko, Lionel

doi:10.1109/72.80329

Cited by 173 publications

(55 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While these early physical devices are analog by design, analog computation also dominates neuromorphic integrated circuits. For the case of artificial neural networks, it is pointed out by Murray, Del Corso and Tarassenko (1991) that this is mainly due to the fact that the arithmetic operations required to compute a neuron's state can be implemented much more efficiently using analog units. The inferior accuracy compared to digital logic is compensated by the fault-tolerant information processing of neural systems.…”

Section: Early Neuromorphic Chip Designsmentioning

confidence: 99%

“…With the spike-based communication of biological neurons in mind, Murray and Smith (1987) therefore proposed hybrid neuromorphic systems which transmit signals digitally as series of pulses while the neural computations are still carried out by analog circuitry. This pulse-stream architecture not only solves the problems caused by analog signal transmission but also enables the creation of larger networks by multiplexing several streams of pulses over a common wire (Murray et al, 1991). An extensive review of early hardware designs for the execution of artificial neural networks is available in Heemskerk (1995).…”

Section: Early Neuromorphic Chip Designsmentioning

confidence: 99%

“…Every microprocessor architecture must address two central questions (Murray et al, 1991): How are computations performed and by which means of communication is involved data exchanged? Standard Von Neumann CPUs use registers and RAM to store and exchange data.…”

Section: Neuromorphic Devices-an Overviewmentioning

confidence: 99%

See 2 more Smart Citations

Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks

2015

View full text Add to dashboard Cite

a b s t r a c tThe application of biologically inspired methods in design and control has a long tradition in robotics. Unlike previous approaches in this direction, the emerging field of neurorobotics not only mimics biological mechanisms at a relatively high level of abstraction but employs highly realistic simulations of actual biological nervous systems. Even today, carrying out these simulations efficiently at appropriate timescales is challenging. Neuromorphic chip designs specially tailored to this task therefore offer an interesting perspective for neurorobotics. Unlike Von Neumann CPUs, these chips cannot be simply programmed with a standard programming language. Like real brains, their functionality is determined by the structure of neural connectivity and synaptic efficacies. Enabling higher cognitive functions for neurorobotics consequently requires the application of neurobiological learning algorithms to adjust synaptic weights in a biologically plausible way. In this paper, we therefore investigate how to program neuromorphic chips by means of learning. First, we provide an overview over selected neuromorphic chip designs and analyze them in terms of neural computation, communication systems and software infrastructure. On the theoretical side, we review neurobiological learning techniques. Based on this overview, we then examine on-die implementations of these learning algorithms on the considered neuromorphic chips. A final discussion puts the findings of this work into context and highlights how neuromorphic hardware can potentially advance the field of autonomous robot systems. The paper thus gives an in-depth overview of neuromorphic implementations of basic mechanisms of synaptic plasticity which are required to realize advanced cognitive capabilities with spiking neural networks.

show abstract

Section: Early Neuromorphic Chip Designsmentioning

confidence: 99%

Section: Early Neuromorphic Chip Designsmentioning

confidence: 99%

See 1 more Smart Citation

Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks

2015

View full text Add to dashboard Cite

show abstract

“…Pulse-stream encoding technique [7]- [22] uses pulse streams to carry information and control analog circuitry, while storing further analog information on the time axis. This approach lends itself naturally to continuous computation, as in the conceptually simple but theoretically rich feedback networks introduced by Hopfield [23].…”

mentioning

confidence: 99%

Analog implementation of pulse-coupled neural networks

Ota¹,

Wilamowski²

1999

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-This paper presents a compact architecture for analog CMOS hardware implementation of voltage-mode pulsecoupled neural networks (PCNN's). The hardware implementation methods shows inherent fault tolerance specialties and high speed, which is usually more than an order of magnitude over the software counterpart. A computational style described in this article mimics a biological neural network using pulse-stream signaling and analog summation and multiplication. Pulse-stream encoding technique uses pulse streams to carry information and control analog circuitry, while storing further analog information on the time axis. The main feature of the proposed neuron circuit is that the structure is compact, yet exhibiting all the basic properties of natural biological neurons. Functional and structural forms of neural and synaptic functions are presented along with simulation results. Finally, the proposed design is applied to image processing to demonstrate successful restoration of images and their features.

show abstract

“…The leaky integrator is a key subsystem in pulse-mode artificial neuron implementations [1]. In most implementations reported to date this function has been implemented with the explicit use of integrated capacitors and with fixed time constants.…”

Section: Introductionmentioning

confidence: 99%