CMOS and Memristor-Based Neural Network Design for Position Detection

Ebong, Idongesit E.; Mazumder, Pinaki

doi:10.1109/jproc.2011.2173089

Cited by 162 publications

(49 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Designs that rely on expensive weight storage circuits, such as capacitor circuits, suffer from large area overheads leading to poor scalability [3]. In the rest of this section, we discuss the design of hardware synapse circuits for a new generation of HNNs based on the integration of CMOS technology with nanoscale memristive devices (CMHNNs).…”

Section: Cmos/memristor Synapse Circuitsmentioning

confidence: 99%

“…This is especially true for networks of spiking neurons that implement spike timedependent plasticity (STDP)-based Hebbian/anti-Hebbian learning. Networks of analog spiking neurons with single-memristor synapses are presented in PerezCarrasco et al [13], Afifi et al [10], and a digital implementation is proposed in Ebong and Mazumder [3]. However, these implementations require neurons to output three different voltage levels, complicating the hardware neuron design.…”

Section: Synapse Circuitsmentioning

confidence: 99%

See 1 more Smart Citation

Design of Neuromorphic Architectures with Memristors

Kudithipudi

Merkel

Soltiz

et al. 2013

Advances in Information Security

View full text Add to dashboard Cite

Section: Cmos/memristor Synapse Circuitsmentioning

confidence: 99%

Section: Synapse Circuitsmentioning

confidence: 99%

Design of Neuromorphic Architectures with Memristors

Kudithipudi

Merkel

Soltiz

et al. 2013

Advances in Information Security

View full text Add to dashboard Cite

“…Squaring circuits represent the core for implementing any continuous function, using the limited Taylor series expansion. The Euclidean distance function is very important in instrumentation circuits [11,12], communication [1,2], neural networks [13,14], display systems [15,16], or classification algorithms [17], being also useful for vector quantization or nearest neighbor classification [18,19].…”

Section: Introductionmentioning

confidence: 99%

High-accuracy function synthesizer circuit with applications in signal processing

Popa

2012

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

An original low-voltage current-mode high-accuracy function synthesizer circuit will be presented, allowing to implement a multitude of continuous mathematical functions. The dynamic range is strongly extended as a result of the superior-order approximation of the implemented functions. The current-mode operation and the independence of the circuit performances on technological parameters are responsible for an additional improvement of structure accuracy. The advantages of reduced design costs per function represent an immediate consequence of the multiple functions realized by the proposed structure. The approximation error of the original function synthesizer circuit is 0.3% for an extended range of the input signal. The function synthesizer is designed for implementing in 0.18 μm CMOS technology and it is supplied at 1 V. An original application of the proposed function synthesizer circuit is represented by a new fourth-order approximation exponential function generator, having a dynamic range of approximately 33 dB, for an error smaller than 1 dB.

show abstract

“…The variable resistance will permit the memristor to learn new synapse weights, while the state abilities will enable the system to remember what it has learned. The concept of using memristors as synapse was first proposed by Snider [8] and have been studied by many researchers since then [9]- [17].…”

Section: Introductionmentioning

confidence: 99%

Spike timing dependent plasticity with memristive synapse in neuromorphic systems

Chan

Lohn

2012

The 2012 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

A methodology to realize spike-timing dependent plasticity and Hebbian learning in a neural network through the usage of memristive synapses is presented. Memristors act as a modulating synapse interconnection between neurons; plasticity is accomplished through adjusting the memristance via current spikes based on the relative timings of pre-synaptic and postsynaptic neuron spikes. The learning plasticity presented is continuous, asynchronous and deterministic. A CMOS implementation is presented along with SPICE simulations validating the methodology and design.

show abstract

CMOS and Memristor-Based Neural Network Design for Position Detection

Cited by 162 publications

References 27 publications

Design of Neuromorphic Architectures with Memristors

Design of Neuromorphic Architectures with Memristors

High-accuracy function synthesizer circuit with applications in signal processing

Spike timing dependent plasticity with memristive synapse in neuromorphic systems

Contact Info

Product

Resources

About