scholarly journals Unsupervised Character Recognition with Graphene Memristive Synapses

2022 ◽  
Author(s):  
Ben Walters ◽  
Corey Lammie ◽  
Shuangming Yang ◽  
Mohan Jacob ◽  
Mostafa Rahimi Azghadi
Keyword(s):  
Single Layer ◽  
Spike Timing ◽  
Homeostatic Plasticity ◽  
Reproducible Research ◽  
Future Research ◽  
Neuromorphic Computing ◽  
Single Digit ◽  
Pixel Resolution ◽  
Efficient Manner ◽  
Output Neurons

Memristive devices being applied in neuromorphic computing are envisioned to significantly improve the power consumption and speed of future computing platforms. The materials used to fabricate such devices will play a significant role in their viability. Graphene is a promising material, with superb electrical properties and the ability to be produced sustainably. In this paper, we demonstrate that a fabricated graphene-pentacene memristive device can be used as synapses within Spiking Neural Networks (SNNs) to realise Spike Timing Dependent Plasticity (STDP) for unsupervised learning in an efficient manner. Specifically, we verify operation of two SNN architectures tasked for single digit (0-9) classification: (i) a simple single-layer network, where inputs are presented in 5x5 pixel resolution, and (ii) a larger network capable of classifying the Modified National Institute of Standards and Technology (MNIST) dataset, where inputs are presented in 28x28 pixel resolution. Final results demonstrate that for 100 output neurons, after one training epoch, a test set accuracy of up to 86% can be achieved, which is higher than prior art using the same number of output neurons. We attribute this performance improvement to homeostatic plasticity dynamics that we used to alter the threshold of neurons during training. Our work presents the first investigation of the use of green-fabricated graphene memristive devices to perform a complex pattern classification task. This can pave the way for future research in using graphene devices with memristive capabilities in neuromorphic computing architectures. In favour of reproducible research, we make our code and data publicly available https://anonymous.4open.science/r/c69ab2e2-b672-4ebd-b266-987ee1fd65e7.

Design of a Robust Memristive Spiking Neuromorphic System with Unsupervised Learning in Hardware

2021 ◽  
Vol 17 (4) ◽  
pp. 1-26
Author(s):  
Md Musabbir Adnan ◽  
Sagarvarma Sayyaparaju ◽  
Samuel D. Brown ◽  
Mst Shamim Ara Shawkat ◽  
Catherine D. Schuman ◽  
...  
Keyword(s):  
Unsupervised Learning ◽  
Recognition Task ◽  
Single Layer ◽  
Process Variations ◽  
Spike Timing ◽  
System Level ◽  
Design Parameters ◽  
Digital Pulse ◽  
Neuromorphic System ◽  
The Impact

Spiking neural networks (SNN) offer a power efficient, biologically plausible learning paradigm by encoding information into spikes. The discovery of the memristor has accelerated the progress of spiking neuromorphic systems, as the intrinsic plasticity of the device makes it an ideal candidate to mimic a biological synapse. Despite providing a nanoscale form factor, non-volatility, and low-power operation, memristors suffer from device-level non-idealities, which impact system-level performance. To address these issues, this article presents a memristive crossbar-based neuromorphic system using unsupervised learning with twin-memristor synapses, fully digital pulse width modulated spike-timing-dependent plasticity, and homeostasis neurons. The implemented single-layer SNN was applied to a pattern-recognition task of classifying handwritten-digits. The performance of the system was analyzed by varying design parameters such as number of training epochs, neurons, and capacitors. Furthermore, the impact of memristor device non-idealities, such as device-switching mismatch, aging, failure, and process variations, were investigated and the resilience of the proposed system was demonstrated.

Reliable analog resistive switching behaviors achieved using memristive devices in AlOx/HfOx bilayer structure for neuromorphic systems

2021 ◽  
Author(s):  
Meng Qi ◽  
Tianquan Fu ◽  
Huadong Yang ◽  
ye tao ◽  
Chunran Li ◽  
...  
Keyword(s):  
Resistive Switching ◽  
Learning Experience ◽  
Random Access ◽  
Resistive Random Access Memory ◽  
Spike Timing ◽  
Information Storage ◽  
Bilayer Structure ◽  
Neuromorphic Computing ◽  
Von Neumann ◽  
Simulation Based

Abstract Human brain synaptic memory simulation based on resistive random access memory (RRAM) has an enormous potential to replace traditional Von Neumann digital computer thanks to several advantages, including its simple structure, high-density integration, and the capability to information storage and neuromorphic computing. Herein, the reliable resistive switching (RS) behaviors of RRAM are demonstrated by engineering AlOx/HfOx bilayer structure. This allows for uniform multibit information storage. Further, the analog switching behaviors are capable of imitate several synaptic learning functions, including learning experience behaviors, short-term plasticity-long-term plasticity transition, and spike-timing-dependent-plasticity (STDP). In addition, the memristor based on STDP learning rules are implemented in image pattern recognition. These results may offer a promising potential of HfOx-based memristors for future information storage and neuromorphic computing applications.

Service-Oriented Architectures for Pervasive Computing

2010 ◽  
pp. 147-174 ◽  
Author(s):  
Elias S. Manolakos ◽  
Demetris G. Galatopoullos
Keyword(s):  
Pervasive Computing ◽  
Service Oriented Architecture ◽  
Future Research ◽  
Open Problems ◽  
Efficient Manner ◽  
Service Oriented Architectures ◽  
Software Applications ◽  
Service Oriented ◽  
User Tasks ◽  
The Many

The vision of pervasive computing is to create and manage computational spaces where large numbers of heterogeneous devices collaborate transparently to serve the user tasks all the time, anywhere. The original utility of a computer is now changing from a stand-alone tool that runs software applications to an environment-aware, context-aware tool that can enhance the user experience by executing services and carrying out his/her tasks in an efficient manner. However, the heterogeneity of devices and the user’s mobility are among the many issues that make developing pervasive computing applications a very challenging task. A solution to the programmability of pervasive spaces is adopting the service-oriented architecture (SOA) paradigm. In the SOA model, device capabilities are exposed as software services thus providing the programmer with a convenient abstraction level that can help to deal with the dynamicity of pervasive spaces. In this chapter the authors review the state of the art in SOA-based pervasive computing, identify existing open problems, and contribute ideas for future research.

scholarly journals Memristive Spiking Neural Networks Trained with Unsupervised STDP

Electronics ◽  
2018 ◽  
Vol 7 (12) ◽  
pp. 396 ◽  
Author(s):  
Errui Zhou ◽  
Liang Fang ◽  
Binbin Yang
Keyword(s):  
Neural Networks ◽  
Feature Learning ◽  
Spike Timing ◽  
Spiking Neural Networks ◽  
Learning Method ◽  
Hardware Complexity ◽  
Neuromorphic Computing ◽  
Computing Systems ◽  
Von Neumann ◽  
Complex Architectures

Neuromorphic computing systems are promising alternatives in the fields of pattern recognition, image processing, etc. especially when conventional von Neumann architectures face several bottlenecks. Memristors play vital roles in neuromorphic computing systems and are usually used as synaptic devices. Memristive spiking neural networks (MSNNs) are considered to be more efficient and biologically plausible than other systems due to their spike-based working mechanism. In contrast to previous SNNs with complex architectures, we propose a hardware-friendly architecture and an unsupervised spike-timing dependent plasticity (STDP) learning method for MSNNs in this paper. The architecture, which is friendly to hardware implementation, includes an input layer, a feature learning layer and a voting circuit. To reduce hardware complexity, some constraints are enforced: the proposed architecture has no lateral inhibition and is purely feedforward; it uses the voting circuit as a classifier and does not use additional classifiers; all neurons can generate at most one spike and do not need to consider firing rates and refractory periods; all neurons have the same fixed threshold voltage for classification. The presented unsupervised STDP learning method is time-dependent and uses no homeostatic mechanism. The MNIST dataset is used to demonstrate our proposed architecture and learning method. Simulation results show that our proposed architecture with the learning method achieves a classification accuracy of 94.6%, which outperforms other unsupervised SNNs that use time-based encoding schemes.

scholarly journals Reinforcement Learning With Modulated Spike Timing–Dependent Synaptic Plasticity

2007 ◽  
Vol 98 (6) ◽  
pp. 3648-3665 ◽  
Author(s):  
Michael A. Farries ◽  
Adrienne L. Fairhall
Keyword(s):  
Synaptic Plasticity ◽  
Reinforcement Learning ◽  
General Purpose ◽  
Spike Timing ◽  
Neural Population ◽  
Minimal Set ◽  
Population Responses ◽  
Wide Range ◽  
Output Neurons ◽  
Novel Model

Spike timing–dependent synaptic plasticity (STDP) has emerged as the preferred framework linking patterns of pre- and postsynaptic activity to changes in synaptic strength. Although synaptic plasticity is widely believed to be a major component of learning, it is unclear how STDP itself could serve as a mechanism for general purpose learning. On the other hand, algorithms for reinforcement learning work on a wide variety of problems, but lack an experimentally established neural implementation. Here, we combine these paradigms in a novel model in which a modified version of STDP achieves reinforcement learning. We build this model in stages, identifying a minimal set of conditions needed to make it work. Using a performance-modulated modification of STDP in a two-layer feedforward network, we can train output neurons to generate arbitrarily selected spike trains or population responses. Furthermore, a given network can learn distinct responses to several different input patterns. We also describe in detail how this model might be implemented biologically. Thus our model offers a novel and biologically plausible implementation of reinforcement learning that is capable of training a neural population to produce a very wide range of possible mappings between synaptic input and spiking output.

TAG: A Neural Network Model for Large-Scale Optical Implementation

1991 ◽  
Vol 3 (1) ◽  
pp. 135-143 ◽  
Author(s):  
Hyuek-Jae Lee ◽  
Soo-Young Lee ◽  
Sang-Yung Shin ◽  
Bo-Yun Koh
Keyword(s):  
Neural Networks ◽  
Adaptive Learning ◽  
Large Scale ◽  
Learning Algorithm ◽  
Single Layer ◽  
Spatial Light Modulators ◽  
Light Modulators ◽  
Different Types ◽  
Multilayer Architecture ◽  
Output Neurons

TAG (Training by Adaptive Gain) is a new adaptive learning algorithm developed for optical implementation of large-scale artificial neural networks. For fully interconnected single-layer neural networks with N input and M output neurons TAG contains two different types of interconnections, i.e., M N global fixed interconnections and N + M adaptive gain controls. For two-dimensional input patterns the former may be achieved by multifacet holograms, and the latter by spatial light modulators (SLMs). For the same number of input and output neurons TAG requires much less adaptive elements, and provides a possibility for large-scale optical implementation at some sacrifice in performance as compared to the perceptron. The training algorithm is based on gradient descent and error backpropagation, and is easily extensible to multilayer architecture. Computer simulation demonstrates reasonable performance of TAG compared to perceptron performance. An electrooptical implementation of TAG is also proposed.

scholarly journals Where’s the noise? Key features of neuronal variability and inference emerge from self-organized learning

2014 ◽  
Author(s):  
Christoph Hartmann ◽  
Andreea Lazar ◽  
Jochen Triesch
Keyword(s):  
Spontaneous Activity ◽  
Network Model ◽  
Neural Circuit ◽  
Intrinsic Noise ◽  
Spike Timing ◽  
Homeostatic Plasticity ◽  
Neural Recordings ◽  
Self Organized ◽  
Key Features ◽  
Neural Variability

AbstractTrial-to-trial variability and spontaneous activity of cortical recordings have been suggested to reflect intrinsic noise. This view is currently challenged by mounting evidence for structure in these phenomena: Trial-to-trial variability decreases following stimulus onset and can be predicted by previous spontaneous activity. This spontaneous activity is similar in magnitude and structure to evoked activity and can predict decisions. Allof the observed neuronal properties described above can be accounted for, at an abstract computational level, by the sampling-hypothesis, according to which response variability reflects stimulus uncertainty. However, a mechanistic explanation at the level of neural circuit dynamics is still missing.In this study, we demonstrate that all of these phenomena can be accounted for by a noise-free self-organizing recurrent neural network model (SORN). It combines spike-timing dependent plasticity (STDP) and homeostatic mechanisms in a deterministic network of excitatory and inhibitory McCulloch-Pitts neurons. The network self-organizes to spatio-temporally varying input sequences.We find that the key properties of neural variability mentioned above develop in this model as the network learns to perform sampling-like inference. Importantly, the model shows high trial-to-trial variability although it is fully deterministic. This suggests that the trial-to-trial variability in neural recordings may not reflect intrinsic noise. Rather, it may reflect a deterministic approximation of sampling-like learning and inference. The simplicity of the model suggests that these correlates of the sampling theory are canonical properties of recurrent networks that learn with a combination of STDP and homeostatic plasticity mechanisms.Author SummaryNeural recordings seem very noisy. If the exact same stimulus is shown to an animal multiple times, the neural response will vary. In fact, the activity of a single neuron shows many features of a stochastic process. Furthermore, in the absence of a sensory stimulus, cortical spontaneous activity has a magnitude comparable to the activity observed during stimulus presentation. These findings have led to a widespread belief that neural activity is indeed very noisy. However, recent evidence indicates that individual neurons can operate very reliably and that the spontaneous activity in the brain is highly structured, suggesting that much of the noise may in fact be signal. One hypothesis regarding this putative signal is that it reflects a form of probabilistic inference through sampling. Here we show that the key features of neural variability can be accounted for in a completely deterministic network model through self-organization. As the network learns a model of its sensory inputs, the deterministic dynamics give rise to sampling-like inference. Our findings show that the notorious variability in neural recordings does not need to be seen as evidence for a noisy brain. Instead it may reflect sampling-like inference emerging from a self-organized learning process.

Sustainable what…? The role of corporate websites in communicating material innovations in the luxury fashion industry

2021 ◽  
Vol 7 (1) ◽  
pp. 83-103 ◽  
Author(s):  
Shuchan Luo ◽  
Claudia E. Henninger ◽  
Aurelie Le Normand ◽  
Marta Blazquez
Keyword(s):  
Qualitative Content Analysis ◽  
Past Research ◽  
Analysis Data ◽  
Future Research ◽  
Fashion Industry ◽  
Luxury Brands ◽  
Efficient Manner ◽  
Corporate Websites ◽  
Information Accessibility

COVID-19 has heightened consumers environmental and social consciousness in the luxury industry, which fosters luxury consumers’ appetite for sustainable luxury, thus, puts renewed interest and pressure on the industry to act upon. Past research highlights that sustainability and luxury may be paradoxical, due to a lack of information on material adoption. Yet, sustainable luxury products are positively perceived by consumers, who see luxury and sustainability as compatible. Material innovations can enhance this perception further, which requires careful communication strategies. Sustainability communication enables companies to broadcast material innovations through a manifold channel. Luxury brands predominantly communicate these innovations through official websites, as it is often the first touchpoint between consumers and the brand. This article addresses a knowledge gap on how to communicate sustainable luxury in an effective and efficient manner, by focusing on material innovations that are increasing in popularity in the sector. This article explores the role of corporate websites in communicating material innovations based on two luxury brands. Data are extracted from company websites to perform a qualitative content analysis. Data highlight that terminologies used affect information accessibility. Sustainable information can be a key selling point for consumers that are more environmentally, thus it is vital to provide this information in a straightforward manner. Data may not be generalized from only two case studies, yet it provides insights that can guide future research.

Materials Strategies for Organic Neuromorphic Devices

2021 ◽  
Vol 51 (1) ◽  
Author(s):  
Aristide Gumyusenge ◽  
Armantas Melianas ◽  
Scott T. Keene ◽  
Alberto Salleo
Keyword(s):  
Energy Efficiency ◽  
High Performance ◽  
Materials Science ◽  
High Energy ◽  
Information Storage ◽  
Oxide Semiconductor ◽  
Future Research ◽  
Annual Review ◽  
Publication Date ◽  
Neuromorphic Computing

Neuromorphic computing is becoming increasingly prominent as artificial intelligence (AI) facilitates progressively seamless interaction between humans and machines. The conventional von Neumann architecture and complementary metal-oxide semiconductor transistor scaling are unable to meet the highly demanding computational density and energy efficiency requirements of AI. Neuromorphic computing aims to address these challenges by using brain-like computing architectures and novel synaptic memories that coallocate information storage and computation, thereby enabling low latency at high energy efficiency and high memory density. Though various emerging memory devices have been extensively studied to emulate the functionality of biological synapses, there is currently no material/device system that encompasses both the needed metrics for high-performance neuromorphic computing and the required biocompatibility for potential body-computer integration. In this review, we aim to equip the reader with general design principles and materials requirements for realizing high-performance organic neuromorphic devices. We use instructive examples from recent literature to discuss each requirement, illustrating the challenges as well as future research opportunities. Though organic devices still face many challenges to become major players in neuromorphic computing, mostly due to their lack of compliance with back-end-of-the-line processes required for integration with digital logic, we propose that their biocompatibility and mechanical conformability give them an advantage for creating adaptive biointerfaces, brain-machine interfaces, and biology-inspired prosthetics. Expected final online publication date for the Annual Review of Materials Science, Volume 51 is July 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Sign in / Sign up

Export Citation Format

Share Document