• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 31
  • 6
  • 3
  • 1
  • 1
  • Tagged with
  • 60
  • 60
  • 60
  • 18
  • 18
  • 16
  • 15
  • 14
  • 8
  • 8
  • 7
  • 7
  • 6
  • 6
  • 6
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
21

A framework for training Spiking Neural Networks using Evolutionary Algorithms and Deep Reinforcement Learning

Anirudh Shankar (10276349) 12 March 2021 (has links)
In this work two novel frameworks, one using evolutionary algorithms and another using Reinforcement Learning for training Spiking Neural Networks are proposed and analyzed. A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (SNN). The weights of a population of SNNs along with morphological parameters of bots they control in the ER environment are treated as phenotypes. Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment. While the bots and their SNNs are given no explicit reward to survive or reproduce via any loss function, these drives emerge implicitly as they evolve to hunt food and survive within these rules. Their efficiency in capturing food as a function of generations exhibit the evolutionary signature of punctuated equilibria. Two evolutionary inheritance algorithms on the phenotypes, Mutation and Crossover with Mutation along with their variants, are demonstrated. Performances of these algorithms are compared using ensembles of 100 experiments for each algorithm. We find that one of the Crossover with Mutation variants promotes 40% faster learning in the SNN than mere Mutation with a statistically significant margin. Along with an evolutionary approach to training SNNs, we also describe a novel Reinforcement Learning(RL) based framework using the Proximal Policy Optimization to train a SNN for an image classification task. The experiments and results of the framework are then discussed highlighting future direction of the work.
22

Adapting Neural Network Learning Algorithms for Neuromorphic Implementations

Jason M Allred (11197680) 29 July 2021 (has links)
<div>Computing with Artificial Neural Networks (ANNs) is a branch of machine learning that has seen substantial growth over the last decade, significantly increasing the accuracy and capability of machine learning systems. ANNs are connected networks of computing elements inspired by the neuronal connectivity in the brain. Spiking Neural Networks (SNNs) are a type of ANN that operate with event-driven computation, inspired by the “spikes” or firing events of individual neurons in the brain. Neuromorphic computing—the implementation of neural networks in hardware—seeks to improve the energy efficiency of these machine learning systems either by computing directly with device physical primitives, by bypassing the software layer of logical implementations, or by operating with SNN event-driven computation. Such implementations may, however, have added restrictions, including weight-localized learning and hard-wired connections. Further obstacles, such as catastrophic forgetting, the lack of supervised error signals, and storage and energy constraints, are encountered when these systems need to perform autonomous online, real-time learning in an unknown, changing environment. </div><div><br></div><div>Adapting neural network learning algorithms for these constraints can help address these issues. Specifically, corrections to Spike Timing-Dependent Plasticity (STDP) can stabilize local, unsupervised learning; accounting for the statistical firing properties of spiking neurons may improve conversions from non-spiking to spiking networks; biologically-inspired dopaminergic and habituation adjustments to STDP can limit catastrophic forgetting; convolving temporally instead of spatially can provide for localized weight sharing with direct synaptic connections; and explicitly training for spiking sparsity can significantly reduce computational energy consumption.</div>
23

Noise Robustness of CNN and SNN for EEG Motor imagery classification / Robusthet mot störning hos CNN och SNN vid klassificering av EEG motor imagery

Sewina, Merlin January 2023 (has links)
As an able-bodied human, understanding what someone says during a phone call with a lot of background noise is usually a task that is quite easy for us as we are aware of what the information is we want to hear, e.g. the voice of the person we are talking to, and the information that is noise, e.g. music or ambient noise in the background. While dealing with noise of all kinds for most humans proves to be the easiest, it is a very hard task for algorithms to deal with noisy data. Unfortunately for some beneficial and interesting applications, like Brain Computer Interfaces (short BCI) based on Electroencephalography (short EEG) data, noise is a very prevalent problem that greatly hinders the progress of making BCIs for real-life applications. In this thesis, we investigate what effect noise added to EEG data has on the classification accuracy of one Spiking Neural Network and one Convolutional Neural Network based classifier for a motor imagery classification task. The thesis shows that already relatively small amounts of noise (10% of original data) can have strong effects on the classification accuracy of the chosen classifiers. It also provides evidence that SNN based models have a more stable classification accuracy for low amounts of noise. Still, their classification accuracy after that declines more rapidly, while CNN based classifiers show a more linear decline in classification accuracy / Att förstå vad någon säger under ett telefonsamtal med mycket bakgrundsljud är en relativt enkel uppgift för en människa eftersom vi är duktiga på att urskilja vilken del av ljudet som är relevant, t.ex. rösten hos den vi pratar med, och vilken del av ljudet som är bakgrundsbrus, t.ex. musik eller omgivningsljud. Även om det är en enkel uppgift för en människa att filtrera bort olika sorters brus så är det betydligt svårare för en algoritm att hantera brusig data. Tyvärr finns det flertalet användbara och intressanta applikationsområden där svårigheten med brus orsakar betydande problem. Ett sådant exempel är braincomputer interfaces (BCI) baserade på elektroencefalografi (EEG) där brus är ett så pass utbrett problem att det begränsar möjligheten att använda BCI i verkliga tillämpningar. I detta examensarbete undersöks hur tillägget av brus till EEG-data påverkar noggrannheten på klassificeringen av hjärnaktivitet vid visualisering av olika rörelser. För detta ändamål jämfördes två typer av klassificerare: ett spiking neural network (SNN) och ett convolutional neural network (CNN). Examensarbetet visar att redan relativt små tillägg av brus (10%) kan ha stor påverkan på klassificeringens noggrannhet. Studien påvisar även att SNN-baserade modeller har en mer stabil noggrannhet för låga mängder brus, men att noggrannheten försämras snabbare vid ökad mängd brus än för CNN-baserade klassificerare som visar en mer linjär försämring.
24

Energy Efficient Deep Spiking Recurrent Neural Networks: A Reservoir Computing-Based Approach

Hamedani, Kian 18 June 2020 (has links)
Recurrent neural networks (RNNs) have been widely used for supervised pattern recognition and exploring the underlying spatio-temporal correlation. However, due to the vanishing/exploding gradient problem, training a fully connected RNN in many cases is very difficult or even impossible. The difficulties of training traditional RNNs, led us to reservoir computing (RC) which recently attracted a lot of attention due to its simple training methods and fixed weights at its recurrent layer. There are three different categories of RC systems, namely, echo state networks (ESNs), liquid state machines (LSMs), and delayed feedback reservoirs (DFRs). In this dissertation a novel structure of RNNs which is inspired by dynamic delayed feedback loops is introduced. In the reservoir (recurrent) layer of DFR, only one neuron is required which makes DFRs extremely suitable for hardware implementations. The main motivation of this dissertation is to introduce an energy efficient, and easy to train RNN while this model achieves high performances in different tasks compared to the state-of-the-art. To improve the energy efficiency of our model, we propose to adopt spiking neurons as the information processing unit of DFR. Spiking neural networks (SNNs) are the most biologically plausible and energy efficient class of artificial neural networks (ANNs). The traditional analog ANNs have marginal similarity with the brain-like information processing. It is clear that the biological neurons communicate together through spikes. Therefore, artificial SNNs have been introduced to mimic the biological neurons. On the other hand, the hardware implementation of SNNs have shown to be extremely energy efficient. Towards achieving this overarching goal, this dissertation presents a spiking DFR (SDFR) with novel encoding schemes, and defense mechanisms against adversarial attacks. To verify the effectiveness and performance of the SDFR, it is adopted in three different applications where there exists a significant Spatio-temporal correlations. These three applications are attack detection in smart grids, spectrum sensing of multi-input-multi-output(MIMO)-orthogonal frequency division multiplexing (OFDM) Dynamic Spectrum Sharing (DSS) systems, and video-based face recognition. In this dissertation, the performance of SDFR is first verified in cyber attack detection in Smart grids. Smart grids are a new generation of power grids which guarantee a more reliable and efficient transmission and delivery of power to the costumers. A more reliable and efficient power generation and distribution can be realized through the integration of internet, telecommunication, and energy technologies. The convergence of different technologies, brings up opportunities, but the challenges are also inevitable. One of the major challenges that pose threat to the smart grids is cyber-attacks. A novel method is developed to detect false data injection (FDI) attacks in smart grids. The second novel application of SDFR is the spectrum sensing of MIMO-OFDM DSS systems. DSS is being implemented in the fifth generation of wireless communication systems (5G) to improve the spectrum efficiency. In a MIMO-OFDM system, not all the subcarriers are utilized simultaneously by the primary user (PU). Therefore, it is essential to sense the idle frequency bands and assign them to the secondary user (SU). The effectiveness of SDFR in capturing the spatio-temporal correlation of MIMO-OFDM time-series and predicting the availability of frequency bands in the future time slots is studied as well. In the third application, the SDFR is modified to be adopted in video-based face recognition. In this task, the SDFR is leveraged to recognize the identities of different subjects while they rotate their heads in different angles. Another contribution of this dissertation is to propose a novel encoding scheme of spiking neurons which is inspired by the cognitive studies of rats. For the first time, the multiplexing of multiple neural codes is introduced and it is shown that the robustness and resilience of the spiking neurons is increased against noisy data, and adversarial attacks, respectively. Adversarial attacks are small and imperceptible perturbations of the input data, which have shown to be able to fool deep learning (DL) models. So far, many adversarial attack and defense mechanisms have been introduced for DL models. Compromising the security and reliability of artificial intelligence (AI) systems is a major concern of government, industry and cyber-security researchers, in that insufficient protections can compromise the security and privacy of everyone in society. Finally, a defense mechanism to protect spiking neurons against adversarial attacks is introduced for the first time. In a nutshell, this dissertation presents a novel energy efficient deep spiking recurrent neural network which is inspired by delayed dynamic loops. The effectiveness of the introduced model is verified in several different applications. At the end, novel encoding and defense mechanisms are introduced which improve the robustness of the model against noise and adversarial attacks. / Doctor of Philosophy / The ultimate goal of artificial intelligence (AI) is to mimic the human brain. Artificial neural networks (ANN) are an attempt to realize that goal. However, traditional ANNs are very far from mimicking biological neurons. It is well-known that biological neurons communicate with one another through signals in the format of spikes. Therefore, artificial spiking neural networks (SNNs) have been introduced which behave more similarly to biological neurons. Moreover, SNNs are very energy efficient which makes them a suitable choice for hardware implementation of ANNs (neuromporphic computing). Despite the many benefits that are brought about by SNNs, they are still behind traditional ANNs in terms of performance. Therefore, in this dissertation, a new structure of SNNs is introduced which outperforms the traditional ANNs in three different applications. This new structure is inspired by delayed dynamic loops which exist in biological brains. The main objective of this novel structure is to capture the spatio-temporal correlation which exists in time-series while the training overhead and power consumption is reduced. Another contribution of this dissertation is to introduce novel encoding schemes for spiking neurons. It is clear that biological neurons leverage spikes, but the language that they use to communicate is not clear. Hence, the spikes require to be encoded in a certain language which is called neural spike encoding scheme. Inspired by the cognitive studies of rats, a novel encoding scheme is presented. Lastly, it is shown that the introduced encoding scheme increases the robustness of SNNs against noisy data and adversarial attacks. AI models including SNNs have shown to be vulnerable to adversarial attacks. Adversarial attacks are minor perturbations of the input data that can cause the AI model to misscalassify the data. For the first time, a defense mechanism is introduced which can protect SNNs against such attacks.
25

Energy-efficient Neuromorphic Computing for Resource-constrained Internet of Things Devices

Liu, Shiya 03 November 2023 (has links)
Due to the limited computation and storage resources of Internet of Things (IoT) devices, many emerging intelligent applications based on deep learning techniques heavily depend on cloud computing for computation and storage. However, cloud computing faces technical issues with long latency, poor reliability, and weak privacy, resulting in the need for on-device computation and storage. Also, on-device computation is essential for many time-critical applications, which require real-time data processing and energy-efficient. Furthermore, the escalating requirements for on-device processing are driven by network bandwidth limitations and consumer anticipations concerning data privacy and user experience. In the realm of computing, there is a growing interest in exploring novel technologies that can facilitate ongoing advancements in performance. Of the various prospective avenues, the field of neuromorphic computing has garnered significant recognition as a crucial means to achieve fast and energy-efficient machine intelligence applications for IoT devices. The programming of neuromorphic computing hardware typically involves the construction of a spiking neural network (SNN) capable of being deployed onto the designated neuromorphic hardware. This dissertation presents a range of methodologies aimed at enhancing the precision and energy efficiency of SNNs. To be more precise, these advancements are achieved by incorporating four essential methods. The first method is the quantization of neural networks through knowledge distillation. This work introduces a quantization technique that effectively reduces the computational and storage resource requirements of a model while minimizing the loss of accuracy. To further enhance the reduction of quantization errors, the second method introduces a novel quantization-aware training algorithm specifically designed for training quantized spiking neural network (SNN) models intended for execution on the Loihi chip, a specialized neuromorphic computing chip. SNNs generally exhibit lower accuracy performance compared to deep neural networks (DNNs). The third approach introduces a DNN-SNN co-learning algorithm, which enhances the performance of SNN models by leveraging knowledge obtained from DNN models. The design of the neural architecture plays a vital role in enhancing the accuracy and energy efficiency of an SNN model. The fourth method presents a novel neural architecture search algorithm specifically tailored for SNNs on the Loihi chip. The method selects an optimal architecture based on gradients induced by the architecture at initialization across different data samples without the need for training the architecture. To demonstrate the effectiveness and performance across diverse machine intelligence applications, our methods are evaluated through (i) image classification, (ii) spectrum sensing, and (iii) modulation symbol detection. / Doctor of Philosophy / In the emerging Internet of Things (IoT), our everyday devices, from smart home gadgets to wearables, can autonomously make intelligent decisions. However, due to their limited computing power and storage, many IoT devices heavily depend on cloud computing, which brings along issues like slow response times, privacy concerns, and unreliable connections. Neuromorphic computing is a recognized and crucial approach for achieving fast and energy-efficient machine intelligence applications in IoT devices. Inspired by the human brain's neural networks, this cutting-edge approach allows devices to perform complex tasks efficiently and in real-time. The programming of this neuromorphic hardware involves creating spiking neural networks (SNNs). This dissertation presents several innovative methods to improve the precision and energy efficiency of these SNNs. Firstly, a technique called "quantization" reduces the computational and storage requirements of models without sacrificing accuracy. Secondly, a unique training algorithm is designed to enhance the performance of SNN models. Thirdly, a clever co-learning algorithm allows SNN models to learn from traditional deep neural networks (DNNs), further improving their accuracy. Lastly, a novel neural architecture search algorithm finds the best architecture for SNNs on the designated neuromorphic chip, without the need for extensive training. By making IoT devices smarter and more efficient, neuromorphic computing brings us closer to a world where our gadgets can perform intelligent tasks independently, enhancing convenience and privacy for users across the globe.
26

Exploring Column Update Elimination Optimization for Spike-Timing-Dependent Plasticity Learning Rule / Utforskar kolumnuppdaterings-elimineringsoptimering för spik-timing-beroende plasticitetsinlärningsregel

Singh, Ojasvi January 2022 (has links)
Hebbian learning based neural network learning rules when implemented on hardware, store their synaptic weights in the form of a two-dimensional matrix. The storage of synaptic weights demands large memory bandwidth and storage. While memory units are optimized for only row-wise memory access, Hebbian learning rules, like the spike-timing dependent plasticity, demand both row and column-wise access of memory. This dual pattern of memory access accounts for the dominant cost in terms of latency as well as energy for realization of large scale spiking neural networks in hardware. In order to reduce the memory access cost in Hebbian learning rules, a Column Update Elimination optimization has been previously implemented, with great efficacy, on the Bayesian Confidence Propagation neural network, that faces a similar challenge of dual pattern memory access. This thesis explores the possibility of extending the column update elimination optimization to spike-timing dependent plasticity, by simulating the learning rule on a two layer network of leaky integrate-and-fire neurons on an image classification task. The spike times are recorded for each neuron in the network, to derive a suitable probability distribution function for spike rates per neuron. This is then used to derive an ideal postsynaptic spike history buffer size for the given algorithm. The associated memory access reductions are analysed based on data to assess feasibility of the optimization to the learning rule. / Hebbiansk inlärning baserat på neural nätverks inlärnings regler används vid implementering på hårdvara, de lagrar deras synaptiska vikter i form av en tvådimensionell matris. Lagringen av synaptiska vikter kräver stor bandbredds minne och lagring. Medan minnesenheter endast är optimerade för radvis minnesåtkomst. Hebbianska inlärnings regler kräver som spike-timing-beroende plasticitet, både rad- och kolumnvis åtkomst av minnet. Det dubbla mönstret av minnes åtkomsten står för den dominerande kostnaden i form av fördröjning såväl som energi för realiseringen av storskaliga spikande neurala nätverk i hårdvara. För att minska kostnaden för minnesåtkomst i hebbianska inlärnings regler har en Column Update Elimination-optimering tidigare implementerats, med god effektivitet på Bayesian Confidence Propagation neurala nätverket, som står inför en liknande utmaning med dubbel mönster minnesåtkomst. Denna avhandling undersöker möjligheten att utöka ColumnUpdate Elimination-optimeringen till spike-timing-beroende plasticitet. Detta genom att simulera inlärnings regeln på ett tvålagers nätverk av läckande integrera-och-avfyra neuroner på en bild klassificerings uppgift. Spike tiderna registreras för varje neuron i nätverket för att erhålla en lämplig sannolikhetsfördelning funktion för frekvensen av toppar per neuron. Detta används sedan för att erhålla en idealisk postsynaptisk spike historisk buffertstorlek för den angivna algoritmen. De associerade minnesåtkomst minskningarna analyseras baserat på data för att bedöma genomförbarheten av optimeringen av inlärnings regeln.
27

Deep spiking neural networks

Liu, Qian January 2018 (has links)
Neuromorphic Engineering (NE) has led to the development of biologically-inspired computer architectures whose long-term goal is to approach the performance of the human brain in terms of energy efficiency and cognitive capabilities. Although there are a number of neuromorphic platforms available for large-scale Spiking Neural Network (SNN) simulations, the problem of programming these brain-like machines to be competent in cognitive applications still remains unsolved. On the other hand, Deep Learning has emerged in Artificial Neural Network (ANN) research to dominate state-of-the-art solutions for cognitive tasks. Thus the main research problem emerges of understanding how to operate and train biologically-plausible SNNs to close the gap in cognitive capabilities between SNNs and ANNs. SNNs can be trained by first training an equivalent ANN and then transferring the tuned weights to the SNN. This method is called ‘off-line’ training, since it does not take place on an SNN directly, but rather on an ANN instead. However, previous work on such off-line training methods has struggled in terms of poor modelling accuracy of the spiking neurons and high computational complexity. In this thesis we propose a simple and novel activation function, Noisy Softplus (NSP), to closely model the response firing activity of biologically-plausible spiking neurons, and introduce a generalised off-line training method using the Parametric Activation Function (PAF) to map the abstract numerical values of the ANN to concrete physical units, such as current and firing rate in the SNN. Based on this generalised training method and its fine tuning, we achieve the state-of-the-art accuracy on the MNIST classification task using spiking neurons, 99.07%, on a deep spiking convolutional neural network (ConvNet). We then take a step forward to ‘on-line’ training methods, where Deep Learning modules are trained purely on SNNs in an event-driven manner. Existing work has failed to provide SNNs with recognition accuracy equivalent to ANNs due to the lack of mathematical analysis. Thus we propose a formalised Spike-based Rate Multiplication (SRM) method which transforms the product of firing rates to the number of coincident spikes of a pair of rate-coded spike trains. Moreover, these coincident spikes can be captured by the Spike-Time-Dependent Plasticity (STDP) rule to update the weights between the neurons in an on-line, event-based, and biologically-plausible manner. Furthermore, we put forward solutions to reduce correlations between spike trains; thereby addressing the result of performance drop in on-line SNN training. The promising results of spiking Autoencoders (AEs) and Restricted Boltzmann Machines (SRBMs) exhibit equivalent, sometimes even superior, classification and reconstruction capabilities compared to their non-spiking counterparts. To provide meaningful comparisons between these proposed SNN models and other existing methods within this rapidly advancing field of NE, we propose a large dataset of spike-based visual stimuli and a corresponding evaluation methodology to estimate the overall performance of SNN models and their hardware implementations.
28

STDP Implementation Using CBRAM Devices in CMOS

January 2015 (has links)
abstract: Alternative computation based on neural systems on a nanoscale device are of increasing interest because of the massive parallelism and scalability they provide. Neural based computation systems also offer defect finding and self healing capabilities. Traditional Von Neumann based architectures (which separate the memory and computation units) inherently suffer from the Von Neumann bottleneck whereby the processor is limited by the number of instructions it fetches. The clock driven based Von Neumann computer survived because of technology scaling. However as transistor scaling is slowly coming to an end with channel lengths becoming a few nanometers in length, processor speeds are beginning to saturate. This lead to the development of multi-core systems which process data in parallel, with each core being based on the Von Neumann architecture. The human brain has always been a mystery to scientists. Modern day super computers are outperformed by the human brain in certain computations. The brain occupies far less space and consumes a fraction of the power a super computer does with certain processes such as pattern recognition. Neuromorphic computing aims to mimic biological neural systems on silicon to exploit the massive parallelism that neural systems offer. Neuromorphic systems are event driven systems rather than being clock driven. One of the issues faced by neuromorphic computing was the area occupied by these circuits. With recent developments in the field of nanotechnology, memristive devices on a nanoscale have been developed and show a promising solution. Memristor based synapses can be up to three times smaller than Complementary Metal Oxide Semiconductor (CMOS) based synapses. In this thesis, the Programmable Metallization Cell (a memristive device) is used to prove a learning algorithm known as Spike Time Dependant Plasticity (STDP). This learning algorithm is an extension to Hebb’s learning rule in which the synapses weight can be altered by the relative timing of spikes across it. The synaptic weight with the memristor will be its conductance, and CMOS oscillator based circuits will be used to produce spikes that can modulate the memristor conductance by firing with different phases differences. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2015
29

A biologically inspired approach to the cocktail party problem

Chou, Kenny 19 May 2020 (has links)
At a cocktail party, one can choose to scan the room for conversations of interest, attend to a specific conversation partner, switch between conversation partners, or not attend to anything at all. The ability of the normal-functioning auditory system to flexibly listen in complex acoustic scenes plays a central role in solving the cocktail party problem (CPP). In contrast, certain demographics (e.g., individuals with hearing impairment or older adults) are unable to solve the CPP, leading to psychological ailments and reduced quality of life. Since the normal auditory system still outperforms machines in solving the CPP, an effective solution may be found by mimicking the normal-functioning auditory system. Spatial hearing likely plays an important role in CPP-processing in the auditory system. This thesis details the development of a biologically based approach to the CPP by modeling specific neural mechanisms underlying spatial tuning in the auditory cortex. First, we modeled bottom-up, stimulus-driven mechanisms using a multi-layer network model of the auditory system. To convert spike trains from the model output into audible waveforms, we designed a novel reconstruction method based on the estimation of time-frequency masks. We showed that our reconstruction method produced sounds with significantly higher intelligibility and quality than previous reconstruction methods. We also evaluated the algorithm's performance using a psychoacoustic study, and found that it provided the same amount of benefit to normal-hearing listeners as a current state-of-the-art acoustic beamforming algorithm. Finally, we modeled top-down, attention driven mechanisms that allowed the network to flexibly operate in different regimes, e.g., monitor the acoustic scene, attend to a specific target, and switch between attended targets. The model explains previous experimental observations, and proposes candidate neural mechanisms underlying flexible listening in cocktail-party scenarios. The strategies proposed here would benefit hearing-assistive devices for CPP processing (e.g., hearing aids), where users would benefit from switching between various modes of listening in different social situations. / 2022-05-19T00:00:00Z
30

Training Spiking Neural Networks for Energy-Efficient Neuromorphic Computing

Gopalakrishnan Srinivasan (8088431) 06 December 2019 (has links)
<p>Spiking Neural Networks (SNNs), widely known as the third generation of artificial neural networks, offer a promising solution to approaching the brains' processing capability for cognitive tasks. With more biologically realistic perspective on input processing, SNN performs neural computations using spikes in an event-driven manner. The asynchronous spike-based computing capability can be exploited to achieve improved energy efficiency in neuromorphic hardware. Furthermore, SNN, on account of spike-based processing, can be trained in an unsupervised manner using Spike Timing Dependent Plasticity (STDP). STDP-based learning rules modulate the strength of a multi-bit synapse based on the correlation between the spike times of the input and output neurons. In order to achieve plasticity with compressed synaptic memory, stochastic binary synapse is proposed where spike timing information is embedded in the synaptic switching probability. A bio-plausible probabilistic-STDP learning rule consistent with Hebbian learning theory is proposed to train a network of binary as well as quaternary synapses. In addition, hybrid probabilistic-STDP learning rule incorporating Hebbian and anti-Hebbian mechanisms is proposed to enhance the learnt representations of the stochastic SNN. The efficacy of the presented learning rules are demonstrated for feed-forward fully-connected and residual convolutional SNNs on the MNIST and the CIFAR-10 datasets.<br></p><p>STDP-based learning is limited to shallow SNNs (<5 layers) yielding lower than acceptable accuracy on complex datasets. This thesis proposes block-wise complexity-aware training algorithm, referred to as BlocTrain, for incrementally training deep SNNs with reduced memory requirements using spike-based backpropagation through time. The deep network is divided into blocks, where each block consists of few convolutional layers followed by an auxiliary classifier. The blocks are trained sequentially using local errors from the respective auxiliary classifiers. Also, the deeper blocks are trained only on the hard classes determined using the class-wise accuracy obtained from the classifier of previously trained blocks. Thus, BlocTrain improves the training time and computational efficiency with increasing block depth. In addition, higher computational efficiency is obtained during inference by exiting early for easy class instances and activating the deeper blocks only for hard class instances. The ability of BlocTrain to provide improved accuracy as well as higher training and inference efficiency compared to end-to-end approaches is demonstrated for deep SNNs (up to 11 layers) on the CIFAR-10 and the CIFAR-100 datasets.<br></p><p>Feed-forward SNNs are typically used for static image recognition while recurrent Liquid State Machines (LSMs) have been shown to encode time-varying speech data. Liquid-SNN, consisting of input neurons sparsely connected by plastic synapses to randomly interlinked reservoir of spiking neurons (or liquid), is proposed for unsupervised speech and image recognition. The strength of the synapses interconnecting the input and liquid are trained using STDP, which makes it possible to infer the class of a test pattern without a readout layer typical in standard LSMs. The Liquid-SNN suffers from scalability challenges due to the need to primarily increase the number of neurons to enhance the accuracy. SpiLinC, composed of an ensemble of multiple liquids, where each liquid is trained on a unique input segment, is proposed as a scalable model to achieve improved accuracy. SpiLinC recognizes a test pattern by combining the spiking activity of the individual liquids, each of which identifies unique input features. As a result, SpiLinC offers comparable accuracy to Liquid-SNN with added synaptic sparsity and faster training convergence, which is validated on the digit subset of TI46 speech corpus and the MNIST dataset.</p>

Page generated in 0.0993 seconds