Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference最新文献_第2页

Easy and efficient spike-based Machine Learning with mlGeNN 简单高效的基于峰值的mlGeNN机器学习

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2023-04-11 DOI: 10.1145/3584954.3585001

James C. Knight, T. Nowotny

引用次数: 3

SupportHDC: Hyperdimensional Computing with Scalable Hypervector Sparsity 支持:具有可伸缩的超向量稀疏的超维计算

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2023-04-11 DOI: 10.1145/3584954.3584961

A. Safa, I. Ocket, F. Catthoor, G. Gielen

{"title":"SupportHDC: Hyperdimensional Computing with Scalable Hypervector Sparsity","authors":"A. Safa, I. Ocket, F. Catthoor, G. Gielen","doi":"10.1145/3584954.3584961","DOIUrl":"https://doi.org/10.1145/3584954.3584961","url":null,"abstract":"Hyperdimensional Computing (HDC) is an emerging brain-inspired machine learning method that is recently gaining much attention for performing tasks such as pattern recognition and bio-signal classification with ultra-low energy and area overheads when implemented in hardware. HDC relies on the encoding of input signals into binary or few-bit Hypervectors (HVs) and performs low-complexity manipulations on HVs in order to classify the input signals. In this context, the sparsity of HVs directly impacts energy consumption, since the sparser the HVs, the more zero-valued computations can be skipped. This short paper introduces SupportHDC, a novel HDC design framework that can jointly optimize system accuracy and sparsity in an automated manner, in order to trade off classification performance and hardware implementation overheads. We illustrate the inner working of the framework on two bio-signal classification tasks: cancer detection and arrhythmia detection. We show that SupportHDC can reach a higher accuracy compared to the conventional splatter-code architectures used in many works, while enabling the system designer to choose the final design solution from the accuracy-sparsity trade-off curve produced by the framework. We release the source code for reproducing our experiments with the hope of being beneficial to future research.","PeriodicalId":375527,"journal":{"name":"Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116905586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Sigma-Delta Networks for Robot Arm Control 机器人手臂控制的Sigma-Delta网络

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2023-04-11 DOI: 10.1145/3584954.3584964

W. Lawson, Anthony M. Harrison, J. Trafton

引用次数: 0

Goemans-Williamson MAXCUT approximation algorithm on Loihi Loihi上的Goemans-Williamson MAXCUT近似算法

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2023-04-11 DOI: 10.1145/3584954.3584955

Bradley H. Theilman, J. Aimone

引用次数: 1

NEO: Neuron State Dependent Mechanisms for Efficient Continual Learning 高效持续学习的神经元状态依赖机制

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2023-04-11 DOI: 10.1145/3584954.3584960

A. Daram, D. Kudithipudi

{"title":"NEO: Neuron State Dependent Mechanisms for Efficient Continual Learning","authors":"A. Daram, D. Kudithipudi","doi":"10.1145/3584954.3584960","DOIUrl":"https://doi.org/10.1145/3584954.3584960","url":null,"abstract":"Continual learning (sequential learning of tasks) is challenging for deep neural networks, mainly because of catastrophic forgetting, the tendency for accuracy on previously trained tasks to drop when new tasks are learned. Although several biologically-inspired techniques have been proposed for mitigating catastrophic forgetting, they typically require additional memory and/or computational overhead. Here, we propose a novel regularization approach that combines neuronal activation-based importance measurement with neuron state-dependent learning mechanisms to alleviate catastrophic forgetting in both task-aware and task-agnostic scenarios. We introduce a neuronal state-dependent mechanism driven by neuronal activity traces and selective learning rules, with storage requirements for regularization parameters that grow slower with network size - compared to schemes that calculate weight importance, whose storage grows quadratically. The proposed model, NEO, is able to achieve performance comparable to other state-of-the-art regularization based approaches to catastrophic forgetting, while operating with a reduced memory overhead.","PeriodicalId":375527,"journal":{"name":"Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131969219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Speech2Spikes: Efficient Audio Encoding Pipeline for Real-time Neuromorphic Systems 用于实时神经形态系统的高效音频编码管道

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2023-04-11 DOI: 10.1145/3584954.3584995

Kenneth Michael Stewart, Timothy M. Shea, Noah Pacik-Nelson, Eric M Gallo, A. Danielescu

{"title":"Speech2Spikes: Efficient Audio Encoding Pipeline for Real-time Neuromorphic Systems","authors":"Kenneth Michael Stewart, Timothy M. Shea, Noah Pacik-Nelson, Eric M Gallo, A. Danielescu","doi":"10.1145/3584954.3584995","DOIUrl":"https://doi.org/10.1145/3584954.3584995","url":null,"abstract":"Despite the maturity and availability of speech recognition systems, there are few available spiking speech recognition tasks that can be implemented with current neuromorphic systems. The methods used previously to generate spiking speech data are not capable of encoding speech in real-time or encoding very large modern speech datasets efficiently for input to neuromorphic processors. The ability to efficiently encode audio data to spikes will enable a wider variety of spiking audio datasets to be available and can also enable algorithmic development of real-time neuromorphic automatic speech recognition systems. Therefore, we developed speech2spikes, a simple and efficient audio processing pipeline that encodes recorded audio into spikes and is suitable for real-time operation with low-power neuromorphic processors. To demonstrate the efficacy of our method for audio to spike encoding we show that a small feed-forward spiking neural network trained on data generated with the pipeline achieves accuracy on the Google Speech Commands recognition task, exceeding the state-of-the art set by Spiking Speech Commands, a prior spiking encoding of the Google Speech Commands dataset, by over 10%. We also demonstrate a proof-of-concept real-time neuromorphic automatic speech recognition system using audio encoded with speech2spikes streamed to an Intel Loihi neuromorphic research processor.","PeriodicalId":375527,"journal":{"name":"Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132447023","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

hxtorch.snn: Machine-learning-inspired Spiking Neural Network Modeling on BrainScaleS-2 hxtorch。snn:基于brainscale的基于机器学习的峰值神经网络建模

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2022-12-23 DOI: 10.1145/3584954.3584993

Philipp Spilger, E. Arnold, Luca Blessing, Christian Mauch, Christian Pehle, Eric Müller, J. Schemmel

引用次数: 2

AEStream: Accelerated event-based processing with coroutines AEStream:使用协程加速基于事件的处理

Proceedings of the 2023 Annual Neuro-Inspired Computational Elements Conference Pub Date : 2022-12-21 DOI: 10.1145/3584954.3584997

Jens Egholm Pedersen, J. Conradt

引用次数: 1