Proceedings of the International Conference on Neuromorphic Systems最新文献

Dynamic Programming with Spiking Neural Computing 基于脉冲神经计算的动态规划

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354285

J. Aimone, Ojas D. Parekh, C. Phillips, A. Pınar, William M. Severa, Helen Xu

引用次数: 18

Approximate Pattern Matching using Hierarchical Graph Construction and Sparse Distributed Representation 基于层次图构造和稀疏分布表示的近似模式匹配

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354286

Aakanksha Mathuria, D. Hammerstrom

{"title":"Approximate Pattern Matching using Hierarchical Graph Construction and Sparse Distributed Representation","authors":"Aakanksha Mathuria, D. Hammerstrom","doi":"10.1145/3354265.3354286","DOIUrl":"https://doi.org/10.1145/3354265.3354286","url":null,"abstract":"With recent developments in deep networks, there have been significant advances in visual object detection and recognition. However, some of these networks are still easily fooled/hacked and have shown \"bag of features\" failures. Some of this is due to the fact that even deep networks make only marginal use of the complex structure that exists in real-world images, even after training on huge numbers of images. Biology appears to take advantage of such a structure, but how? In our research, we are studying approaches for robust pattern matching using still, 2D Blocks World images based on graphical representations of the various components of an image. Such higher order information represents the \"structure\" of the visual object. Here we discuss how the structural information of an image can be captured in a Sparse Distributed Representation (SDR) loosely based on cortical circuits. We apply probabilistic graph isomorphism and subgraph isomorphism to our 2D Blocks World images and achieve O (1) and O (nk) complexity for an approximate match. The optimal match is an NP-Hard problem. The image labeled graph is created using OpenCV to find the object contours and objects' labels and a fixed radius nearest neighbor algorithm to build the edges between the objects. Pattern matching is done using the properties of SDRs. Our research shows the promise of applying graph-based neuromorphic techniques for pattern matching of images based on such structure.","PeriodicalId":225636,"journal":{"name":"Proceedings of the International Conference on Neuromorphic Systems","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124163731","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

Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips 神经形态芯片实时脉冲神经网络解码器的设计与分析

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354280

Chenyuan Zhao, Lingjia Liu, Y. Yi

引用次数: 2

MLP+NeuroSimV3.0: Improving On-chip Learning Performance with Device to Algorithm Optimizations MLP+NeuroSimV3.0:通过设备到算法优化提高片上学习性能

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354266

Yandong Luo, Xiaochen Peng, Shimeng Yu

引用次数: 23

Feature Extraction using Spiking Convolutional Neural Networks 基于脉冲卷积神经网络的特征提取

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354279

Ruthvik Vaila, John N. Chiasson, V. Saxena

引用次数: 18

Constraints on sequence processing speed in biological neuronal networks 生物神经网络中序列处理速度的约束

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354281

Younes Bouhadjar, M. Diesmann, R. Waser, D. Wouters, T. Tetzlaff

引用次数: 2

Proceedings of the International Conference on Neuromorphic Systems 神经形态系统国际会议论文集

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265

引用次数: 2

Approximating Back-propagation for a Biologically Plausible Local Learning Rule in Spiking Neural Networks 脉冲神经网络中生物似然局部学习规则的近似反向传播

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354275

Amar Shrestha, Haowen Fang, Qing Wu, Qinru Qiu

{"title":"Approximating Back-propagation for a Biologically Plausible Local Learning Rule in Spiking Neural Networks","authors":"Amar Shrestha, Haowen Fang, Qing Wu, Qinru Qiu","doi":"10.1145/3354265.3354275","DOIUrl":"https://doi.org/10.1145/3354265.3354275","url":null,"abstract":"Asynchronous event-driven computation and communication using spikes facilitate the realization of spiking neural networks (SNN) to be massively parallel, extremely energy efficient and highly robust on specialized neuromorphic hardware. However, the lack of a unified robust learning algorithm limits the SNN to shallow networks with low accuracies. Artificial neural networks (ANN), however, have the backpropagation algorithm which can utilize gradient descent to train networks which are locally robust universal function approximators. But backpropagation algorithm is neither biologically plausible nor neuromorphic implementation friendly because it requires: 1) separate backward and forward passes, 2) differentiable neurons, 3) high-precision propagated errors, 4) coherent copy of weight matrices at feedforward weights and the backward pass, and 5) non-local weight update. Thus, we propose an approximation of the backpropagation algorithm completely with spiking neurons and extend it to a local weight update rule which resembles a biologically plausible learning rule spike-timing-dependent plasticity (STDP). This will enable error propagation through spiking neurons for a more biologically plausible and neuromorphic implementation friendly backpropagation algorithm for SNNs. We test the proposed algorithm on various traditional and non-traditional benchmarks with competitive results.","PeriodicalId":225636,"journal":{"name":"Proceedings of the International Conference on Neuromorphic Systems","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126850153","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: 27

Training Spiking Networks via Natural Evolution Strategies 通过自然进化策略训练尖峰网络

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354283

W. Olin-Ammentorp, N. Cady

引用次数: 0

Graph Partitioning as Quadratic Unconstrained Binary Optimization (QUBO) on Spiking Neuromorphic Hardware 峰值神经形态硬件上的二次无约束二值优化(QUBO)图划分

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354269

S. Mniszewski

引用次数: 11