Proceedings of the International Conference on Neuromorphic Systems最新文献_第2页

Memristor Based Autoencoder for Unsupervised Real-Time Network Intrusion and Anomaly Detection 基于忆阻器的无监督实时网络入侵与异常检测自编码器

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354267

Md. Shahanur Alam, B. Fernando, Yassine Jaoudi, C. Yakopcic, Raqibul Hasan, M. Tarek, Taha, G. Subramanyam

引用次数: 12

A Segmented Attractor Network for Neuromorphic Associative Learning 神经形态联想学习的分段吸引子网络

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354284

Alexander Jones, R. Jha, A. Jacob, Cory E. Merkel

引用次数: 2

Unsupervised Dictionary Learning via a Spiking Locally Competitive Algorithm 基于尖峰局部竞争算法的无监督字典学习

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354276

Y. Watkins, A. Thresher, Peter F. Schultz, Andreas Wild, A. Sornborger, Garrett T. Kenyon

{"title":"Unsupervised Dictionary Learning via a Spiking Locally Competitive Algorithm","authors":"Y. Watkins, A. Thresher, Peter F. Schultz, Andreas Wild, A. Sornborger, Garrett T. Kenyon","doi":"10.1145/3354265.3354276","DOIUrl":"https://doi.org/10.1145/3354265.3354276","url":null,"abstract":"A new class of neuromorphic processors promises to provide fast and power-efficient execution of spiking neural networks with on-chip synaptic plasticity. This efficiency derives in part from the fine-grained parallelism as well as event-driven communication mediated by spatially and temporally sparse spike messages. Another source of efficiency arises from the close spatial proximity between synapses and the sites where their weights are applied and updated. This proximity of compute and memory elements drastically reduces expensive data movements but imposes the constraint that only local operations can be efficiently performed, similar to constraints present in biological neural circuits. Efficient weight update operations should therefore only depend on information available locally at each synapse as non-local operations that involve copying, taking a transpose, or normalizing an entire weight matrix are not efficiently supported by present neuromorphic architectures. Moreover, spikes are typically non-negative events, which imposes additional constraints on how local weight update operations can be performed. The Locally Competitive Algorithm (LCA) is a dynamical sparse solver that uses only local computations between non-spiking leaky integrator neurons, allowing for massively parallel implementations on compatible neuromorphic architectures such as Intel's Loihi research chip. It has been previously demonstrated that non-spiking LCA can be used to learn dictionaries of convolutional kernels in an unsupervised manner from raw, unlabeled input, although only by employing non-local computation and signed non-spiking outputs. Here, we show how unsupervised dictionary learning with spiking LCA (S-LCA) can be implemented using only local computation and unsigned spike events, providing a promising strategy for constructing self-organizing neuromorphic chips.","PeriodicalId":225636,"journal":{"name":"Proceedings of the International Conference on Neuromorphic Systems","volume":"35 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":"132123267","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: 4

A Neuromorphic Sparse Coding Defense to Adversarial Images 对抗图像的神经形态稀疏编码防御

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354277

Edward Kim, Jessica Yarnall, Priya Shah, Garrett T. Kenyon

{"title":"A Neuromorphic Sparse Coding Defense to Adversarial Images","authors":"Edward Kim, Jessica Yarnall, Priya Shah, Garrett T. Kenyon","doi":"10.1145/3354265.3354277","DOIUrl":"https://doi.org/10.1145/3354265.3354277","url":null,"abstract":"Adversarial images are a class of images that have been slightly altered by very specific noise to change the way a deep learning neural network classifies the image. In many cases, this particular noise is imperceptible to the human vision system and thus presents a vulnerability of significant concern to the machine learning and artificial intelligence community. Research towards mitigating this type of attack has taken many forms, one of which is to filter or post process the image before classifying the image with a deep neural network. Techniques such as smoothing, filtering, and compression have been used with varying levels of success. In our work, we explored the use of a neuromorphic software and hardware approach as a protection against adversarial image attack. The algorithm governing our neuromorphic approach is based upon sparse coding. Our sparse coding approach is solved using a dynamic system of equations that models biological low level vision. Our quantitative and qualitative results show that a sparse coding reconstruction is remarkably invariant to changes in sparsity and reconstruction error with respect to classification accuracy. Furthermore, our approach is able to maintain low reconstruction errors without sacrificing classification performance.","PeriodicalId":225636,"journal":{"name":"Proceedings of the International Conference on Neuromorphic Systems","volume":"17 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":"114412423","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: 15

Analog Neurons that Signal with Spiking Frequencies 具有尖峰频率信号的模拟神经元

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354273

K. Yue, Xiaoyu Wang, Jay Jadav, Akshay Vartak, A. C. Parker

引用次数: 2

Benchmarking Event-Driven Neuromorphic Architectures 对标事件驱动的神经形态架构

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354278

C. Vineyard, Sam Green, William M. Severa, Ç. Koç

引用次数: 5

Fabrication and Performance of Hybrid ReRAM-CMOS Circuit Elements for Dynamic Neural Networks 动态神经网络用rram - cmos混合电路元件的制备与性能研究

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354271

Maximilian Liehr, Jubin Hazra, K. Beckmann, W. Olin-Ammentorp, N. Cady, Ryan Weiss, Sagarvarma Sayyaparaju, G. Rose, J. V. Nostrand

引用次数: 8

Learning Behavior of Memristor-Based Neuromorphic Circuits in the Presence of Radiation 基于记忆器的神经形态回路在辐射下的学习行为

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-07-23 DOI: 10.1145/3354265.3354272

Sumedha Gandharava Dahl, Robert C. Ivans, K. D. Cantley

{"title":"Learning Behavior of Memristor-Based Neuromorphic Circuits in the Presence of Radiation","authors":"Sumedha Gandharava Dahl, Robert C. Ivans, K. D. Cantley","doi":"10.1145/3354265.3354272","DOIUrl":"https://doi.org/10.1145/3354265.3354272","url":null,"abstract":"In this paper, a feed-forward spiking neural network with memristive synapses is designed to learn a spatio-temporal pattern representing the 25-pixel character 'B' by separating correlated and uncorrelated afferents. The network uses spike-timing-dependent plasticity (STDP) learning behavior, which is implemented using biphasic neuron spikes. A TiO2 memristor non-linear drift model is used to simulate synaptic behavior in the neuromorphic circuit. The network uses a many-to-one topology with 25 pre-synaptic neurons (afferent) each connected to a memristive synapse and one postsynaptic neuron. The memristor model is modified to include the experimentally observed effect of state-altering radiation. During the learning process, irradiation of the memristors alters their conductance state, and the effect on circuit learning behavior is determined. Radiation is observed to generally increase the synaptic weight of the memristive devices, making the network connections more conductive and less stable. However, the network appears to relearn the pattern when radiation ceases but does take longer to resolve the correlation and pattern. Network recovery time is proportional to flux, intensity, and duration of the radiation. Further, at lower but continuous radiation exposure, (flux 1x1010 cm-2s-1 and below), the circuit resolves the pattern successfully for up to 100 s.","PeriodicalId":225636,"journal":{"name":"Proceedings of the International Conference on Neuromorphic Systems","volume":"23 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":"121469698","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: 6

A Low-Power Domino Logic Architecture for Memristor-Based Neuromorphic Computing 基于忆阻器的神经形态计算的低功耗Domino逻辑架构

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-06-13 DOI: 10.1145/3354265.3354282

Cory E. Merkel, A. Nikam

引用次数: 1

Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning 特定任务动态学习的神经形态架构优化

Proceedings of the International Conference on Neuromorphic Systems Pub Date : 2019-06-04 DOI: 10.1145/3354265.3354270

Sandeep Madireddy, A. Yanguas-Gil, Prasanna Balaprakash

{"title":"Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning","authors":"Sandeep Madireddy, A. Yanguas-Gil, Prasanna Balaprakash","doi":"10.1145/3354265.3354270","DOIUrl":"https://doi.org/10.1145/3354265.3354270","url":null,"abstract":"The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key challenge, however, is to understand which learning rules are best suited for specific tasks and how the relevant hyperparameters can be fine-tuned. In this work, we introduce a conceptual framework in which the learning process is integrated into the network itself. This allows us to cast meta-learning as a mathematical optimization problem. We employ DeepHyper, a scalable, asynchronous model-based search, to simultaneously optimize the choice of meta-learning rules and their hyperparameters. We demonstrate our approach with two different datasets, MNIST and FashionMNIST, using a network architecture inspired by the learning center of the insect brain. Our results show that optimal learning rules can be dataset-dependent even within similar tasks. This dependency demonstrates the importance of introducing versatility and flexibility in the learning algorithms. It also illuminates experimental findings in insect neuroscience that have shown a heterogeneity of learning rules within the insect mushroom body.","PeriodicalId":225636,"journal":{"name":"Proceedings of the International Conference on Neuromorphic Systems","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114934427","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