检索结果-内蒙古大学图书馆

Neuromorphic computing for Interactive Robotics: A Systematic Review

IEEE ACCESS 2022年 10卷 122261-122279页

作者： Aitsam, Muhammad Davies, Sergio Di Nuovo, Alessandro Sheffield Hallam Univ Dept Comp Sheffield S1 1WB England

Modelling functionalities of the brain in human-robot interaction contexts requires a real-time understanding of how each part of a robot (motors, sensors, emotions, etc.) works and how they interact all together to accomplish complex behavioural tasks while interacting with the environment. Human brains are very efficient as they process the information using event-based impulses also known as spikes, which make living creatures very efficient and able to outperform current mainstream robotic systems in almost every task that requires real-time interaction. In recent years, combined efforts by neuroscientists, biologists, computer scientists and engineers make it possible to design biologically realistic hardware and models that can endow the robots with the required human-like processing capability based on neuromorphic computing and Spiking Neural Network (SNN). However, while some attempts have been made, a comprehensive combination of neuromorphic computing and robotics is still missing. In this article, we present a systematic review of neuromorphic computing applications for socially interactive robotics. We first introduce the basic principles, models and architectures of neuromorphic computation. The remaining articles are classified according to the applications they focus on. Finally, we identify the potential research topics for fully integrated socially interactive neuromorphic robots.

关键词： Cognitive robotics neuromorphic engineering socially interactive robotics event-driven computing biologically-plausible computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Spike Timing Dependent Gradient for Direct Training of Fast and Efficient Binarized Spiking Neural Networks

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2023年第4期13卷 1083-1093页

作者： Cai, Zhengyu Kalatehbali, Hamid Rahimian Walters, Ben Azghadi, Mostafa Rahimi Amirsoleimani, Amirali Genov, Roman Univ Toronto Edward S Rogers Sr Dept Elect & Comp Engn Toronto ON M5S 1A1 Canada York Univ Lassonde Sch Engn Toronto ON M3J 1P3 Canada James Cook Univ Coll Sci & Engn Townsville Qld 4811 Australia

Spiking neural networks (SNNs) are well-suited for neuromorphic hardware due to their biological plausibility and energy efficiency. These networks utilize sparse, asynchronous spikes for communication and can be binarized. However, the training of such networks presents several challenges due to their non-differentiable activation function and binarized inter-layer data movement. The well-established backpropagation through time (BPTT) algorithm used to train SNNs encounters notable difficulties because of its substantial memory consumption and extensive computational demands. These limitations restrict its practical utility in real-world scenarios. Therefore, effective techniques are required to train such networks efficiently while preserving accuracy. In this paper, we propose Binarized Spike Timing Dependent Gradient (BSTDG), a novel method that utilizes presynaptic and postsynaptic timings to bypass the non-differentiable gradient and the need of BPTT. Additionally, we employ binarized weights with a threshold training strategy to enhance energy savings and performance. Moreover, we exploit latency/temporal-based coding and the Integrate-and-Fire (IF) model to achieve significant computational advantages. We evaluate the proposed method on Caltech101 Face/Motorcycle, MNIST, Fashion-MNIST, and Spiking Heidelberg Digits. The results demonstrate that the accuracy attained surpasses that of existing BSNNs and single-spike networks under the same structure. Furthermore, the proposed model achieves up to 30 $\times \times \times $ speedup in inference and effectively reduces the number of spikes emitted in the hidden layer by 50% compared to previous works.

关键词： Spike-timing-dependent learning binarized neural network event-driven computing spiking neural networks neuromorphic computing

来源：评论

学校读者我要写书评

暂无评论

TICKTOCKTOKENS: a minimal building block for event-driven systems

TICKTOCKTOKENS: a minimal building block for event-driven sy...

引用

Neuro Inspired Computational Elements Conference (NICE)

作者： Leugering, Johannes Univ Calif San Diego Bioengn Dept La Jolla CA 92093 USA

ISBN: (纸本)9798350390599;9798350390582

event-driven computing is a key feature of many neuromorphic circuits, yet we lack a common general purpose language to describe such systems, reason about their capabilities, and design them by deliberately composing smaller parts. In this paper, I want to ask: what is the equivalent of a logic gate for event-driven systems? I propose one very simple candidate and show how it can be composed into arbitrarily complex event-driven systems using a framework I call TICKTOCKTOKENS. I motivate its design, discuss its capabilities, and share a hardware implementation as a very compact digital circuit.

关键词： event-driven computing neuromorphic discrete event system tokens building block

来源：评论

学校读者我要写书评

暂无评论

Digital Multiplier-Less Spiking Neural Network Architecture of Reinforcement Learning in a Context-Dependent Task

引用

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2020年第4期10卷 498-511页

作者： Asgari, Hajar Maybodi, Babak Mazloom-Nezhad Kreiser, Raphaela Sandamirskaya, Yulia Univ Zurich Inst Neuroinformat INI CH-8057 Zurich Switzerland Swiss Fed Inst Technol Inst Neuroinformat INI CH-8092 Zurich Switzerland Shahid Beheshti Univ Dept Elect Engn Tehran *** Iran

Neuromorphic engineers develop event-based spiking neural networks (SNNs) in hardware. These SNNs closer resemble the dynamics of biological neurons than conventional artificial neural networks and achieve higher efficiency thanks to the event-based, asynchronous nature of the processing. Learning in the hardware SNNs is a more challenging task, however. The conventional supervised learning methods cannot be directly applied to SNNs due to the non-differentiable event-based nature of their activation. For this reason, learning in SNNs is currently an active research topic. Reinforcement learning (RL) is a particularly promising learning method for neuromorphic implementation, especially in the field of autonomous agents' control. An SNN realization of a bio-inspired RL model is in the focus of this work. In particular, in this article, we propose a new digital multiplier-less hardware implementation of an SNN with RL capability. We show how the proposed network can learn stimulus-response associations in a context-dependent task. The task is inspired by biological experiments that study RL in animals. The architecture is described using the standard digital design flow and uses power- and space-efficient cores. The proposed hardware SNN model is compared both to data from animal experiments and to a computational model. We perform a comparison to the behavioral experiments using a robot, to show the learning capability in hardware in a closed sensory-motor loop.

关键词： Neural networks Synapses Membrane potentials Field programmable gate arrays Neuromorphics Reinforcement learning Neuromorphic engineering spiking neural networks (SNN) event-driven computing context-dependent task reinforcement learning field programmable gate array (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Twister2: Design of a big data toolkit

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2020年第3期32卷

作者： Kamburugamuve, Supun Govindarajan, Kannan Wickramasinghe, Pulasthi Abeykoon, Vibhatha Fox, Geoffrey Indiana Univ Sch Informat Comp & Engn Bloomington IN 47408 USA

Data-driven applications are essential to handle the ever-increasing volume, velocity, and veracity of data generated by sources such as the Web and Internet of Things (IoT) devices. Simultaneously, an event-driven computational paradigm is emerging as the core of modern systems designed for database queries, data analytics, and on-demand applications. Modern big data processing runtimes and asynchronous many task (AMT) systems from high performance computing (HPC) community have adopted dataflow event-driven model. The services are increasingly moving to an event-driven model in the form of Function as a Service (FaaS) to compose services. An event-driven runtime designed for data processing consists of well-understood components such as communication, scheduling, and fault tolerance. Different design choices adopted by these components determine the type of applications a system can support efficiently. We find that modern systems are limited to specific sets of applications because they have been designed with fixed choices that cannot be changed easily. In this paper, we present a loosely coupled component-based design of a big data toolkit where each component can have different implementations to support various applications. Such a polymorphic design would allow services and data analytics to be integrated seamlessly and expand from edge to cloud to HPC environments.

关键词： big data dataflow event-driven computing high performance computing

来源：评论

学校读者我要写书评

暂无评论

Digital Multiplier-Less Spiking Neural Network Architecture of Reinforcement Learning in a Context-Dependent Task

Digital Multiplier-Less Spiking Neural Network Architecture ...

引用

2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

来源：评论

学校读者我要写书评

暂无评论

Twister2: Design of a big data toolkit

Twister2: Design of a big data toolkit

引用

Workshop on Exascale MPI (ExaMPI) held in conjunction with International Conference for High Performance computing, Networking, Storage and Analysis (SC)

作者： Kamburugamuve, Supun Govindarajan, Kannan Wickramasinghe, Pulasthi Abeykoon, Vibhatha Fox, Geoffrey Indiana Univ Sch Informat Comp & Engn Bloomington IN 47408 USA

关键词： big data dataflow event-driven computing high performance computing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Production Serverless computing Environments 11

Evaluation of Production Serverless Computing Environments

引用

11th IEEE International Conference on Cloud computing (CLOUD) Part of the IEEE World Congress on Services

作者： Lee, Hyungro Satyam, Kumar Fox, Geoffrey C. Indiana Univ Sch Informat Comp & Engn Bloomington IN 47405 USA

ISBN: (纸本)9781538672358

Serverless computing provides a small runtime container to execute lines of codes without infrastructure management which is similar to Platform as a Service (PaaS) but a functional level. Amazon started the event-driven compute named Lambda functions in 2014 with a 25 concurrent limitation, but it now supports at least a thousand of concurrent invocation to process event messages generated by resources like databases, storage and system logs. Other providers, i.e., Google, Microsoft, and IBM offer a dynamic scaling manager to handle parallel requests of stateless functions in which additional containers are provisioning on new compute nodes for distribution. However, while functions are often developed for microservices and lightweight workload, they are associated with distributed data processing using the concurrent invocations. We claim that the current serverless computing environments can support dynamic applications in parallel when a partitioned task is executable on a small function instance. We present results of throughput, network bandwidth, a file I/O and compute performance regarding the concurrent invocations. We deployed a series of functions for distributed data processing to address the elasticity and then demonstrated the differences between serverless computing and virtual machines for cost efficiency and resource utilization.

关键词： FaaS Serverless event-driven computing Amazon Lambda Google Functions Microsoft Azure Functions IBM OpenWhisk

来源：评论

学校读者我要写书评

暂无评论

An Information System for Deciding and Acting ahead of Time in Sensing Enterprises 8

An Information System for Deciding and Acting ahead of Time ...

引用

8th International Conference on Information, Intelligence, Systems and Applications (IISA)

作者： Bousdekis, Alexandros Papageorgiou, Nikos Magoutas, Babis Apostolou, Dimitris Mentzas, Gregoris NTUA ICCS IMU Athens Greece Univ Piraeus Dept Informat Piraeus Greece

ISBN: (纸本)9781538637319

The evolution of Internet of Things (IoT) has significantly contributed to the development of the sensing enterprise concept and to the use of appropriate information systems for real-time processing of sensor data that are able to provide meaningful insights about potential problems in a proactive way. In the current paper, we outline a conceptual architecture and we describe the system design requirements for deciding and acting ahead of time with the aim to address the Decide and the Act phases of the "Detect-Predict-Decide-Act" proactive principle, which are still underexplored areas. The associated developed information system is capable of being integrated with systems addressing the Detect and the Predict phases in an event driven Architecture (EDA).

关键词： proactivity decision making event-driven computing context-awareness feedback sensing enterprise

来源：评论

学校读者我要写书评

暂无评论

event-driven Modeling for Context-Aware Information Systems 13

Event-Driven Modeling for Context-Aware Information Systems

引用

13th IEEE/ACS International Conference on Computer Systems and Applications (AICCSA)

作者： Aarab, Zineb Saidi, Rajaa Rahmani, Moulay Driss Mohammed V Univ Fac Sci LRIT Associated Unit CNRST URAC 29 BP 1014 Rabat Morocco INSEA Lab SI2M BP 6217 Rabat Morocco

ISBN: (纸本)9781509043200

In mobile computing developers will need to develop applications that will interact with the end user. Context-aware applications notify or ask users what they want based on what they have sensed or on a user profile. event-driven mobile computing detects conditions of interest to users and notifies them accordingly. In this paper we discuss the importance and challenges in designing event-driven applications through a comparison between some event-driven metamodels and propose an event metamodel to instantiate productive and comprehensible models.

关键词： event-driven computing event metamodel event-driven Architecture Model-driven Architecture Context modeling Entreprise Architecture Entreprise Modeling Context-Awareness

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：