1,721,172 research outputs found
Neuromorphic design using reward-based STDP learning on event-based reconfigurable cluster architecture
No full textNeuromorphic computing systems simulate spiking neural networks that are used for research into how biological neural networks function, as well as for applied engineering such as robotics, pattern recognition, and machine learning. In this paper, we present a neuromorphic system based on an asynchronous event-based hardware platform. We represent three algorithms for implementing spiking networks on our asynchronous hardware platform. We also discuss different trade-offs between synchronisation and messaging costs. A reinforcement learning method known as Reward-modulated STDP is presented as an online learning algorithm in the network. We evaluate the system performance in a single box of our designed architecture using 6000 concurrent hardware threads and demonstrate scaling to networks with up to 2 million neurons and 400 million synapses. The performance of our architecture is also compared to existing neuromorphic platforms, showing a 20 times speed-up over the Brian simulator on an x86 machine, and a 16 times speed-up over a 48-chip SpiNNaker node
Exploring performance enhancement of event-driven processor networks
No full textEvent-driven processor networks have been proposed as an effective way of exploiting recent advances in field-programmable technology. This paper explores an approach to enhancing the performance of event-driven processor networks for specific applications: Attaching to the processor network accelerators with custom-designed logic. We present a design flow of this approach, and apply the flow to a heatplate application.</p
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Accelerating Large-Scale Graph Processing with FPGAs Lesson Learned and Future Directions
Get PDFProcessing graphs on a large scale presents a range of difficulties, including irregular memory access
patterns, device memory limitations, and the need for effective partitioning in distributed systems,
all of which can lead to performance problems on traditional architectures such as CPUs and
GPUs. To address these challenges, recent research emphasizes the use of Field-Programmable Gate
Arrays (FPGAs) within distributed frameworks, harnessing the power of FPGAs in a distributed
environment for accelerated graph processing. This paper examines the effectiveness of a multi-FPGA
distributed architecture in combination with a partitioning system to improve data locality and
reduce inter-partition communication. Utilizing Hadoop at a higher level, the framework maps the
graph to the hardware, efficiently distributing pre-processed data to FPGAs. The FPGA processing
engine, integrated into a cluster framework, optimizes data transfers, using offline partitioning for
large-scale graph distribution. A first evaluation of the framework is based on the popular PageRank
algorithm, which assigns a value to each node in a graph based on its importance. In the realm of
large-scale graphs, the single FPGA solution outperformed the GPU solution that were restricted
by memory capacity and surpassing CPU speedup by 26x compared to 12x. Moreover, when a
single FPGA device was limited due to the size of the graph, our performance model showed that a
distributed system with multiple FPGAs could increase performance by around 12x. This highlights
the effectiveness of our solution for handling large datasets that surpass on-chip memory restrictions
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
Tools for efficient Deep Learning
Get PDFIn the era of Deep Learning (DL), there is a fast-growing demand for building and deploying Deep Neural Networks (DNNs) on various platforms. This thesis proposes five tools to address the challenges for designing DNNs that are efficient in time, in resources and in power consumption.
We first present Aegis and SPGC to address the challenges in improving the memory efficiency of DL training and inference. Aegis makes mixed precision training (MPT) stabler by layer-wise gradient scaling. Empirical experiments show that Aegis can improve MPT accuracy by at most 4\%. SPGC focuses on structured pruning: replacing standard convolution with group convolution (GConv) to avoid irregular sparsity. SPGC formulates GConv pruning as a channel permutation problem and proposes a novel heuristic polynomial-time algorithm. Common DNNs pruned by SPGC have maximally 1\% higher accuracy than prior work.
This thesis also addresses the challenges lying in the gap between DNN descriptions and executables by Polygeist for software and POLSCA for hardware. Many novel techniques, e.g. statement splitting and memory partitioning, are explored and used to expand polyhedral optimisation. Polygeist can speed up software execution in sequential and parallel by 2.53 and 9.47 times on Polybench/C. POLSCA achieves 1.5 times speedup over hardware designs directly generated from high-level synthesis on Polybench/C.
Moreover, this thesis presents Deacon, a framework that generates FPGA-based DNN accelerators of streaming architectures with advanced pipelining techniques to address the challenges from heterogeneous convolution and residual connections. Deacon provides fine-grained pipelining, graph-level optimisation, and heuristic exploration by graph colouring. Compared with prior designs, Deacon shows resource/power consumption efficiency improvement of 1.2x/3.5x for MobileNets and 1.0x/2.8x for SqueezeNets.
All these tools are open source, some of which have already gained public engagement. We believe they can make efficient deep learning applications easier to build and deploy.Open Acces
- …
