1,721,032 research outputs found
MemTorch: a simulation framework for deep memristive cross-bar architectures
No full textMemristive devices arranged in cross-bar architectures have shown great promise to facilitate the acceleration and improve the power efficiency of Deep Learning (DL) systems for deployment in resource-constrained platforms, such as the Internet-of-Things (IoT) edge devices. These cross-bar architectures can be used to implement various in-memory computing operations, such as Multiply-Accumulate (MAC) and convolution, which are used extensively in Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs). Currently, there is a lack of an open source, general, high-level simulation platform that can fully integrate any behavioral or experimental memristive device model into cross-bar architectures. This paper presents such a framework named MemTorch, which integrates directly with the well-known PyTorch Machine Learning (ML) library. To demonstrate an example practical use of MemTorch, we use it to simulate the performance degradation that non-ideal devices introduce to a typical Memristive DNN (MDNN) implementing VGG-16 for CIFAR-10. Our open source 1 MemTorch framework can be used by circuit and system designers to conveniently build customized large-scale simulation platforms, as a preliminary step before circuit-level realization
Live demonstration: Low-Power and High-Speed Deep FPGA Inference Engines for weed classification at the edge
No full textIn Low-Power and High-Speed Deep FPGA Inference Engines for Weed Classification at the Edge [1] we implemented GPU- and FPGA-accelerated deterministically binarized Deep Neural Networks (DNNs), tailored toward weed species classification for robotic weed control. The dataset used consisted of 17,508 unique 256×256 color images in 9 classes, collected in situ from eight rangeland areas across Northern Australia [2]. For this live demonstration, we have designed a weed classification game. We first provide the visitor with a printed sheet showing several examples of each of the 9 various weed species classes in our dataset, to learn and memorize the weed names. This learning process can take for as long as the visitor wishes. For the game to start, five weed images from our test set are randomly selected. We then measure the interference times and accuracies for our optimized GPUand FPGA-accelerated binarized DNNs, alongside the visitors' performance. Are low-resolution, low-power, binarized DNNs able to outperform humans at categorizing weed species
Evolutionary Optimization of Neuromorphic Architecture for Low-power Cerebellum Prosthetic Instrumentation and Device in Biomedical Systems
No full textNeuromorphic computing is a new generation of technique, which has been used in the neuroprosthetic implementation in biomedical applications. The spike-based computing mechanism enables it with low power consumption and real-time speed. However, there is a lack of optimization strategy for neuromorphic architecture of neuroprosthetic. In this paper, a novel optimization strategy for neuromorphic architecture of neuroprosthetic, named the Evolutionary Neuromorphic Optimization Framework (ENOF), is presented. A HEMA algorithm is proposed for the implementation of ENOF. It can continuously find the optimal mapping scheme and achieve better accuracy by jumping out of local optimization. Experimental results show that the proposed method can cut down the energy consumption and have better stability. Better optimization can be achieved along with the NoC scale increasing. The proposed work is meaningful for the low-power prosthetic instrumentation and device of biomedical systems, and can be applied in healthcare or clinical situations
SOMeL: Multi-Granular Optimized Framework for Digital Neuromorphic Meta-Learning
No full textNeuromorphic computing has shown significant promises toward artificial intelligence achieved through event-driven spiking neural network (SNN) architectures. However, online meta-learning in neuromorphic systems is yet to be fully achieved. This study presents SOMeL (spike-driven online meta learning), a novel multi-granular optimized framework for meta-learning implemented on a digital neuromorphic architecture. We investigate the powerful meta-learning capability of SOMeL by applying it to a challenging task of autonomous navigation. We further explore the meta-learning learning performance of SOMeL. Besides, we draw detailed comparisons to state-of-the-art digital neuromorphic hardware to demonstrate stronger scalability, higher throughput and lower latency of SOMeL. SOMeL can facilitate emulating and studying neural mechanisms underlying spiking network dynamics in neuroscience research. It can also be applied in realtime meta-learning and navigation applications, circuits and embedded systems for instrumentation and measurement. SOMeL has a promising application prospect for fast adaptive calibration of instrument measurements, which enables instruments to adapt well to changing measurement environments and tasks, and improve their measurement performance in new environments
Sea surface temperature forecasting with ensemble of stacked deep neural networks
No full textOceanic temperature has a great impact on global climate and worldwide ecosystems, as its anomalies have been shown to have a direct impact on atmospheric anomalies. The major parameter for measuring the thermal energy of oceans is the sea surface temperature (SST). SST prediction plays an essential role in climatology and ocean-related studies. However, SST prediction is challenging due to the involvement of complex and nonlinear sea thermodynamic factors. To address this challenge, we design a novel ensemble of two stacked deep neural networks (DNNs) that uses air temperature, in addition to water temperature, to improve the SST prediction accuracy. To train our model and compare its accuracy with the state-of-the-art, we employ two well-known datasets from the national oceanic and atmospheric administration as well as the international Argo project. Using DNNs, our proposed method is capable of automatically extracting required features from the input time series and utilizing them internally to provide a highly accurate SST prediction that outperforms state-of-the-art models
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe 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
Variations on the Author
Full text link“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
Full text linkWe 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
Full text linkWe 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
- …
