Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in n...
详细信息
ISBN:
(数字)9781728169262
ISBN:
(纸本)9781728169262
Unsupervised learning of hierarchical representations has been one of the most vibrant research directions in deep learning during recent years. In this work we study biologically inspired unsupervised strategies in neural networks based on local Hebbian learning. We propose new mechanisms to extend the Bayesian Confidence Propagating Neural Network (BCPNN) architecture, and demonstrate their capability for unsupervised learning of salient hidden representations when tested on the MNIST dataset.
This paper presents a detection method of electricity theft based on SOM neural network and K-means clustering algorithm. This method combines the advantages of SOM neural network which can automatically classify and ...
详细信息
Theemergence of cloud computing technology has changed the traditional business economic model and provided convenience for the application of e-commerce in the financial field. This paper uses cloud computing as the...
详细信息
In order to solve the problem of information leakage when employees of power companies access the power system through mobile terminals, this paper proposes the identity authentication mechanism of power mobile termin...
详细信息
2.5D chiplet technology is gaining popularity for theefficiency of integrating multiple heterogeneous dies or chiplets on interposers, and it is also considered an ideal option for agile silicon system design by mitiga...
详细信息
2.5D chiplet technology is gaining popularity for theefficiency of integrating multiple heterogeneous dies or chiplets on interposers, and it is also considered an ideal option for agile silicon system design by mitigating the huge design, verification, and manufacturing overhead of monolithic SoCs. Although it significantly reduces development costs by chiplet reuse, the design and fabrication of interposers also introduce additional high non-recurring engineering (NRe) costs and development cycles which might be prohibitive for application-specific designs having low *** address this challenge, in this paper, we propose a reusable general interposer architecture (GIA) to amortize NRe costs and accelerate integration flows of interposers across different chiplet-based systems effectively. The proposed assembly-time configurable interposer architecture covers both active interposers and passive interposers considering diverse applications of 2.5D systems. The agile interposer integration is also facilitated by a novel end-to-end design automation framework to generate optimal system assembly configurations including the selection of chiplets, inter-chiplet network configuration, placement of chiplets, and mapping on GIA, which are specialized for the given target workload. Theexperimental results show that our proposed active GIA and passive GIA achieve 3.15x and 60.92x performance boost with 2.57x and 2.99x power saving over baselines respectively.
In view of the cumbersome, time-consuming., inefficient, resource-consuming and costly signing process of traditional paper contracts, the paper analyzes the design principles and designs relevant architectures for el...
详细信息
With the development and popularization of power Internet of Things (IoT), IoT produces a large number of distributed data, theelectronic text data and the concurrency of multiple services. To support unified managem...
详细信息
Internet of things is one of the rapidly growing innovations in the field of telecommunication. The main purpose of the correspondence and collaboration among things, mans and objects is to fulfill the objective set t...
详细信息
This paper presents a brief overview of the remote real time monitoring system of the smart micro grid at Dayalbagh educational Institute. Various components of smart micro grid i.e., battery, inverter etc., are smart...
详细信息
The proceedings contain 10 papers. The topics discussed include: adaptive and personalized e/M-learning : approaches and techniques;an OFDMA MAC protocol aggregating variable length data in the next ieee 802.11ax stan...
The proceedings contain 10 papers. The topics discussed include: adaptive and personalized e/M-learning : approaches and techniques;an OFDMA MAC protocol aggregating variable length data in the next ieee 802.11ax standard;stacked sparse autoencoder for unsupervised features learning in PanCancer miRNA cancer classification;simulation study of video transmission by optical fiber;training feedforward neural networks using hybrid particle swarm optimization, multi-verse optimization;shot boundary detection: fundamental concepts and survey;a hybrid chemical reaction optimization algorithm for solving the DNA fragment assembly problem;a novel Arabic handwriting recognition system based on image matching technique;and job migration for load balancing algorithm in gridcomputing using queue length parameter.
暂无评论