51 Hits in 2.8 sec

A hybrid DBNS processor for DSP computation

G.A. Jullien, V.S. Dimitrov, B. Li, W.C. Miller, A. Lee, M. Ahmadi
ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349)  
The modification proposed in this paper, targeted to DSP inner product computations, uses a single digit representation for the coefficient vector and a 2-digit representation for the data vector.  ...  This paper introduces a modification to an index calculus representation for the Double-Base Number System (DBNS).  ...  A HYBRID 2-DIGIT PROCESSOR A diagram of the hybrid processor is shown in Figure 6 .  ... 
doi:10.1109/iscas.1999.777792 dblp:conf/iscas/JullienDLMLA99 fatcat:6qm5npmhlfcjdntzzzf4j7xsgm

Comparative Study and Analysis of Performances among RNS, DBNS, TBNS and MNS for DSP Applications

Rakhi Roy, Debanjana Datta, Somnath Bhagat, Sangita Saha, Amitabha Sinha
2015 Journal of Signal and Information Processing  
System (TBNS) and Mixed Number System (MNS) for DSP applications.  ...  This paper presents a comparative study of the performances of arithmetic units, based on different number systems like Residue Number System (RNS), Double Base Number System (DBNS), Triple Base Number  ...  For real time applications and DSP related problems fast arithmetic units particularly adders and multipliers are required for enhanced performance of the processors.  ... 
doi:10.4236/jsip.2015.62005 fatcat:4ecql6qofzgtlonqy64mxexqzu

Embedded Mission Decision-Making based on Dynamic Decision Networks in SoPC Platform

Hanen Chenini
2019 International Journal of Advanced Computer Science and Applications  
The proposed approach is then validated with a practical case UAV mission planning using the proposed dynamic decision-maker implemented on embedded system based on a hybrid device.  ...  After proposing a DBN model, a probabilistic approach based on Multiple-Criteria Decision-Making (MCDM) is then applied to find the best configuration reaching a balance between performance and energy  ...  Digital signal processors (DSP) or FPGAs are used for hardware implementation of such real-time systems.  ... 
doi:10.14569/ijacsa.2019.0101287 fatcat:zqg3wnaun5fubgsy3nkcrz6u4m

Wireless Channel Scene Recognition Method Based on an Autocorrelation Function and Deep Learning

Shuguang Ning, Yigang He, Lifen Yuan, Yuan Huang, Shudong Wang, Tongtong Cheng, Yongbo Sui
2020 IEEE Access  
The tested wireless channel data were imported into the computer processor to verify the recognition effect of the proposed method.  ...  Following a similar derivation, the DSP can be theoretically obtained for other kinds for Rayleigh time-varying channels.  ... 
doi:10.1109/access.2020.3044167 fatcat:uwik7iub5bbkbeqxdlqfijvvk4

Hardware implementation of spiking neural networks on FPGA

Jianhui Han, Zhaolin Li, Weimin Zheng, Youhui Zhang
2020 Tsinghua Science and Technology  
It features a hybrid updating algorithm, which combines the advantages of existing algorithms to simplify hardware design and improve performance.  ...  His current research interests include embedded systems, parallel computing, multicore design, and system-on-achip. Weimin Zheng received the MS degree  ...  Acknowledgment This work was supported in part by the Beijing Innovation Center for Future Chip, Tsinghua University, in part by the Science and Technology Innovation Special Zone project, China, and in  ... 
doi:10.26599/tst.2019.9010019 fatcat:daag6qtcrfh2xklrtbj3nxlmda

Robustness of hardware-oriented restricted Boltzmann machines in deep belief networks for reliable processing

Kodai Ueyoshi, Takao Marukame, Tetsuya Asai, Masato Motomura, Alexandre Schmid
2016 Nonlinear Theory and Its Applications IEICE  
RBMs used in deep belief networks (DBNs) demonstrate robustness against memory errors during and after learning.  ...  Fine-tuning has a significant impact on the recovery of accuracy under the presence of static errors that may modify structural data of RBMs.  ...  Muraoka of Toshiba Corporation for their invaluable support and suggestions.  ... 
doi:10.1587/nolta.7.395 fatcat:hde3rpci2fbdlpczgahdrh7fze

Eye State Identification Utilizing EEG Signals: A Combined Method Using Self-Organizing Map and Deep Belief Network

Neda Ahmadi, Mehrbakhsh Nilashi, Behrouz Minaei-Bidgoli, Murtaza Farooque, Sarminah Samad, Nojood O. Aljehane, Waleed Abdu Zogaan, Hossein Ahmadi, Sheng Bin
2022 Scientific Programming  
This paper accordingly proposes a new method for EEG signal analysis through Self-Organizing Map (SOM) clustering and Deep Belief Network (DBN) approaches to efficiently improve the computation and accuracy  ...  The method is developed using SOM clustering and DBN, which is a deep layer neural network with multiple layers of Restricted Boltzmann Machines (RBMs).  ...  In fact, a hybrid intelligent method is developed through Self-Organizing Map (SOM) clustering and Deep Belief Network (DBN) approaches.  ... 
doi:10.1155/2022/4439189 fatcat:3hvwxfryzzaftjz4ap6zip7u2q

Speech recognition using deep neural network - recent trends

Mousmita Sarma
2017 International Journal of Intelligent Systems Design and Computing  
She serves as a reviewer to several journals and IEEE international and national conferences. Her areas of interest include speech recognition, soft-computation and HCI applications.  ...  ANNs with deep learning which uses a generative, layer by-layer pre-training method for initialising the weights has provided best solution for acoustic modelling for speech recognition.  ...  The use of a 'bottleneck' in the last layer of the BP-DBN proved to help avoid over fitting while hybrid generative and discriminative training prevent over fitting in the AM-DBN.  ... 
doi:10.1504/ijisdc.2017.082853 fatcat:74c7x6rognayjpbuverpumox54

A Review on Driver Face Monitoring Systems for Fatigue and Distraction Detection

Mohamad-Hoseyn Sigari, Muhammad-Reza Pourshahabi, Mohsen Soryani, Mahmood Fathy
2014 International Journal of Advanced Science and Technology  
Although a precise definition for fatigue is not presented yet, but there is a relation between the fatigue/drowsiness and body temperature, electrical skin resistance, eye movement, breathing rate, heart  ...  A precise and scientific definition for fatigue has not been presented yet; therefore, there is not any quantitative criterion to measure it.  ...  DSP and FPGA are flexible to programming via software and hardware respectively. Therefore, in the driver face monitoring systems, DSP or FPGA is often used as processor.  ... 
doi:10.14257/ijast.2014.64.07 fatcat:wqzph4nohrcifgh4lknbsqov4y

From DNNs to GANs: Review of efficient hardware architectures for deep learning [article]

Gaurab Bhattacharya
2021 arXiv   pre-print
Similarly, different algorithms have been adapted to design a DSP processor compatible for fast performance in neural network, activation function, convolutional neural network and generative adversarial  ...  Presently available DSP processors are incapable of performing these operations and they mostly face the problems, for example, memory overhead, performance drop and compromised accuracy.  ...  This paper primarily focused on DBN, hence for activation function, a novel tanh design is proposed using finite-state-machine.  ... 
arXiv:2107.00092v1 fatcat:i6kijx7pavdajeskn4lip7gnhe

Harmonic Detection Technology for Power Grids Based on Adaptive Ensemble Empirical Mode Decomposition

Jianming Shi, Zhongmin Liu
2021 IEEE Access  
For such cases, the development of deep neural networks has provided a new solution for harmonic detection.  ...  Ensemble empirical mode decomposition (EEMD) provides a new approach for harmonic detection in power systems.  ...  Then, an adaptive deep neural network model based on a deep belief network (DBN) structure with a backpropagation (BP) layer (DBN-BP) can be trained and used to set the white noise parameters for EEMD  ... 
doi:10.1109/access.2021.3055553 fatcat:ldfnhgffrve35fw3v3ltv2imha

Accelerating Deep Neural Networks implementation: A survey

Meriam Dhouibi, Ahmed Karim Ben Salem, Afef Saidi, Slim Ben Saoud
2021 IET Computers & Digital Techniques  
Deploying such Deep Neural Networks (DNN) on embedded devices is still a challenging task considering the massive requirement of computation and storage.  ...  Field Programmable Gate Arrays (FPGAs) are promising platforms for the deployment of large-scale DNN which seek to reach a balance between the above objectives.  ...  Whole systems can be integrated on a chip using many hardware components such as memories, fast devices, DSP units and processor cores which expedite the design of such large-scale systems.  ... 
doi:10.1049/cdt2.12016 fatcat:3kl4j5ztl5eahmgv7vetu2egay

A new binary arithmetic for finite-word-length linear controllers: MEMS applications

A. K. Oudjida, A. Liacha, M. L. Berrandjia, N. Chaillet
2014 2014 9th International Design and Test Symposium (IDT)  
The CSE problem of disappearing patterns due to colliding digits DMAC Double Multiply-And-Accumulate DSP Digital-Signal-Processor/Processing FF Flip-Flop FPGA Field Programmable Gate Array FPR Fixed-Point  ...  Analog Converter DAG Directed Acyclic Graphs, a framework for solving SCM and MCM DBNS Double Base Number System, an existing number representation system DFS Dynamic Frequency Scaling Digit Clashing  ...  general-purpose-processor or a DSP.  ... 
doi:10.1109/idt.2014.7038608 dblp:conf/idt/OudjidaLBC14 fatcat:ykr7hhrd7ndy5jbmu53hb3t7vm

Semantics Interaction Control for Constructing Intelligent Ecology of Internet of Things and Critical Component Research

Haijun Zhang, Yinghui Chen
2018 Journal of Computer and Communications  
For this purpose, in this paper, first, we present a type of novel intelligent deep hybrid neural network algorithm based on a deep bidirectional recurrent neural network integrated with a deep backward  ...  Intelligent equipment is a kind of device that is characterized by intelligent sensor interconnections, big data processing, new types of displays, human-machine interaction and so on for the new generation  ...  The popular system architecture includes the embedded microprocessor unit (EMP), the embedded micro controller unit (MCU), embedded digital signal processors (DSP), embedded systems on chip (SOC) and so  ... 
doi:10.4236/jcc.2018.611003 fatcat:ryq5moawtjg3pm4pkvfjd4xmze

CNNLab: a Novel Parallel Framework for Neural Networks using GPU and FPGA-a Practical Study with Trade-off Analysis [article]

Maohua Zhu, Liu Liu, Chao Wang, Yuan Xie
2016 arXiv   pre-print
Experimental results on the state-of-the-art Nvidia K40 GPU and Altera DE5 FPGA board demonstrate that the CNNLab can provide a universal framework with efficient support for diverse applications without  ...  However, the diversity and large-scale data size have posed a significant challenge to construct a flexible and high-performance implementation of deep learning neural networks.  ...  CNNLab maps the applications into computing kernels using CUDA and OpenCL programming interfaces. • CNNLab is based on a heterogeneous hybrid system which includes the software processor, GPU accelerator  ... 
arXiv:1606.06234v1 fatcat:en7acoahonb7beqrnxv553g46e
« Previous Showing results 1 — 15 out of 51 results