Zobrazeno 1 - 10
of 151
pro vyhledávání: '"B.2.4"'
Attention mechanisms are becoming increasingly popular, being used in neural network models in multiple domains such as natural language processing (NLP) and vision applications, especially at the edge. However, attention layers are difficult to map
Externí odkaz:
http://arxiv.org/abs/2405.04206
Autor:
Gu, Yu, Huang, Puyang, Chen, Tianhao, Fu, Chenyi, Chen, Aitian, Peng, Shouzhong, Zhang, Xixiang, Kou, Xufeng
We report a spin-orbit torque(SOT) magnetoresistive random-access memory(MRAM)-based probabilistic binary neural network(PBNN) for resource-saving and hardware noise-tolerant computing applications. With the presence of thermal fluctuation, the non-d
Externí odkaz:
http://arxiv.org/abs/2403.19374
Autor:
Perez, Sergio P., Zhang, Yan, Briggs, James, Blake, Charlie, Levy-Kramer, Josh, Balanca, Paul, Luschi, Carlo, Barlow, Stephen, Fitzgibbon, Andrew William
FP8 formats are gaining popularity to boost the computational efficiency for training and inference of large deep learning models. Their main challenge is that a careful choice of scaling is needed to prevent degradation due to the reduced dynamic ra
Externí odkaz:
http://arxiv.org/abs/2309.17224
The rising usage of AI and ML-based processing across application domains has exacerbated the need for low-cost ML implementation, specifically for resource-constrained embedded systems. To this end, approximate computing, an approach that explores t
Externí odkaz:
http://arxiv.org/abs/2309.12830
Autor:
Guo, Wenbo
Fast binary compressors are the main components of many basic digital calculation units. In this paper, a high-speed (7,2) compressor with a fast carry-generation logic is proposed. The carry-generation logic is based on the sorting network, and it c
Externí odkaz:
http://arxiv.org/abs/2309.03643
We propose Dual-Feedback Generalized Proximal Gradient Descent (DFGPGD) as a new, hardware-friendly, operator splitting algorithm. We then establish convergence guarantees under approximate computational errors and we derive theoretical criteria for
Externí odkaz:
http://arxiv.org/abs/2306.16935
Autor:
Chang, Yangyang, Sobelman, Gerald E.
Publikováno v:
Electrical and Electronics Engineering: An International Journal (ELELIJ), Vol.12, No.1, February 2023
Quantization using a small number of bits shows promise for reducing latency and memory usage in deep neural networks. However, most quantization methods cannot readily handle complicated functions such as exponential and square root, and prior appro
Externí odkaz:
http://arxiv.org/abs/2303.13601
Autor:
Sosnovski, Bianca
We establish a connection between semi-primitive roots of the multiplicative group of integers modulo $2^{k}$ where $k\geq 3$, and the logarithmic base in the algorithm introduced by Fit-Florea and Matula (2004) for computing the discrete logarithm m
Externí odkaz:
http://arxiv.org/abs/2211.09163
Autor:
Ma, Jingxiao, Reda, Sherief
Approximate computing is an emerging computing paradigm that offers improved power consumption by relaxing the requirement for full accuracy. Since real-world applications may have different requirements for design accuracy, one trend of approximate
Externí odkaz:
http://arxiv.org/abs/2207.00459
In this paper, we propose ThundeRiNG, a resource-efficient and high-throughput system for generating multiple independent sequences of random numbers (MISRN) on FPGAs. Generating MISRN can be a time-consuming step in many applications such as numeric
Externí odkaz:
http://arxiv.org/abs/2105.09578