DEMN
发表于 2025-3-23 10:15:38
The Implementation and Optimization of Matrix Decomposition Based Collaborative Filtering Task on X8from the big dataset in daily lives. Collaborative filtering is a popular technology often used in recommendation systems, which recommend items to users according to other users having the similar behaviors with the target user or according to the items having the alike properties with the target i
epidermis
发表于 2025-3-23 16:32:12
An Efficient Implementation of the ALS-WR Algorithm on x86 CPUsvies, games, online shopping, and so on, to solve information redundancy and effectively to recommend interesting products for users. In this paper, we implement and accelerate the Alternating-Least-Squares with Weighted-.-Regularization (ALS-WR) by adopting a two-level parallel strategies on the x8
nonchalance
发表于 2025-3-23 19:34:00
Accelerating Parallel ALS for Collaborative Filtering on Hadoopsed in CF models to calculate the latent factor matrix factorization. Parallel ALS on Hadoop is widely used in the era of big data. However, existing work on the computational efficiency of parallel ALS on Hadoop have two defects. One is the imbalance of data distribution, the other is lacking the f
羽饰
发表于 2025-3-23 22:23:34
Improving RGB-D Face Recognition via Transfer Learning from a Pretrained 2D Networktive to variations in poses, facial expressions and illuminations. Depth images provide valuable information to help model facial boundaries and understand the global facial layout and provide low frequency patterns. Intuitively, RGB-D images are more robust to external environments than RGB images.
Prostatism
发表于 2025-3-24 03:21:49
http://reply.papertrans.cn/19/1834/183393/183393_15.png
unstable-angina
发表于 2025-3-24 06:36:45
http://reply.papertrans.cn/19/1834/183393/183393_16.png
neolith
发表于 2025-3-24 13:03:25
http://reply.papertrans.cn/19/1834/183393/183393_17.png
Inflamed
发表于 2025-3-24 16:47:37
RVTensor: A Light-Weight Neural Network Inference Framework Based on the RISC-V Architecturepose RVTensor that a light-weight neural network inference framework based on the RISC-V architecture. RVTensor is based on the SERVE.r platform and is optimized for resource-poor scenarios. Our experiments demonstrate that the accuracy of RVTensor and the Keras is the same.
招惹
发表于 2025-3-24 19:03:10
http://reply.papertrans.cn/19/1834/183393/183393_19.png
停止偿付
发表于 2025-3-24 23:30:15
0302-9743 IBench; AI Challenges on X86 using AIBench; AI Challenges on 3D Face Recognition using AIBench; Benchmark; AI and Edge; Big Data; Datacenter; Performance Analysis; Scientific Computing..978-3-030-49555-8978-3-030-49556-5Series ISSN 0302-9743 Series E-ISSN 1611-3349