A survey on efficient convolutional neural networks and hardware acceleration
Over the past decade, deep-learning-based representations have demonstrated remarkable
performance in academia and industry. The learning capability of convolutional neural …
performance in academia and industry. The learning capability of convolutional neural …
Tensor networks meet neural networks: A survey and future perspectives
Tensor networks (TNs) and neural networks (NNs) are two fundamental data modeling
approaches. TNs were introduced to solve the curse of dimensionality in large-scale tensors …
approaches. TNs were introduced to solve the curse of dimensionality in large-scale tensors …
Objective-hierarchy based large-scale evolutionary algorithm for improving joint sparsity-compression of neural network
Q Wang, Q Zhang, F Meng, B Li - Information Sciences, 2023 - Elsevier
Network training error and sparsity are two critical factors in optimizing the model
parameters of existing neuro-evolution algorithms. Alleviating the curse of dimensionality in …
parameters of existing neuro-evolution algorithms. Alleviating the curse of dimensionality in …
EL-Rec: Efficient large-scale recommendation model training via tensor-train embedding table
Deep learning Recommendation Models (DLRMs) plays an important role in various
application domains. However, existing DLRM training systems require a large number of …
application domains. However, existing DLRM training systems require a large number of …
TQCompressor: improving tensor decomposition methods in neural networks via permutations
V Abronin, A Naumov, D Mazur, D Bystrov… - arXiv preprint arXiv …, 2024 - arxiv.org
We introduce TQCompressor, a novel method for neural network model compression with
improved tensor decompositions. We explore the challenges posed by the computational …
improved tensor decompositions. We explore the challenges posed by the computational …
eSSpMV: An embedded-FPGA-based hardware accelerator for symmetric sparse matrix-vector multiplication
Symmetric Sparse Matrix-Vector Multiplication (SSpMV) is a prevalent operation in
numerous application domains (eg, physical simulations, machine learning, and graph …
numerous application domains (eg, physical simulations, machine learning, and graph …