Neural network pruning based on channel attention mechanism
Sign Up to like & getrecommendations! Published in 2022 at "Connection Science"
DOI: 10.1080/09540091.2022.2111405
Abstract: Network pruning facilitates the deployment of convolutional neural networks in resource-limited environments by reducing redundant parameters. However, most of the existing methods ignore the differences in the contributions of the output feature maps. In response… read more here.
Keywords: network pruning; attention mechanism; channel attention;
Crossbar-Aware Neural Network Pruning
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Access"
DOI: 10.1109/access.2018.2874823
Abstract: Crossbar architecture has been widely adopted in neural network accelerators due to the efficient implementations on vector-matrix multiplication operations. However, in the case of convolutional neural networks (CNNs), the efficiency is compromised dramatically because of… read more here.
Keywords: network; network pruning; aware neural; neural network ... See more keywords
Bearing Remaining Useful Life Prediction Using Federated Learning With Taylor-Expansion Network Pruning
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Instrumentation and Measurement"
DOI: 10.1109/tim.2023.3264027
Abstract: Accurate prediction of bearing remaining useful life (RUL) is essential for machine health management. In existing data-driven prognostic methods, centralized data resources and deep neural networks (DNNs) are two requisites. However, conventional data aggregation may… read more here.
Keywords: taylor expansion; network; prediction; network pruning ... See more keywords
SOKS: Automatic Searching of the Optimal Kernel Shapes for Stripe-Wise Network Pruning.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3162067
Abstract: In spite of the remarkable performance, deep convolutional neural networks (CNNs) are typically over-parameterized and computationally expensive. Network pruning has become a popular approach to reducing the storage and calculations of CNN models, which commonly… read more here.
Keywords: kernel shapes; network pruning; searching optimal; optimal kernel ... See more keywords
Discrimination-aware Network Pruning for Deep Model Compression
Sign Up to like & getrecommendations! Published in 2021 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2021.3066410
Abstract: We study network pruning which aims to remove redundant channels/kernels and accelerate the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature… read more here.
Keywords: discriminative power; model; network pruning; discrimination aware ... See more keywords
Adaptive Search-and-Training for Robust and Efficient Network Pruning.
Sign Up to like & getrecommendations! Published in 2023 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.1109/tpami.2023.3248612
Abstract: Both network pruning and neural architecture search (NAS) can be interpreted as techniques to automate the design and optimization of artificial neural networks. In this paper, we challenge the conventional wisdom of training before pruning… read more here.
Keywords: network; network pruning; search training; search ... See more keywords