Results 41 to 50 of about 22,594 (260)
Importance Estimation for Neural Network Pruning [PDF]
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019 Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores.
Pavlo Molchanov 0001 +4 more
openaire +2 more sources
IEEE Access, 2023 Train Operators can improve railway passengers’ service quality and traffic management by accurately predicting travel arrangements and delays. Precise prediction of train delays is vital for creating feasible scheduled timetables.
Veronica A. Boateng, Bo Yang
doaj +1 more source
Image Super-Resolution Reconstruction Algorithm Based on Sparse Neural Network [PDF]
Jisuanji gongcheng, 2022 Many deep learning-based image super-resolution reconstruction algorithms improve the overall feature expression ability of a network by extending the depth of the network.However, excessively extending the depth of the network causes the model to be ...
LI Haomin, LI Guangping
doaj +1 more source
Ps and Qs: Quantization-Aware Pruning for Efficient Low Latency Neural Network Inference
Frontiers in Artificial Intelligence, 2021 Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption.
Benjamin Hawks +6 more
doaj +1 more source
Renormalized Sparse Neural Network Pruning
CoRR, 2022 Large neural networks are heavily over-parameterized. This is done because it improves training to optimality. However once the network is trained, this means many parameters can be zeroed, or pruned, leaving an equivalent sparse neural network. We propose renormalizing sparse neural networks in order to improve accuracy.
openaire +2 more sources
Combine-Net: An Improved Filter Pruning Algorithm
Information, 2021 The powerful performance of deep learning is evident to all. With the deepening of research, neural networks have become more complex and not easily generalized to resource-constrained devices.
Jinghan Wang, Guangyue Li, Wenzhao Zhang
doaj +1 more source
Neural Network Pruning by Gradient Descent
CoRR, 2023 21 pages, 5 ...
Zhang Zhang, Ruyi Tao, Jiang Zhang
openaire +2 more sources
Partition Pruning: Parallelization-Aware Pruning for Dense Neural Networks [PDF]
2020 28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), 2020 Parameters of recent neural networks require a huge amount of memory. These parameters are used by neural networks to perform machine learning tasks when processing inputs. To speed up inference, we develop Partition Pruning, an innovative scheme to reduce the parameters used while taking into consideration parallelization. We evaluated the performance
Shahhosseini, Sina +3 more
openaire +4 more sources
Leaftronics: Bio‐Fractal Scaffolds From Leaf Venation for Low‐Waste Electronics
Advanced Materials, EarlyView.“Leaftronics” transforms naturally evolved leaf venation into quasi‐fractal scaffolds for sustainable electronics. Polymer‐infiltrated leaf skeletons can be used to fabricate ultra‐smooth, reflow‐ and thin‐film‐compatible decomposable substrates, while making the same lignocellulose networks conducting results in flexible transparent electrodes.
Rakesh Rajendran Nair +3 more
wiley +1 more source
Neural Networks at a Fraction with Pruned Quaternions
Proceedings of the 6th Joint International Conference on Data Science & Management of Data (10th ACM IKDD CODS and 28th COMAD), 2023 Contemporary state-of-the-art neural networks have increasingly large numbers of parameters, which prevents their deployment on devices with limited computational power. Pruning is one technique to remove unnecessary weights and reduce resource requirements for training and inference. In addition, for ML tasks where the input data is multi-dimensional,
Sahel Mohammad Iqbal, Subhankar Mishra
openaire +2 more sources