Results 21 to 30 of about 79,498 (272)

Neural Network Pruning by Cooperative Coevolution

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022
Neural network pruning is a popular model compression method which can significantly reduce the computing cost with negligible loss of accuracy. Recently, filters are often pruned directly by designing proper criteria or using auxiliary modules to measure their importance, which, however, requires expertise and trial-and-error.
Haopu Shang, Jia-Liang Wu, Wenjing Hong, Chao Qian 0001   +3 more
openaire   +2 more sources

Adversarial Structured Neural Network Pruning [PDF]

Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019
In recent years, convolutional neural networks (CNN) have been successfully employed for performing various tasks due to their high capacity. However, just like a double-edged sword, high capacity results from millions of parameters, which also brings a huge amount of redundancy and dramatically increases the computational complexity.
Xingyu Cai, Jinfeng Yi, Fan Zhang 0010, Sanguthevar Rajasekaran   +3 more
openaire   +1 more source

Efficient Digital Predistortion Using Sparse Neural Network

IEEE Access, 2020
This paper proposes an efficient neural-network-based digital predistortion (DPD), named as envelope time-delay neural network (ETDNN) DPD. The method complies with the physical characteristics of radio-frequency (RF) power amplifiers (PAs) and uses a ...
Masaaki Tanio, Naoto Ishii, Norifumi Kamiya   +2 more
doaj   +1 more source

A Verification Method on Post-Pruning Generalization Ability of Neural Network Model [PDF]

Jisuanji gongcheng, 2019
To address the over-fitting problem caused by the down-regulation of the Dropout rate in the pruning operation of the neural network model,a verification method for the generalization ability of the pruning model is proposed.By artificially occluding the
LIU Chongyang, LIU Qinrang
doaj   +1 more source

Symmetric Pruning in Quantum Neural Networks

CoRR, 2022
Many fundamental properties of a quantum system are captured by its Hamiltonian and ground state. Despite the significance of ground states preparation (GSP), this task is classically intractable for large-scale Hamiltonians. Quantum neural networks (QNNs), which exert the power of modern quantum machines, have emerged as a leading protocol to conquer ...
Xinbiao Wang, Junyu Liu, Tongliang Liu, Yong Luo 0002, Yuxuan Du, Dacheng Tao   +5 more
openaire   +3 more sources

Number of necessary training examples for Neural Networks with different number of trainable parameters

Journal of Pathology Informatics, 2022
In this work, the network complexity should be reduced with a concomitant reduction in the number of necessary training examples. The focus thus was on the dependence of proper evaluation metrics on the number of adjustable parameters of the considered ...
Th.I. Götz, S. Göb, S. Sawant, X.F. Erick, T. Wittenberg, C. Schmidkonz, A.M. Tomé, E.W. Lang, A. Ramming   +8 more
doaj   +1 more source

Cyclical Pruning for Sparse Neural Networks

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022
Current methods for pruning neural network weights iteratively apply magnitude-based pruning on the model weights and re-train the resulting model to recover lost accuracy. In this work, we show that such strategies do not allow for the recovery of erroneously pruned weights.
Suraj Srinivas, Andrey Kuzmin, Markus Nagel, Mart van Baalen, Andrii Skliar, Tijmen Blankevoort   +5 more
openaire   +2 more sources

Dirichlet Pruning for Neural Network Compression

CoRR, 2020
We introduce Dirichlet pruning, a novel post-processing technique to transform a large neural network model into a compressed one. Dirichlet pruning is a form of structured pruning that assigns the Dirichlet distribution over each layer's channels in convolutional layers (or neurons in fully-connected layers) and estimates the parameters of the ...
Adamczewski, K., Park, M.
openaire   +3 more sources

Dynamically Optimizing Network Structure Based on Synaptic Pruning in the Brain

Frontiers in Systems Neuroscience, 2021
Most neural networks need to predefine the network architecture empirically, which may cause over-fitting or under-fitting. Besides, a large number of parameters in a fully connected network leads to the prohibitively expensive computational cost and ...
Feifei Zhao, Feifei Zhao, Yi Zeng, Yi Zeng, Yi Zeng, Yi Zeng, Yi Zeng   +6 more
doaj   +1 more source

Dissecting Pruned Neural Networks

CoRR, 2019
Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these networks contain a vast amount of ...
Jonathan Frankle, David Bau
openaire   +2 more sources