Results 231 to 240 of about 22,594 (260)

Pruned Neural Networks for Regression

2000
Neural networks have been widely used as a tool for regression. They are capable of approximating any function and they do not require any assumption about the distribution of the data. The most commonly used architectures for regression are the feedforward neural networks with one or more hidden layers.
Rudy Setiono, Wee Kheng Leow
openaire   +1 more source

A new method to prune the neural network

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000
Using the backpropagation algorithm (BP) to train neural networks is a widely adopted practice in both theory and practical applications. However, its distributed weight representation, that is the weight matrix of final network after training by using BP are usually not sparsified, and prohibits its use in the rule discovery of inherent functional ...
Wan, Weishui, Hirasawa, Kotaro, Hu, Jinglu, Jin, Chunzhi   +3 more
openaire   +1 more source

Growing and pruning neural tree networks

IEEE Transactions on Computers, 1993
A pattern classification method called neural tree networks (NTNs) is presented. The NTN consists of neural networks connected in a tree architecture. The neural networks are used to recursively partition the feature space into subregions. Each terminal subregion is assigned a class label which depends on the training data routed to it by the neural ...
Ananth Sankar, Richard J. Mammone
openaire   +1 more source

Neural network pruning and hardware acceleration

2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC), 2020
Neural network pruning is a critical technique to efficiently deploy neural network models on edge devices with limited computing resources. Although many neural network pruning methods have been published, it is difficult to implement such algorithms due to their inherent complexity.
Taehee Jeong, Ehsam Ghasemi, Jorn Tuyls, Elliott Delaye, Ashish Sirasao   +4 more
openaire   +1 more source

Variational Convolutional Neural Network Pruning

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019
We propose a variational Bayesian scheme for pruning convolutional neural networks in channel level. This idea is motivated by the fact that deterministic value based pruning methods are inherently improper and unstable. In a nutshell, variational technique is introduced to estimate distribution of a newly proposed parameter, called channel saliency ...
Chenglong Zhao, Bingbing Ni, Jian Zhang 0079, Qiwei Zhao, Wenjun Zhang 0001, Qi Tian 0001   +5 more
openaire   +1 more source

Neural network pruning for function approximation

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000
A simple algorithm for pruning feedforward neural networks with a single hidden layer trained for function approximation is presented. The algorithm assumes that the networks have been trained with more then the necessary number of hidden units and it consists of two stages. In the first stage redundant hidden units are removed, and in the second stage
Rudy Setiono, Adam E. Gaweda
openaire   +1 more source

Pruning Neural Network Parameters Using Recurrent Neural Networks

Lecture Notes in Computer Science
Koichiro Yamauchi
exaly   +2 more sources

Pruned and Structurally Sparse Neural Networks

2018 IEEE MIT Undergraduate Research Technology Conference (URTC), 2018
Advances in designing and training deep neural networks have led to the principle that the large and deeper a network is, the better it can perform. As a result, computational resources have become a key limiting factor in achieving better performance.
Simon Alford, Ryan A. Robinett, Lauren Milechin, Jeremy Kepner   +3 more
openaire   +2 more sources

Pruning versus clipping in neural networks

Physical Review A, 1989
The number of interconnections in a neutral network is reduced by eliminating the ``weakest'' bonds. The performance is then improved by reapplying the learning algorithm.
openaire   +2 more sources

Neural Network Pruning and Pruning Parameters

1996
The default multilayer neural network topology is a fully interlayer connected one. This simplistic choice facilitates the design but it limits the performance of the resulting neural networks. The best-known methods for obtaining partially connected neural networks are the so called pruning methods which are used for optimizing both the size and the ...
Thimm, Georg, Fiesler, Emile
openaire   +1 more source