.png){kind=icon}
Return
A generalized Lorenz system-based initialization method for deep neural networks
.png){kind=icon}
PRE
AI
DOI：10.1016/j.asoc.2024.112316.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep neural networks (DNNs) are a powerful tool for solving complex problems. The effectiveness of DNNs largely depends on the initialization technique used. This research develops a new initialization method for DNNs that uses chaotic sequences from the generalized Lorenz system to improve their performance. The proposed method, termed Generalized Lorenz Initialization (GLI), has been compared with two established initialization methods (Kaiming and Xavier) across four different DNN architectures: Informer, Neural Basis Expansion Analysis for Interpretable Time Series, Long Short-Term Memory, and NeuRewriter. The performance of these methods has been evaluated on seven time series forecasting datasets and one combinatorial optimization dataset. Results show that the GLI method improved forecasting accuracy by up to 86.47% compared to the Kaiming method and 88.86% compared to the Xavier method across all time series datasets. For the combinatorial optimization task, the GLI method reduced computational time by up to 9.24% with the better solution quality. These indicate the superiority of the GLI method over the two representative initialization methods for different DNN architectures across different problem domains.
Keywords:
Initialization method
Generalized Lorenz system
Deep neural networks
Time series forecasting
Combinatorial optimization
Journal
IF:
6.6
Papers:
1.4W
Citations:
4.8W
Organization
Cited Papers
ShareSaveImproving deep neural networks with multi-layer maxout networks and a novel initialization method.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSaveShareSaveConglomeration of deep neural network and quantum learning for object detection: Status quo review
PREAI
ShareSaveAutomatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initializationMEDICAL IMAGE ANALYSIS
OAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAIShareSaveShareSaveSW-ELM: A summation wavelet extreme learning machine algorithm with a priori parameter initializationNEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAIShareSave
View more