Performance Analysis Between Combinations of Optimization Algorithms and Activation Functions used in Multi-Layer Perceptron Neural Networks
Background:- Artificial Neural networks are motivated from biological nervous system and can be used for classification and forecasting the data. Each neural node contains activation function could be used for solving non-linear problems and optimization function to minimize the loss and give more a...
Main Authors: | Valmiki, Geetha Charan, Tirupathi, Akhil Santosh |
---|---|
Format: | Others |
Language: | English |
Published: |
Blekinge Tekniska Högskola, Institutionen för datavetenskap
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:bth-20204 |
Similar Items
-
Teaching learning-based whale optimization algorithm for multi-layer perceptron neural network training
by: Yongquan Zhou, et al.
Published: (2020-09-01) -
The Effects of Using Results from Inversion by Evolutionary Algorithms to Retrain Artificial Neural Networks
by: Hardarson, Gisli
Published: (2000) -
The optimal training interval for amultilayer perceptron on a day to dayestimation of the Swedish OMXS30index
by: Meier, Anton, et al.
Published: (2014) -
Evolutionary Computation in Continuous Optimization and Machine Learning
by: Dahlberg, Leslie
Published: (2017) -
A new scheme for training ReLU-based multi-layer feedforward neural networks
by: Wang, Hao
Published: (2017)