A statistically resilient method of weight initialization for SFANN

Mittal, Apeksha; Chandra, P.; Singh, Amit Prakash

doi:10.1109/icacci.2015.7275804

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2016

2021

Publication Types

Select...

Article3

Book2

Relationship

Self Cite1

Independent4

Authors

Journals

Cited by 5 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Qiao et al [14] initialized weights based on useful information between input and output variables. Mittal et al [10] initialized weights in the statistically resilient intervals in significant range of activation function. Bhatia et al [1] initialized weights in the interval (−3/ √ I, 3/ √ I), where I is the number of input.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Random Weight Initialization to New Weight Initialization CONEXP

Mittal

Singh

Chandra

2020

Data Science and Analytics

Self Cite

View full text Add to dashboard Cite

Training in feedforward networks is adaptation of weights of network which makes weight initialization an important factor in determining the training speed in network. This work aims at proposing a new weight initialization technique, wherein the weights are initialized in the useful range in threshold function. It further initializes weights to each hidden node in a region which alternately contracts and expands statistically. The proposed weight initialization is compared to the conventional random weight initialization. The proposed weight initialization is expected to perform better than the random weight initialization.

show abstract

Section: Introductionmentioning

confidence: 99%