Pathnet: A Neuronal Model for Robotic Motion Planning

Aparanji, V. M.; Wali, Uday; Hemavati, Hemavati

doi:10.1007/978-981-10-9059-2_34

Cited by 5 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is possible to use several of the existing types of neural networks discussed in [13,14] for path planning of robotic motion. A hierarchical network for path planning built using ARN has been reported in [15,16]. However, they can be used as generic data classifiers and find applications in various areas of artificial intelligence.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Tunability of auto resonance network

Aparanji

Wali

Aparna³

2020

SN Appl. Sci.

Self Cite

View full text Add to dashboard Cite

This paper proposes a new type of Artificial Neural Network called Auto-Resonance Network (ARN) derived from synergistic control of biological joints. The network can be tuned to any real valued input without any degradation of learning rate. Neuronal density of the network is low and grows at a linear or low order polynomial rate with input classification. Input coverage of the neuron can be tuned dynamically to match properties of input data. ARN can be used as a part of hierarchical structures to support deep learning applications.

show abstract

Section: Resultsmentioning

confidence: 99%

“…For a node described by (15), and knowing that y max = 1 and assuming x r = 0, we can write the value of x for threshold of y = as, which gives an expression for coverage of an ARN node as a function of threshold and tuning factor. Equation 17can be rewritten as (16)…”

Section: Tuning the Nodes And Coveragementioning

confidence: 99%