Evolving an Adaptive Controller for a Legged-Robot With Dynamically-Rearranging Neural Networks

Otsu, K.; Fujii, Asuka; Ishiguro, Akio; Uchikawa, Yoshiki; Aoki, Takeshi; Eggenberger, Peter

doi:10.1299/jsmemecjo.2000.1.0_915

Cited by 6 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural Networks find applications in critical and sensitive environments [6]. The advantage of using Neural Network is that they learn by example and also can adapt to various environments [7][8][9], because of the availability of robust training algorithms, their precision, accuracy can be controlled and data processing by the Neural Network can result in faster output due to their parallel processing nature which can be used in the design of highly reliable and fast logic circuits.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Synchronous Binary Counter Using Hybrid Algorithm Training

Yakkali¹,

Raghava²

2017

IJIGSP

View full text Add to dashboard Cite

Abstract-Information processing using Neural NetworkCounter can result in faster and accurate computation of data due to their parallel processing, learning and adaptability to various environments. In this paper, a novel 4-Bit Negative Edge Triggered Binary Synchronous Up/Down Counter using Artificial Neural Networks trained with hybrid algorithms is proposed. The Counter was built solely using logic gates and flip flops, and then they are trained using different evolutionary algorithms, with a multi objective fitness function using the back propagation learning. Thus, the device is less prone to error with a very fast convergence rate. The simulation results of proposed hybrid algorithms are compared in terms of network weights, bit-value, percentage error and variance with respect to theoretical outputs which show that the proposed counter has values close to the theoretical outputs.

show abstract

Section: Introductionmentioning

confidence: 99%