Associative memory framework for speech recognition: Adaptation of Hopfield network

Vaishnavi, Y.; Shreyas, R.; Suhas, S; Surya, U. N.; Ladwani, Vandana M.; Ramasubramanian, V.

doi:10.1109/indicon.2016.7839105

Cited by 5 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aghajari et al [1] suggested a chaotic hetero-associative memory built using a learning strategy that allows to store and recall a set of associated patterns even when these are noisy. Vaishnavi et al [44] adapted the Hopfield network for isolated word recognition. Villuendas-Rey et al [45] presented the naïve associative classifier, which was based upon a new similarity operator with the capability to handle missing values and both numerical and categorical data.…”

Section: Introductionmentioning

confidence: 99%

Gene selection and disease prediction from gene expression data using a two-stage hetero-associative memory

2018

View full text Add to dashboard Cite

In general, gene-expression microarrays consist of a vast number of genes and very few samples, which represents a critical challenge for disease prediction and diagnosis. This paper develops a two-stage algorithm that integrates feature selection and prediction by extending a type of heteroassociative neural networks. In the first level, the algorithm generates the associative memory, whereas the second level picks the most relevant genes. With the purpose of illustrating the applicability and efficiency of the method proposed here, we use four different gene-expression microarray databases and compare its classification performance against that of other renowned classifiers built on the whole (original) feature (gene) space. The experimental results show that the two-stage hetero-associative memory is quite competitive with standard classification models regarding the overall accuracy, sensitivity, and specificity. In addition, it also produces a significant decrease in computational efforts and an increase in the biological interpretability of microarrays because worthless (irrelevant and/or redundant) genes are discarded.

show abstract

Section: Introductionmentioning

confidence: 99%