Performance Evaluation of Autism Diagnosis Tool at Diverse Learning Rates
By: Khullar, Vikas.
Contributor(s): Bala, Manju.
Publisher: New Delhi STM Journals 2019Edition: Vol.6(2), May-Aug.Description: 92-99p.Subject(s): Computer EngineeringOnline resources: Click here In: Journal of artificial intelligence research and advances (JoAIRA)Summary: Artificial Neural Networks (ANN) has been considered as a major artifact in the scenario of Machine Learning, which needs optimization for more accurate and efficient results. The main aim of this paper is to identify the optimization techniques and their learning rates for ANN with better results. In this paper, we have been utilized “Keras” library for framing ANN with different optimization techniques. The evaluation of the optimization techniques has conducted on the basis of accuracy and loss as parameters. On the basis of our comparative study, we have proposed the best ANN optimization technique out of our evaluated techniques for the diagnosis of available Autism Spectrum Disorder (ASD) dataset.Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|
Articles Abstract Database | School of Engineering & Technology Archieval Section | Not for loan | 2020181 |
Artificial Neural Networks (ANN) has been considered as a major artifact in the scenario of Machine Learning, which needs optimization for more accurate and efficient results. The main aim of this paper is to identify the optimization techniques and their learning rates for ANN with better results. In this paper, we have been utilized “Keras” library for framing ANN with different optimization techniques. The evaluation of the optimization techniques has conducted on the basis of accuracy and loss as parameters. On the basis of our comparative study, we have proposed the best ANN optimization technique out of our evaluated techniques for the diagnosis of available Autism Spectrum Disorder (ASD) dataset.
There are no comments for this item.