Abstract:
A teacher in a school plays significant role in classroom while teaching the students. Similarly, learning via privileged information (LUPI) gives extra information gener...Show MoreMetadata
Abstract:
A teacher in a school plays significant role in classroom while teaching the students. Similarly, learning via privileged information (LUPI) gives extra information generated by a teacher to ‘teach’ the learning algorithm while training. This paper proposes minimum variance embedded random vector functional link network with privileged information (MVRVFL+). The proposed MVRVFL+ minimizes the intraclass variance of the training data and uses privileged information paradigm which provides the additional knowledge during the training of the model. The proposed MVRVFL+ classification model is evaluated on 43 benchmark UCI datasets. From the experimental analysis, the proposed MVRVFL+ showed best average accuracy and emerged as the lowest average rank classifier among the baseline models.
Date of Conference: 18-23 July 2022
Date Added to IEEE Xplore: 30 September 2022
ISBN Information:
ISSN Information:
Funding Agency:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Functional Networks ,
- Minimum Variance ,
- Random Networks ,
- Privileged Information ,
- Random Vector Functional Link ,
- Functional Link Network ,
- Training Data ,
- Classification Model ,
- Learning Algorithms ,
- Average Rank ,
- Neural Network ,
- Null Hypothesis ,
- Least-squares ,
- Feature Space ,
- Unsupervised Learning ,
- Regularization Parameter ,
- Feed-forward Network ,
- Action Recognition ,
- Original Space ,
- Ridge Regression ,
- Extreme Learning Machine ,
- Privileged Space ,
- Random Feature ,
- Original Feature Space ,
- Regularized Least Squares ,
- Dual Space ,
- Moore Penrose Inverse ,
- Class Variance ,
- Weights Of Layer ,
- Penalty Parameter
- Author Keywords
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Functional Networks ,
- Minimum Variance ,
- Random Networks ,
- Privileged Information ,
- Random Vector Functional Link ,
- Functional Link Network ,
- Training Data ,
- Classification Model ,
- Learning Algorithms ,
- Average Rank ,
- Neural Network ,
- Null Hypothesis ,
- Least-squares ,
- Feature Space ,
- Unsupervised Learning ,
- Regularization Parameter ,
- Feed-forward Network ,
- Action Recognition ,
- Original Space ,
- Ridge Regression ,
- Extreme Learning Machine ,
- Privileged Space ,
- Random Feature ,
- Original Feature Space ,
- Regularized Least Squares ,
- Dual Space ,
- Moore Penrose Inverse ,
- Class Variance ,
- Weights Of Layer ,
- Penalty Parameter
- Author Keywords