Labelled data are not only time consuming but often expensive and difficult to procure as it involves skilful inputs by humans to tag and annotate. Contrary to this unlabelled data is comparatively easier to procure but fewer methods exist to optimally use them. Semi-Supervised Learning overcomes this problem and assists to build better classifiers by using unlabelled data along with sufficient labelled data and may actually yield higher accuracy with considerably less human input effort. But if the labelled data set is inadequate in size then the Semi-Supervised techniques are also stuck. We propose a novel framework where the small labelled dataset is appropriately augmented using the intelligent learning mechanisms of artificial immune systems to train the proposed model. The model retrains with the unlabelled data to fortify the learning mechanism. We show that the generative deep framework utilizing artificial immune system principles provides a highly competitive approach for learning in the semi-supervised environment.

Integrated Semi-Supervised Model for Learning and Classification

Machine learning methods are used today mostly for recognition problems. Convolutional Neural Networks (CNN) have time and again proved successful for many image processing tasks primarily for their architecture. In this paper we propose to apply CNN to small data sets like for example, personal photo albums or other similar environs where the size of training dataset is a limitation, within the framework of a proposed hybrid CNN-AIS model. We use Artificial Immune System Principles to enhance the small size of training data set. A layer of Clonal Selection is added to the local filtering and max pooling of CNN Architecture. The proposed Architecture is evaluated using the standard MNIST dataset by limiting the data size and also with a small personal data sample belonging to two different classes. Experimental results show that the proposed hybrid CNN-AIS based recognition engine works well when the size of training data is limited in size.

/pdf/a-novel-hybrid-cnn-ais-visual-pattern-recognition-engine-37fvyzj0d7.pdf

A Novel Hybrid CNN-AIS Visual Pattern Recognition Engine

Machine learning methods are used today for most recognition problems. Convolutional Neural Networks (CNN) have time and again proved successful for many image processing tasks primarily for their architecture. In this paper we propose to apply CNN to small data sets like for example, personal albums or other similar environs where the size of training dataset is a limitation, within the framework of a proposed hybrid CNN-AIS model. We use Artificial Immune System Principles to enhance small size of training data set. A layer of Clonal Selection is added to the local filtering and max pooling of CNN Architecture. The proposed Architecture is evaluated using the standard MNIST dataset by limiting the data size and also with a small personal data sample belonging to two different classes. Experimental results show that the proposed hybrid CNN-AIS based recognition engine works well when the size of training data is limited in size

A vast number of applications do not have ample training data and consequently the accuracies suffer. There is a need to develop a technique to optimally and intelligently augment such datasets and design an automated classifier which gives good performance despite the smallness of dataset size. Meticulously stored data will ease retrieval. Artificial Immune System (AIS) is one amongst many computational algorithms in literature that are inspired by the dynamic learning mechanism of the human system. AIS based classification algorithm was proposed initially as one of the machine learning techniques which is suited for supervised learning problems. There are various applications areas of this powerful algorithm. We present a novel technique inspired by clonal selection to augment small datasets and classification.

Vandna Bhalla

Papers

A Novel Hybrid CNN-AIS Visual Pattern Recognition Engine

A Novel Hybrid CNN-AIS Visual Pattern Recognition Engine

Innovative model to augment small datasets for classification

Integrated Semi-Supervised Model for Learning and Classification