Abstract:Learning with datasets containing a limited number of exemplars is a contentious research area. Researchers have used deep learning (DL) models with a large number of trainable parameters for such limited datasets leading to problems such as overfitting, overparameterization, lack of generalization, and the need for large computational resources. Judicious use of appropriate learning methodologies may be in order when the dataset for training is limited. Non-DL methodologies or traditional machine learning methodologies with appropriate pre-processing and feature extraction techniques may perform at par or better than DL techniques for applications that have a limited dataset. This talk will demonstrate this proposition for two non-contact sensor-based applications namely, radar-based monitoring of human activities (and fall event detection) and thermography-based breast abnormality detection. This talk with discuss the development of computationally inexpensive novel supervised and unsupervised non-DL learning methodologies for binary and multi-class classification problems that outperform the current state-of-the-art techniques of the respective fields in those remote sensor-based <a href="http://applications.Speaker(s):" target="_blank" title="applications.Speaker(s):">applications.Speaker(s): Ankita, Virtual: https://events.vtools.ieee.org/m/456113