Unsupervised MKL in Multi-layer Kernel Machines

no code implementations • 26 Nov 2021 • Akhil Meethal, Asharaf S, Sumitra S

Kernel based Deep Learning using multi-layer kernel machines(MKMs) was proposed by Y. Cho and L. K.

Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory

1 code implementation • 29 Sep 2020 • Asif Salim, Sumitra S

In this work, we explore the regularization properties of graph Laplacian and proposed a generalized framework for regularized filter designs in spectral GCNNs.

Graph Learning Node Classification

Disentanglement based Active Learning

1 code implementation • 15 Dec 2019 • Silpa Vadakkeeveetil Sreelatha, Adarsh Kappiyath, Sumitra S

We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement.

Active Learning Disentanglement +1