Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

A Meta-cognitive Recurrent Fuzzy Inference System with Memory Neurons (McRFIS-MN) and its Fast Learning Algorithm for Time Series Forecasting

Published in The 2018 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2018), Bangalore, India, 2018

This paper proposes to introduce recurrence in fuzzy neural networks and training using the one-shot Project-Based Learning algorithm for faster prediction.

Recommended citation: Samanta, S., Ghosh, S., & Sundaram, S. (2018). A Meta-cognitive Recurrent Fuzzy Inference System with Memory Neurons (McRFIS-MN) and its Fast Learning Algorithm for Time Series Forecasting.

Page Rank for Word Sense Disambiguation

Published: April 19, 2018

Presented the idea of exploiting the capability of the Page Rank algorithm to handle the circularity of word definitions for an application in word sense disambiguation. [Slides]

Recurrence in Fuzzy Neural Networks and a faster training algorithm for Time Series forecasting

Published: November 20, 2018

Presented our novelty approach in having introduced recurrence in fuzzy inference systems, while using a faster one-shot projectionbased learning algorithm for time series forecasting [Slides]

Deep Learning Masterclass

Workshop, Indian Institute of Technology Madras, 2018

Conducted classes covering basics of Machine Learning and Deep Learning, Optimization, Regularization, CNNs, Word Vectors, RNNs and Encoder-Decoder Models for an audience of 90 people comprising Undergraduate and Post-Graduate students