NITC is a vibrant place that offers the best opportunities for researchers and I being a member of this community would resonate the same. My research interests are specifically in Machine, Learning, Deep Learning, Computer Vision, etc. My PhD thesis centers around explainability for computer vision models whose summary is presented below for your quick reference:

Image classification is the task in which a machine learning model predicts the class/category of an object contained in a given image from the set of known classes. Convolutional Neural Networks(CNN) have achieved state-of-the-art image classification results. However, how these models arrive at predictions for a given image is unclear.

The research field Explainable AI (XAI), aims to unravel the working mechanism used by these accurate, opaque black boxes. If the explanations are closer to how humans interpret images, they help better understand the working mechanism of CNNs. This fact was proved by previous experiments as reviewed from existing XAI literature. Studies show that humans process images in terms of sub-regions called concepts. For instance, a peacock is identifed by its characteristic concepts like green feathers, blue neck, etc.

My thesis intended to automatically extract such concepts learned by CNN from the data. Three novel frameworks are proposed to provide automatically extracted concept-based explanations for standard image classifiers. The first framework, PACE, automatically extracts class-specific concepts relevant to the prediction. While class-specific concepts unravel the blueprints of a class from CNN’s perspective, concepts are often shared across classes; for instance, gorillas and chimpanzees naturally share many characteristics as they belong to the same family. The second framework, SCE, unravels the concept sharedness across related classes from CNNs perspective. The relevance of the extracted concepts towards prediction and the primitive image aspects, like color, texture, and shape encoded by the concept, are estimated after training the explainer.

The thesis identifies a void in XAI’s panorama that much attention is given to classifiers trained and tested using the same data. However, allied paradigms have been shown to add to state-of-the-art successes. Despite the data hunger of deep models, domain adaptation techniques have been employed to leverage a huge amount of related data to help learn a classifier that is expected to work on scarce data of interest. The third framework XSDA-Net, builds a supervised domain-adapted classifier that can explain itself in terms of concepts extracted from the different datasets the classifier is exposed to.

Experiments demonstrate the utility of all three proposed frameworks in automatically extracting concepts from the data such that they unravel the working mechanism of the image classifiers. The thesis reviews the different types of explanations prevalent in the XAI field and enlightens the possible future research avenues for potential researchers looking to venture into XAI.

Given that I work in explainability which is crucial for any state-of-the-art deep learning system and have started branching out into allied learning paradigms by proposing mechanisms that help harness the fruits of explainability and the paradigm, there is a possibility to branch out into any deep learning paradigms and build models that are explainable, fair, transparent and accountable which are necessary characteristics a model is expected to exhibit for deployment in real-world safety-critical environments.

Update: I have started working on Speech Processing data modality (currently the work is done in collaboration with my Research Scholars, Undergraduate, and Postgraduate students), Reinforcement Learning (currently the work is done in collaboration with my Postgraduate students and Research Scholars) apart from the future directions identified in my thesis. 

I believe that the earlier we start the research projects, the deeper understanding and greater results may be achieved. So I welcome Undergraduate and Post-Graduate students of all years interested in my research spectrum to mail me and explore the possibility of collaboration.

PhD

1. Ms. Aswani Raj N P (from Aug 2024)

2. Ms. Sulala Saleem P (from Aug 2024) - Primary Supervisor- Co-Supervised by Dr. Gopakumar

3. Ms. Antu Raj S (from Dec 2024)

4. Ms. Anagha Chand R (Jan-Jun 2025) - Primary Supervisor - Co-Supervised by Dr. Umamaheswara Sharma 

5. Ms. Diviya K N (from Aug 2025) - Co Supervisor - Primary Supervisor Dr. Jay Prakash

M Tech Project

1. Mr. Harsh Vardhan (Aug 2024 - Jul 2025)

2. Mr. Chelluri Ashish Dheer (from Dec 2024)

3. Mr. Edvin Bishor (from Dec 2024)

4. Mr. Shijaz K S (from Dec 2024)

5. Mr. Danish Mohammed (from Dec 2024)

6. Mr. Bhavi Teja Reddy (from Dec 2024)

B Tech Project

1. Mr. Pratyush CC, Mr. Gopinath S Kumar, Mr. Crescent, Mr. Anuvind, Mr. Aditya Narisipalli, Mr. Koushik (from April 2025)

2. Mr. Teja Sri Harsha, Mr. Yeruva Rajagopal Reddy, Mr. Ajay Perumalla, Mr. Tharian Thomas, Mr. Saurav Singh, Mr. Ayush Gautam (July 2024 - May 2025)

3. Mr. Meesala Suresh Gopi, Mr. Yendluri Jahnav, Mr. Deepak Reddy (Feb 2024 - May 2024)

Interns

Ms. Radhika Suresh, Trivandrum

Neural Networks and Deep Learning (Elective) - S1 M Tech AIDA (Monsson 2025)

Machine Learning (Elective) - S1 M Tech CSIS (Monsoon 2025)

Data Structures and Algorithms Lab (Core) - S3 B Tech (Monsoon 2025)

Advanced Deep Learning and Computer Vision (Elective) - S2 M Tech AIDA (Winter 2025)

Machine Learning Lab (Elective) - S6 B Tech (Winter 2025)

Artificial Intelligence (Core) - S7 B Tech (Monsoon 2024)

Machine Learning (Elective) - S7 B Tech (Monsoon 2024)

Programming (Lab) - S1 B Tech (Monsson 2024)

Machine Learning (Core) - S2 M Tech AIDA (Winter 2024)

Program Design (Lab) - S2 B Tech (Winter 2024) 

Problem Solving & C Programming (Core) - S1 B Tech CSE(AI) (Monsoon 2023 at Amrita Vishwa Vidyapeetham Coimbatore)

Invited as a resource person for online FDP on Demystifying LLMs using Responsible AI, organized by TCE, Madurai, Tamil Nadu, India.

Delivered an online talk for the IEEE CIS Kerala Chapter

Delivered a session at the FDP on Envisioning the Future: Deep Dive into Advanced Artificial Intelligence and Machine Learning Technologies for Society organized by NITTE Mangaluru, Karnataka.

Delivered a session on the National Level Workshop on SAGE: Software Advancements in the Gen-AI Era, organized jointly by the Automatic Software Engineering Research (ASER), Centre for Information Technology Research & Automation (CITRA) and the Department of Computer Science & Engineering (CSED), National Institute of Technology Calicut.

FDPs completed:

1. High Performance Computing for Medical Image Processing and Computer Vision - Dec 9 - 14 , 2024 - ATAL FDP organized by MNNIT Allahabad
2. Future Perspectives of AI and Data Sciences: Algorithms and Applications - Dec 2-7, 2024 - ATAL FDP organized by IIITDM Kancheepuram
3. FDP for Teaching Excellence by IIT Madras Teaching Learning Centre - June 10-12, 2024 - Organized by Centre for Holistic Teaching & Learning, NIT Calicut

Workshops/ Expert Talks attended:

• "SPS JSTSP Webinar: 08 October 2025 by Dr. Kim, Dr. Skoglund, Dr. Anumanchipalli, Mr. Liu, Ms. Jiang & Dr. Villemoes" - “Overview of Special Issue on Neural Speech and Audio Coding” presented by Dr. Minje Kim, Dr. Jan Skoglund, Dr. Gopala K. Anumanchipalli, Mr. Haohe Liu, Ms. Xue Jiang & Dr. Lars Villemoes

• "SPS SLTC/AASP : 27 August 2025 by Dr. Piotr Żelasko".“Foundational Speech Models and their Efficient Training with NVIDIA NeMo” presented by Dr. Piotr Żelasko

• Wellness Seminar at NIT Calicut on 16 July 2025.

• 3rd Symposium on NLP for Social Good on 25-26 June 2025.

• Reinvent Workshop at NIT Calicut on 23 April 2025.

• Reinforcement Learning Workshop - 22-26 January 2025 - organized by IISc Bangalore
• Winter school on Deep Learning for Vision and Language Modelling  - 6-13  January 2025 - organized by IIT Guwahati
• Two-Day National Level Online Workshop on Concepts, Assumptions and Diagnostics in ANOVA and Regression Models - 6-7 December 2024 - Organized by Rajalakshmi Engineering College in collaboration with CEDAAR Chennai
• AI tools fro optimizing Research Workflow - 8th November 2024 - organized by Central Library, NIT Calicut
• Advanced Drone Technology (Air Taxi) - 13th October 2024 -  session hosted by India Space Lab
• Webinar on Healthcare & Technology - Trends in Data, Devices and Delivery - 16th September 2024 - organized by IIIT Bangalore
• Physics-informed Neural Networks for Aerial Robotics - 13th August 2024 - organized by  IEEE Control Systems Society Kerala Chapter
• Session on Generative AI in Healthcare - 10th August 2024 - organized by Institute Innovation Council
• Model-Based Deep Learning for Inverse Problems in MRI: Beyond Algorithm Unrolling, organized by the The ECE Association and IEEE Signal Processing Society (SB) Chapter - 26th July 2024
• Webinar on Artificial Intelligence – Standardization Landscape  - 21st June 2024 - organized by Electronics & IT Department, Bureau of Indian Standards
•  Introduction to Machine Learning and Computer Vision - one-day workshop organized under the Scientific Social Responsibility (SSR) Scheme for SERB funded SRG project - 22nd March 2024

Conferences:

Attended the Golden Jubilee of ICASSP 2025 a flagship IEEE conference of IEEE Signal Processing Society at Hyderabad, Telangana, India from 06 to 11 April 2025