The Department of Computer Science & Engineering, Mangalore Institute of Technology & Engineering, organized a two-day hands-on workshop on “Machine Learning: Bridging Theory to Deep Learning Practice” on 24th and 26th August 2026. The workshop was aimed at providing seventh-semester students with practical exposure to the complete Machine Learning workflow and enabling them to connect theoretical concepts with real-world implementation. The students actively participated in the workshop, making it an engaging and application-oriented learning experience.
The resource persons for the workshop were Dr. Radhika Kamath, Associate Professor, School of Computer Engineering, Manipal Institute of Technology, and Dr. Krishnaraj Chadaga, Assistant Professor, Manipal Institute of Technology. Dr. Radhika Kamath is an experienced academician and researcher specializing in Image Processing, Computer Vision, Wireless Sensor Networks, Artificial Intelligence, medical image analysis, pattern recognition, and Machine Learning. She has extensive experience in teaching, research, and mentoring and has contributed through numerous research publications and student research projects. Dr. Krishnaraj Chadaga specializes in Artificial Intelligence, Machine Learning, Explainable AI (XAI), medical data analytics, and intelligent healthcare systems. His research includes interpretable and secure machine learning models for applications such as cancer detection, thermographic analysis, biomarker analytics, bone marrow transplant outcome prediction, and intelligent disease prediction. He has authored 50+ high-quality Q1 journal publications and has actively contributed to AI-based clinical decision support and predictive healthcare technologies.
The workshop provided participants with practical exposure to the complete Machine Learning workflow, covering problem formulation, data preprocessing, data handling and visualization, regression, classification, clustering, neural network implementation, optimization, and model evaluation. Through hands-on exercises, students gained experience in data cleaning and visualization, implementation of regression and classification algorithms, model training and evaluation, and comparison of different algorithms using standard performance measures. The sessions also provided practical exposure to Support Vector Machines, K-Means and Hierarchical Clustering, Perceptron, Reinforcement Learning, Artificial Neural Networks using Keras, and optimization techniques such as Stochastic Gradient Descent (SGD) and Adam. The expert demonstrations and practical exercises helped students develop confidence in selecting, implementing, evaluating, and optimizing Machine Learning models for practical problems.
The event was coordinated by Dr. Sumalatha U and Ms. Sunitha N V, Assistant Professors, Department of Computer Science & Engineering, MITE. The workshop concluded successfully with active participation and interaction from students. Overall, the program served as an effective platform for experiential learning, helping participants bridge the gap between Machine Learning theory and practical implementation while establishing a strong foundation for further learning in Deep Learning and Artificial Intelligence.
