FDP on “Machine Learning and Natural language Processing” from 4th to 9th January 2016

The introductory session about Machine Learning was delivered by Dr Kaimal M R, Professor, Amrita School of Engineering. The session began with a briefing of the concept of learning. It progressed with an overview of a range of applications that are dealt with using various machine learning algorithms.

The second session for the day was delivered by Dr Asharaf S. He walked through the emerging areas of SVM, some of which included object detection & recognition, content-based image retrieval, text recognition, biometrics and speech recognition.

The second day of FDP started with the session on Neural Networks by Dr Vinod Chandra from University of Kerala, R&D in e-Governance.

The Session on probability Theory and Hidden Markov Model was delivered by Dr Ibrahim. The motivation behind using Probability theory in Machine Learning and its usefulness in making optimal predictions based on the available information was described.

Day 3 began with introductory lectures on Natural Language Processing. Dr. Anand Kumar was successful in providing a clear road map development of Natural Language Processing Algorithms and development of applications that utilize them. The various packages and programming languages used best suited for NLP were also discussed in details. Dr. Anand Kumar further went on explain the various algorithms and techniques used for Question Answering and Information Extraction from Text Data. The session concluded with Dr. Kumar giving the participants a glimpse of some of his person works through an interactive discussion.

The afternoon session of Day 3 was handled by Dr. P C Raghuraj who delivered lectures that were aimed at briefing the participants on Computational Linguistics and how concepts of learning could be used in Natural Language Processing.

Dr. Madhukumar who handled the morning session of Day 4 delivered talks on Data Science and Big Data Analytics. The initials portions of the lectures were mostly focused on defining the term “Big Data” and why it had immense possibilities.

The afternoon session of Day 4 and all session of Day 5 were handled by Mr. Vijaya Krishna Menon. The first session aimed to introduce the participants to the basics of  Programming in SCALA. It began with a tutorial for installation and configuration of scala. Compilation and execution of a simple SCALA programs were then demonstrated by Mr. Vijaya Krishna Menon. The usage of the data types and data structures were also illustrated in the session. The second session, which was the morning session of day 5, began with lectures on additional functions, loops and conditional statements. In the Final Session Mr. Vijay Krishna Menon discussed about the OpenSpark package for SCALA which is used for Big Data Analytics. Further, a demonstration on the Big Data Analytics using OpenSpark on Wikipedia Data as corpus was also done by Mr. Vijay Krishna Menon.

The final day had sessions were the participant could try out and practice what they learned on the previous days about programming using SCALA and Big Data Analytics using OpenSpark. The participants used the sessions fruitfully and it helped in cementing all the concepts they learned.

event-cse2 event-cse1