Certification Course on Problem solving using AIML techniques

The Signal Processing group of the School of ECE is organising a certification course on “Problem-solving using AIML techniques” starting from October 2023. Experts from the School of ECE and industry will deliver lectures with hands-on sessions. The total contact hours of the course will be 40 hours. The course focuses more on practical sessions (30 hours) with the required theory sessions (12 hours) followed by the assessment. After successful completion of the course, the candidates will be awarded the certificate.

The goal of this certification course is to give a firm foundation in the implementation of Machine Learning algorithms. The course focuses on the conceptual depths of topics such as Data Science, Machine Learning and Artificial Intelligence, The course imparts extensive knowledge on Python for Data Science, Data Visualization in Python, Exploratory Data Analysis, Linear Regression, Logistic Regression, Classification using Decision Trees, unsupervised learning: clustering, principal component analysis.

Course Outcomes

• Learn how to manipulate datasets in Python using Pandas which is the most powerful library for data preparation and analysis.
• Humans are visual learners, and hence no task related to data is complete without visualization. Learn to plot and interpret various graphs in Python and observe how they make data analysis and drawing insights easier.
• Learn how to find and analyze the patterns in the data to draw actionable insights.
• Solve a real industry problem through the concepts learned in exploratory data analysis.
• Venture into the machine learning community by learning how one variable can be predicted using several other variables through a housing dataset where you will predict the prices of houses based on various factors.
• Learn binary classification technique by determining which telecom operator customers are likely to churn versus those who are not to help the business retain customers.
• Learn how the human decision-making process can be replicated using a decision tree and tune it to suit your needs.
• Learn how to group elements into different clusters when you don’t have any pre-defined labels to segregate them through K-means clustering, hierarchical clustering.

Contents

Textbooks & Supporting Literature

• Tom Mitchell: In Tom Mitchell, Machine Learning, TMH
• C. Bishop, Pattern Recognition and Machine Learning, Springer
• R. O. Duda, P. E. Hart and D. G. Stork, Pattern Classification and Scene Analysis, Wiley
• Kishan Mehrotra, Chilukuri Mohan and Sanjay Ranka, Elements of Artificial NeuralNetworks, Penram International
• Rajjan Shinghal, Pattern Recognition, Techniques and Applications, OXFORD 6. Ethem alpaydin. Introduction to Machine Learning, PHI

Online Material