IIT Mandi Certificate Programme in Applied Artificial Intelligence and Machine Learning

About Course

The Certificate Programme in Applied Artificial Intelligence and Machine Learning offers a comprehensive and hands-on approach to mastering the principles and applications of AI and Machine Learning (ML). Tailored for both beginners and experienced professionals, this programme covers a wide range of topics, including Python fundamentals, data preprocessing, predictive modelling, deep learning, computer vision, and more. Led by industry experts, the curriculum combines theoretical knowledge with practical exercises and real-world case studies to ensure participants gain a deep understanding of AI and ML concepts and their practical applications. With flexible learning options and personalised guidance, participants will acquire the skills and confidence needed to excel in the rapidly growing field of artificial intelligence and machine learning.

Find more details in Brochure

URL: Programme Page

Design and deploy AI solutions for real-world applications
Understand computer vision, including segmentation, 3D vision, and motion estimation
Implement image processing techniques for image enhancement, restoration, and transformation
Understand and implement natural language processing techniques
Understand applications of AI in various industries.
Learn the fundamentals of LLM and GenAI

Course Content

Python Fundamentals
1. Grasp Basic Python essentials, covering Data Types to Numpy and Pandas. Develop a solid foundation in Python fundamentals for advanced programming and data science concepts. 2. Learn fundamental data science concepts, including Probability, Statistics, and Basics of Linear Algebra. Gain a strong foundation in discrete and continuous random variables, moments, and functions for effective data analysis.

Basic Python
Basic Primer

Data Pre-Processing
Explore basics of data pre-processing along with introduction to Principal Component Analysis (PCA). Identify categorical variables and explore variable levels to grasp their impact on data analysis.

Building Predictive Models
Explore machine learning basics, distinguishing between supervised and unsupervised learning. Master K-Nearest Neighbour (KNN) classification, Bayes classifier, and regression. Develop skills in Time Series Prediction using AR, MA, and ARIMA models.

Data Mining and Recommender Systems
Discover Decision Trees, Clustering with K-Means, and techniques to address Class Imbalance. Learn about pruning, Tree Building Model Selection, and handling Recommender systems.

Deep Learning for AI
Explore Deep Learning foundations, covering ANN, ReLu, and advanced topics like RNNs, LSTMs, CNN architectures, and GANs. Gain a comprehensive understanding of AI in Natural Language Processing.

Image Processing for AI
Learn Image Enhancement techniques, including Power Law transformation, Histogram processing, and Image Smoothing. Explore Image-to-Image Transformations, covering Super resolution, image inpainting, dehazing, and colorisation for effective image restoration.

AI for Speech Processing
Gain insights into speech processing and its diverse applications, and explore features to represent speech data. Engage in a case study on Speaker Recognition with a corresponding hands-on lab. Further, delve into the design of GMM-based and neural network-based classifiers for Speaker Recognition, solidifying your understanding through practical application in a case study.

Computer Vision
1. Understand Image Segmentation, covering colour, texture, and intensity-based methods. Explore K-means Clustering and SLIC Superpixels through hands-on labs. 2. Introduce Stereo Vision, depth cues, and simple stereo vision (2D and 3D). 3. Learn stereo derivations, disparity estimations, and image-to-image transformations using depth cues. 4. Apply knowledge in the lab focused on Disparity. 5. Explore semantic segmentation, its necessity, and applications. 6. Implement learning-based semantic segmentation using FCN and Segnet decoders in the lab. 7. Learn Image Registration, motion estimation, and types of geometric transformations. Understand tracking methods, including Harris corner detection and KLT tracker through a practical lab. 8. Discover the applications of computer vision in remote sensing, visual quality assessment, and other domains.

Application of AI in Industry
1. Discover various ML/CV applications in healthcare, expanding your understanding of the broader impact of AI in the medical field. 2. Explore Computer Vision's role in biomedical problem-solving and standard tasks in medical image analysis, forensics, and medical document analysis.

About Course

What Will You Learn?

Course Content

Basic Python

Basic Primer

Data Pre-Processing Explore basics of data pre-processing along with introduction to Principal Component Analysis (PCA). Identify categorical variables and explore variable levels to grasp their impact on data analysis.

Data Pre-Processing

Principal Component Analysis

Building Predictive Models Explore machine learning basics, distinguishing between supervised and unsupervised learning. Master K-Nearest Neighbour (KNN) classification, Bayes classifier, and regression. Develop skills in Time Series Prediction using AR, MA, and ARIMA models.

Introduction to Machine Learning

Bayes Classifier

Discriminative Learning Methods for Classification

Regression: Linear Model for Regression

Time Series Prediction

Data Mining and Recommender Systems Discover Decision Trees, Clustering with K-Means, and techniques to address Class Imbalance. Learn about pruning, Tree Building Model Selection, and handling Recommender systems.

Decision Tree

Clustering and Holt Winters

Deep Learning for AI Explore Deep Learning foundations, covering ANN, ReLu, and advanced topics like RNNs, LSTMs, CNN architectures, and GANs. Gain a comprehensive understanding of AI in Natural Language Processing.

Deep Learning for AI

AI for Natural Language Processing

Image Processing for AI Learn Image Enhancement techniques, including Power Law transformation, Histogram processing, and Image Smoothing. Explore Image-to-Image Transformations, covering Super resolution, image inpainting, dehazing, and colorisation for effective image restoration.

Image Enhancement and Restoration

Image to Image Tranformations

Introduction to Speech Processing and Different Applications, Features to Represent the Speech Data

Case Study: Speaker Recognition

Lab Associated with theory Covered

Case Study: Designing GMM-based Classifiers and Neural Network-based Classifiers for Speaker Recognition

Low-level and High-level Segmentation

3D Computer Vision

Segmentation and 3D Computer

Registration, Motion Estimation, Tracking

Applications of Computer Vision

AI in Healthcare

Other Healthcare and Medical Application of ML/CV

Tools

Python

PyTorch

TensorFlow

ScikitLearn

SciPy

NumPy

Google Colab

Assignments/Projects/ Learners can choose from the options provided to them

Natural Language Processing

Bioinformatics

Computer Vision

Healthcare

Bring Your Own Project

Data Pre-Processing
Explore basics of data pre-processing along with introduction to Principal Component Analysis (PCA). Identify categorical variables and explore variable levels to grasp their impact on data analysis.

Building Predictive Models
Explore machine learning basics, distinguishing between supervised and unsupervised learning. Master K-Nearest Neighbour (KNN) classification, Bayes classifier, and regression. Develop skills in Time Series Prediction using AR, MA, and ARIMA models.

Data Mining and Recommender Systems
Discover Decision Trees, Clustering with K-Means, and techniques to address Class Imbalance. Learn about pruning, Tree Building Model Selection, and handling Recommender systems.

Deep Learning for AI
Explore Deep Learning foundations, covering ANN, ReLu, and advanced topics like RNNs, LSTMs, CNN architectures, and GANs. Gain a comprehensive understanding of AI in Natural Language Processing.

Image Processing for AI
Learn Image Enhancement techniques, including Power Law transformation, Histogram processing, and Image Smoothing. Explore Image-to-Image Transformations, covering Super resolution, image inpainting, dehazing, and colorisation for effective image restoration.

Assignments/Projects/
Learners can choose from the options provided to them