15^th June to 15^th July 2026

           IIT Kanpur Certificate Program on PYTHON
for Artificial Intelligence Machine Learning and Deep Learning   

      Organized by Prof. Aditya K. Jagannatham, EE Department, IIT Kanpur

Below is the detailed day-to-day & slot-wise program with Lecture Modules & Hands-On Coding Sessions for the   IIT Kanpur Certification Program on Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) from 15^th June to 15^th July 2026

	Week-1
	15th June, 2026
06:00 PM - 7:30 PM	Zoom Test Session
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 1: Introduction to Artificial Intelligence (AI) Machine Learning (ML)  •   Overview of AI, ML  •   Regression  •   Classification  •   Supervised Learning  •   Unsupervised Learning  •   Deep Learning  •   Test-Train Split  •   Metrics
	16th June, 2026
6:00 PM - 7:30 PM	Lecture 2: Linear Algebra for AIML  •   Vector Representation  •   Inner Product  •   Orthogonality  •   Matrices  •   Matrix Inversion
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 3: Linear Regression for AIML  •   Regression Model  •   Multiple Regressors  •   Model Computation  •   Pseudo inverse  •   Online Learning
	17th June, 2026
	Break Day
	18th June, 2026
06:00 PM - 07:30 PM	Project 1: IRIS Dataset Regression using PYTHON  •   IRIS Dataset Features  •   Linear Regression Module  •   Mean Squared Error (MSE)  •   R2 Score Project 2: Boston Housing Price Analysis using PYTHON-Based Regression  •   Boston Housing set Features  •   Model Fitting  •   Model Performance  •   MSE, R2 Score  •   Regression Plot
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 4: Logistic Regression-Based AIML  •   Logistic Function  •   Class Probabilities  •   Likelihood and ML  •   Logistic Regression Metrics  •   Confusion Matrix
	19th June, 2026
06:00 PM - 7:30 PM	Project 3: SCIKIT Package for Logistic Regression using Purchase/ Shopping Data  •   Purchase/ Shopping Dataset Features  •   Logistic Model Fitting  •   Confusion Matrix Display  •   Accuracy Score
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 5: Support Vector Classifier (SVC) for Machine Learning  •   SVM Structure  •   Maximum Margin Classifier  •   Convexity and Convex Optimization  •   Kernel SVM
	Week-2
	22nd June, 2026
06:00 PM - 7:30 PM	Project 4: IRIS Data Set classification using PYTHON-Based SVC  •   Dataset Features  •   Accuracy Metrics  •   Performance Evaluation
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 6: Naïve Bayes Technique for AIML  •   Feature Vector  •   Likelihood and Prior Probabilities  •   Naïve Bayes Principle  •   Posterior Probability Evaluation  •   Gaussian Naïve Bayes  •   Movie Recommender System Example
	23rd June, 2026
06:00 PM - 7:30 PM	Project 5: Breast Cancer Dataset Analysis using SVC  •   Breast Cancer Dataset Features  •   SVM Fit  •   Gaussian Kernel  •   Polynomial Kernel  •   Sigmoid Kernel  •   Performance Assessment Project 6: Naïve Bayes Classification of Purchase Dataset  •   Purchase Dataset Features  •   Gaussian NB Model Fitting  •   Accuracy Metrics  •   Confusion Matrix Display
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 7: Discriminant Analysis (LDA) Based Data Classification  •   Gaussian Density  •   Multivariate Gaussian  •   Gaussian/ Linear Discriminant  •   Example Model Computation
	24th June, 2026
06:00 PM - 7:30 PM	Project 7: Discriminant Based Data Classification using IRIS Data Set  •   IRIS Dataset Features  •   LDA Model Fitting  •   Performance Visualization
7:30 PM-8:00 PM	Break
8:00 PM - 09:15 PM	Lecture 8: Data Clustering for Machine Learning  •   K-Means Algorithm  •   Centroid Computation  •   Cluster Assignment  •   Elbow Method for Number of Clusters  •   Silhouette Score
	25th June, 2026
06:00 PM - 7:30 PM	Project 8: PYTHON Project for Data Clustering  •   K-Means Implementation  •   Elbow Curve  •   Silhouette Plot  •   Cluster Visualization
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 9:Decision Tree Classifiers (DTC) for AIML  •   Optimal Feature Selection  •   Entropy  •   Conditional Entropy  •   Information Gain  •   Computation for Practical Restaurant Reservation Example
	26th June, 2026
	Gazetted Holiday
	Week-3
	29th June, 2026
06:00 PM - 7:30 PM	Project 9: Building a DTC for IRIS Dataset using PYTHON  •   IRIS Dataset Features  •   DTC Model Fitting  •   Accuracy Score  •   Confusion Matrix
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 10: Introduction to Neural Networks (NNs)  •   Neuron Structure and Properties  •   ANN Model  •   Activation Functions  •   One Hot Encoding  •   Categorical Crossentropy
	30th June, 2026
06:00 PM - 7:30 PM	Project 10: Decision Tree Classifier using for Purchase Logistic Data Set  •   Purchase Dataset Features  •   DTC Visualization  •   DTC Prediction  •   Performance Metrics
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Leture 11: Deep Learning and Deep Neural Nets  •   Multi-layer Neural Networks  •   DNN Models  •   Dense and Sequential Architectures  •   NN Notation  •   Multi-layer Neural Nets  •   Gradient Descent  •   Backpropagation  •   Dropout Layers
	01th July, 2026
	Break Day
	02nd July, 2026
06:00 PM - 7:30 PM	Project 11: PYTHON-based Neural Network using PYTHON for Boston Housing Dataset  •   Boston Dataset Features  •   Sequential NN Model  •   Model Fitting  •   Training Epochs  •   Accuracy Performance
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 12: Convolutional Neural Networks (CNNs)  •   CNN Architectures  •   Convolution  •   Dot Product,  •   Padding  •   Hierarchical Structure  •   Max/ Average Pooling
	3rd July, 2026
06:00 PM - 7:30 PM	Project 12: Neural Network for analysis of Mobile Prices Dataset  •   Dataset Features  •   One Hot Encoding  •   Data Scaling  •   NN Model  •   Crossentropy  •   Adam Optimizer  •   Plots of Loss and Accuracy
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Distinguished Guest Lecture I: Dr. Bamdev Mishra, Principal Applied Scientist, Microsoft India, Bangalore
	Week-4
	6th July, 2026
06:00 PM - 7:30 PM	Project 13: Deep Learning for Fashion Classification using the MNIST Fashion Data Set  •   Fashion MNIST (Modified National Institute of Standards and Technology)      Dataset Description  •   MNIST Dataset Features and Classes  •   CNN Modeling  •   CNN Training  •   Sparse Categorical Crossentropy  •   Loss/ Accuracy Plotting Project 14: Deep Learning for Digit Classification using MNIST Digit DataSet  •   MNIST Handwritten Digit Dataset Features  •   CNN Architecture  •   Data Encoding  •   Softmax Activation  •   Confusion Matrix  •   Plots of Loss and Accuracy
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Distinguished Guest Lecture II: Dr. Dhananjay Ram, Senior Applied Scientist, Amazon Web Services (AWS), Novel Architectures for LLM Bellevue, Washington, United States
	7th July, 2026
06:00 PM - 7:30 PM	Project 15: Deep Learning using the CIFAR Dataset  •   CIFAR-10 dataset (Canadian Institute for Advanced Research, 10 classes)  •   Dataset Visualization  •   CNN Architecture  •   Model Building and Compilation  •   Classification Accuracy  •   Confusion Matrix Metrics
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 13: RNNs and LSTMs  •   Recurrent neural network  •    Long-term dependencies  •    Long Short Term Memory networks  •   Forget gate layer  •   Input gate layer  •    Output gate layer
	8th July, 2026
06:00 PM - 7:30 PM	Test prep 1:Test preparation 1  •   Interview problem solving session  •   Solution discussion
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Lecture 14: Transformers  •    Large language models  •    Transformer encoder  •    Query vector  •   Key vector  •   Attention mechanism  •    Value vector  •    Transformer decoder
	9th July, 2026
06:00 PM - 07:30 PM	Project 16: IMDB Dataset and Deep Learning for Movie Rating Classification  •   Internet Movie Database (IMDb) Dataset Description  •   Vectorization  •   Binary Crossentropy  •   Model Training  •   Training and Validation Accuracy Plots  •   Training and Validation Loss Plots
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Distinguished Guest Lecture III: Dr. Karthikeyan Shanmugam, Research scientist, Google DeepMind India, Bengaluru
	10th July, 2026
	Break Day
	15th July, 2026
06:00 PM - 7:30 PM	Lecture 17: Share price prediction using LSTM  •    LSTM Module  •    Share price dataset  •    LSTM Architecture  •    Model compilation  •   Model fit and share price prediction
7:30 PM-8:00 PM	Break
8:00 PM - 9:15 PM	Test prep 2:Test preparation 2  •   Interview problem solving session  •   Solution discussion