CEP, IIT Delhi Advanced Certificate Programme in AI ML and DL - Batch 08

• Foundations of Python Programming
• Functional Programming in Python
• Data Structures, Loops, and Control Structures
• Object oriented programming in python.

Learning Outcomes

• Covers essential Python programming concepts, including basic syntax and data types, control sequences like loops and conditional statements, and writing functions and classes.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Numerical Computations and Linear Algebra Using NumPy
• Data Pre-processing Using Pandas
• Data Visualisation Using Matplotlib
• Introduction to Scikit-learn

Learning Outcomes

• Learn about file handling with python, plotting and visualization with Matplotlib, arrays, and matrices with NumPy, scientific computing with Numpy and data handling with pandas.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Linear Algebra: Vectors, Matrices, Norms, Subspaces, Projections, SVD, EVD, Derivatives of Matrices, Vector Derivative Identities, and Least Squares
• Optimisation: Constrained and Unconstrained Optimisation, Maxima and Minima, Convex and Non-Convex, Gradient and Hessian, Positive Definite and Semi-Definite, Second Derivative Test, Steepest Descent, Adam, AdaGrad, RMSProp, and KKT
• Probability Theory: Discrete and Continuous Random Variables, Conditional Probability, Joint Probability Distribution, Multivariate, MAP Criterion, and ML Criterion

Learning Outcomes

• Gaining an understanding of the mathematical fundamentals crucial for machine and deep learning success, like linear algebra, probability theory, and optimisation methods.
• In linear algebra, master essential operations involving vectors and matrices and the understanding of eigenvalues and eigenvectors.
• Probability theory will provide concepts on probability distributions and Bayes' theorem, which is crucial to understanding the probabilistic nature of machine learning algorithms.
• Furthermore, it delves into optimisation techniques, including gradient descent and convex optimisation, empowering to optimise models and algorithms effectively.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Differences between Artificial Intelligence, Machine Learning, and Deep Learning
• Differences between Statistical Approach, Shallow Learning, and Deep Learning
• Data Types and their Properties
• Attribute Types
• General Characteristics of Datasets
• Data Measurement Criteria: Precision, Bias, and Accuracy
• Data Pre-processing Techniques
• Distance-based Dissimilarities Between Datasets
• Machine Learning Problems: Classification, Regression, Interpolation, and Density Estimation
• Linear Regression Model, Classification Model, and Classification Evaluation
• Learning Algorithms: Supervised and Unsupervised

Learning Outcomes

• Understand and differentiate between key concepts like AI, Machine Learning, and Deep Learning.
• Gain a strong foundation in data properties, types, and characteristics of datasets.
• Evaluate data quality using metrics like precision, bias, and accuracy, and explore pre-processing techniques for data preparation.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Bayesian Decision Theory: Bayesian Classifier, Discriminant Functions, and Minimum Error Rate Classification
• Naïve Bayes Classifier
• Logistic Regression Model and Parameter Estimation (Maximum-Likelihood)
• Dimensionality Reduction Technique: Principal Component Analysis (PCA)
• Non-parametric Techniques: K-Nearest Neighbour (KNN) and Density Estimation
• K-means Clustering
• Decision Tree (Entropy, Gini Impurity Index)
• Demonstration of All Machine Learning Algorithms

Learning Outcomes

• Gain proficiency in data analysis and visualisation techniques essential for extracting insights from datasets.
• Dive into various machine learning algorithms, including supervised, unsupervised, and reinforcement learning and tasks such as classification and regression.
• Understand the theoretical background of supervised methods like Linear and Logistic regression, SVM, decision trees and unsupervised methods, including clustering, KNN, and dimensionality reduction techniques (PCA).

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Neurons, Perceptron Convergence Theorem, Relation between the Perceptron and Bayes' Classifier, Batch Perceptron Algorithm, Adaptive Filtering Algorithm, Least Mean Square (LMS) Algorithm, Multilayer Perceptron, Feedforward Operation, Batch and On-line Learning, Activation Function, Backpropagation Algorithm, Rate of Learning, Stopping Criteria, XOR Problem, Loss Function, Bias and Variance, Regularisation, Cross-Validation, and Early-Stopping Criteria, VM, Radial Basis Function, Bagging and Boosting
• Support Vector Machine (SVM)
• Random Forest, Ensemble Learning, Bagging, and Boosting
• Python Demo on construction and training of neural networks for classification and regression applications.

Learning Outcomes

• Delve into the theory and design of Artificial Neural Networks (ANNs) for classification and regression tasks, mastering essential concepts like backpropagation and stochastic gradient descent for training ANNs.
• Gain the necessary practical skills to implement all the algorithms using Python libraries like NumPy, pandas, scikit-learn, and Keras.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Basics of Deep Learning: Importance, Large Datasets, Architectures, End-to-end Model Design
• Convolutional Neural Network (CNN): Architecture Design, Training, Use Cases, State-of-the-art Models, Python Demo
• Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM): Time-series Data, Training, Architectures, Python Demo
• Autoencoder (AE): Unsupervised Learning, Convolutional AE, Training with Unlabelled Data, Python Demo
• Generative Modelling: Variational Autoencoder (VAE), Generative Adversarial Network (GAN), Diffusion Models, Python Demos
• Attention and Transformer: Mechanism, Advantages, Architecture Design, Training, Python Demo
• Transfer Learning: Knowledge Leverage, Pre-training, Fine-tuning, Use Cases
• Knowledge Distillation: Optimisation, Teacher-Student Model, Training Methodology

Learning Outcomes

• Understand the advantages of deep learning and gain in-depth knowledge of CNNs, RNNs, LSTMs, Transformers, and Autoencoders.
• Learn essential model training concepts like regularisation, dropout, data augmentation, and hyperparameter tuning.
• Understand popular generative methods like VAEs, GANs, and Diffusion alongside transfer learning and knowledge distillation.
• Equip with practical skills using TensorFlow and PyTorch for images, text, and time-series data.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Computer Vision: Industry Use Cases, Case Studies, Latest Trends
• Speech Recognition: Industry Use Cases, Case Studies, Latest Trends
• Natural Language Processing (NLP): Industry Use Cases, Case Studies, Latest Trends
• RAG (Text and Multimodal) and Agentic AI

Learning Outcomes

• Gain an overview of computer vision and speech recognition industry applications.
• Acquire knowledge about applications and latest trends of speech recognition challenges.
• Understand the concept of NLP and its common industry tasks.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• No-coding machine learning laboratory platform exploration.
• Explore AI models through an intuitive visual environment.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• No-coding deep learning laboratory platform exploration.
• Explore neural networks through interactive experimentation and visual analysis.

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.

• Bring Your Own Project (BYOP)

Disclaimer: The list of tools and topics mentioned is indicative and may be modified as per programme requirements and at the discretion of the Programme Coordinator.