Professional Certificate Programme in AI, Machine Learning, and Deep Learning

• Overview of topics to be covered in the Programme 

• Motivation for the Programme 

• Overview of the Programme 

• Expected Outcomes of the Programme 

• Brief about software/tools 

[Taught by IIT Faculty and Domain Experts]

• Linear algebra: Vectors, matrices, inner products, matrix-vector multiplication, eigen values/vectors, singular value decomposition 

• Calculus: Differentiation (single/multiple variables, vectors, and matrices), unconstrained and constrained optimisation (Lagrangian multiplier) 

• Probability Theory: Discrete and continuous random variables, probability distributions, Bayes' rule, Gaussian density function, conditional probability 

• Statistics: Descriptive and inferential statistics, hypothesis testing, probability distributions

[Taught by IIT Faculty and Domain Experts]

• Python: Pre-read 

• Python details: Python syntax, factors, NumPy, Scipy, Pandas, Data Visualization, Scikit Learn, Pytorch,Matplolib, Seaborn Tensorflow, Deployment and productionisation 

• Advanced python techniques: generators, iterators, decorators, context managers, performance optimisation techniques. Demo on Python tools, python packages, pytorch, scikit learn, tensorflow, demo of deployment on python, demo on advanced python techniques 

[Taught by Domain Experts]

• EDA: Data types and variables, central tendency and dispersion 

• Five-point summary and skewness, Box-plot, covariance and correlation, encoding, scaling and normalisation.  

• Focus on pre-processing, missing values, working with outliers, demo on EDA

[Taught by Domain Experts]

• NLP and text processing applications: Text classification, parts-of-speech tagging, named entity recognition, text summarization, text question answering, machine translation. Demo on sentiment analysis, chatbot creation and text-to-text translation 

• Image and video processing applications: Image classification, image annotation, image captioning, video classification, video captioning, visual question answering, visual common-sense reasoning 

• Speech processing applications: Speech recognition, speaker recognition, speech emotion recognition, spoken language recognition, text-to-speech synthesis, speech-to-speech translation 

[Taught by IIT Faculty and Domain Experts]

• Supervised learning 

• Unsupervised learning 

• Semi-supervised learning 

• Active learning 

• Self-supervised learning 

• Transfer learning 

• Domain adaptation, Zero-shot 

• One-shot and Few-shot learning; Federated learning 

[Taught by IIT Faculty and Domain Experts]

• Linear model for regression 

• Supervised learning 

• Parameter estimation 

• Overfitting 

• Regularisation 

• Ridge regression 

[Taught by IIT Faculty and Domain Experts]

• K-nearest neighbour classifier 

• Bayes classifier 

• Normal density function 

• Decision surfaces 

• Naïve Bayes classifier 

• Maximum likelihood estimation 

• Gaussian mixture model 

[Taught by IIT Faculty and Domain Experts]

• Distance of a point to a hyperplane 

• Margin of a separating hyperplane 

• Hard-margin SVM 

• Soft-margin SVM 

• Kernel functions 

• Multi-class classification using SVMs

[Taught by IIT Faculty and Domain Experts]

• Principal component analysis 

• Fisher discriminant analysis

[Taught by IIT Faculty and Domain Experts]

• Construction of decision tree for classification 

• Random forest classifier 

[Taught by IIT Faculty and Domain Experts]

• Bagging 

• Boosting 

• AdaBoost 

• Applications of Ensemble methods 

[Taught by IIT Faculty and Domain Experts]

• K- -Means clustering 

• Hierarchical clustering 

• Applications of Clustering Techniques 

[Taught by IIT Faculty and Domain Experts]

• McCulloch-Pitts neuron 

• Perceptron learning rule 

• Sigmoidal activation function 

• ReLU activation function 

• Softmax activation function 

• Multilayer feedforward neural network 

• Error backpropagation method 

• Gradient descent method 

• Stochastic gradient descent method 

• Stopping criteria, Logistic regression-based classifier 

• Focus on Deep Learning using Tensorflow and Keras, understanding Feedforward neural network, back propagation, gradient descent and logistic regression 

[Taught by IIT Faculty and Domain Experts]

• Generalized delta rule 

• AdaM based optimizer 

• Regularization: Drop-out, Drop-connect, Batch normalization 

[Taught by IIT Faculty and Domain Experts]

• Basic CNN architecture, Rectilinear Unit (ReLU), 2-D Deep CNNs: LeNet, VGGNet, GoogLeNet, ResNet 

• Image classification using 2-D CNNs 

• 3-D CNN for video classification 

• 1-D CNN for text and audio processing 

• Object localization and detection algorithms – YOLO, Image Segmentation, and UNet 

[Taught by IIT Faculty and Domain Experts]

• Architecture of an RNN, Unfolding an RNN, Backpropagation through time 

• Long short-term memory (LSTM) units 

• Gated recurrent units 

• Bidirectional RNNs 

• Deep RNNs 

[Taught by IIT Faculty and Domain Experts]

• Structure of GAN, types of GAN models, applications of GAN models

[Taught by IIT Faculty and Domain Experts]

• Attention mechanism 

• Transformer architecture 

• BERT (Bidirectional Encoder Representations from Transformers) 

• ViLBERT 

• GPT (Generative Pre-trained Transformer) 

• Applications of transformer models 

[Taught by IIT Faculty and Domain Experts]

• Applications of Gen AI in different domains 

• Examples of prompt engineering, fine tuning and API creation and integration 

[Taught by IIT Faculty and Domain Experts]

• Markov Decision Processes (MDPs) 

• Q-Learning and Deep Q Networks (DQN) 

• Actor-Critic models 

• Exploration vs. Exploitation strategies 

[Taught by IIT Faculty and Domain Experts]

• The capstone project is a comprehensive, real-world assignment in which participants apply their knowledge and skills to solve industry-specific problems  

• It integrates concepts from their coursework, encouraging critical thinking and innovation  

• Capstone projects help participants gain hands-on experience, making them industry-ready by demonstrating their ability to tackle complex challenges in a professional setting 

[Taught by IIT Faculty and Domain Experts]

• Ethical considerations (banking, ecommerce sectors); pushing code to repository 

• Responsible AI 

• Explainable AI 

• Registry, Model & Data Monitoring  

[Taught by Domain Experts]

• Understanding cloud infrastructure essentials 

• Cloud-based ML Services and Databases 

• Containerization 

• Cloud enablement - scalability and flexibility 

• Understanding emerging themes: FaaS, Edge Computing 

• Federated Learning 

• AutoML 

• Explainable AI 

• Cloud ML-Ops 

• Deployment on Gemma models on Vertex AI and Kubernetes engine 

• Scaling with AWS

[Taught by Domain Experts]

• Embedding Models & Agent Memory

• Vector Search & Chunking Strategies

• Advanced RAG Architectures & Tuning

• Learning & Adaptation (Reinforcement Learning, Human Feedback)

• Deployment Options (Cloud, Serverless, Embedded)

• Monitoring & Observability (LangSmith)

• Responsible Agentic AI (Risks, Bias, Privacy, Safety Layers)

• Industry Case Studies & Future Trends

• Interactive Design Exercise: Architect Your Own Agent

• Introduction to Chatbots 

• Working with Intents 

• Working with Entities 

• Defining the Dialog 

• Deploying your Chatbot 

• Advanced Concepts – Part 1 

• Advanced Concepts – Part 2

• Overview of Tensors 

• Tensors 1D 

• Two-Dimensional Tensors 

• Derivatives in PyTorch 

• Simple Dataset 

• Dataset and Data Augmentation 

Yes, this is a 100% online AI and Machine learning training course by IITM Pravartak (The technological hub of IIT Madras). The course includes live online sessions, recorded lectures, AI and ML projects, and interactive discussions with IIT Madras faculty and domain experts. 

This IITM Pravartak AI and machine learning course covers: 

• Machine Learning Training (Supervised & Unsupervised Learning) 

• AI and ML Applications in business and industry 

• AI and ML Techniques for model building and optimization 

• Deep Learning, Neural Networks & NLP 

• Data Science, Predictive Analytics & AI Model Deployment 

Yes, the IITM Pravartak AI and Machine Learning course emphasises on real-world AI and ML projects. Participants work on practical applications using AI and ML tools such as TensorFlow, PyTorch, and Scikit-learn, ensuring a hands-on learning experience. 

This programme provides in-depth AI and Machine Learning training in: 

• Python & Jupyter Notebooks 

• Machine Learning Algorithms & Deep Learning Models 

• TensorFlow, Keras & PyTorch 

• AI and ML Applications in data analytics, NLP, and computer vision 

• Cloud-based AI and ML tools for deployment 

Yes, upon successfully completing this machine learning certificate programme, participants receive an AI and ML certification from IITM Pravartak, a prestigious credential that is widely recognized in the industry. 

This IITM Pravartak artificial intelligence certification stands out due to: 

• World-class faculty from IITM Pravartak 

• Practical AI and ML training with real-world projects 

• Recognition from IITM Pravartak, one of India’s top institutions 

• Industry-relevant AI and ML applications and case studies 

No prior AI or ML experience is required. However, a basic understanding of programming (Python), statistics, and data science is beneficial. This IITM Pravartak machine learning course is structured for both beginners and professionals. 

The Advanced Certificate Programme in Applied AI and ML equips you with industry-relevant AI and ML techniques to advance in roles like: 

• AI/ML Engineer 

• Data Scientist 

• Business Analyst 

• AI Researcher 

• Machine Learning Specialist 

Additionally, the IITM Pravartak artificial intelligence certification enhances your resume and career prospects. 

The IITM Pravartak AI and ML course runs for 11 months, with a flexible learning schedule. Fees and enrolment details can be found on the official course page. 

Professionals from diverse backgrounds - manufacturing, automation, data, and business - describe the IITM Pravartak AI, ML, and Deep Learning Programme as comprehensive, flexible, and career-transformative. Many highlight its strong conceptual foundation, IIT faculty expertise, and interactive weekly sessions that balance theory with application.

Common Highlights

• Well-structured learning path: Learners appreciate the blend of pre-recorded IIT faculty lectures and weekly live expert-led sessions that fit well into busy schedules.

• Accessible for all backgrounds: Non-technical learners find the fundamentals approachable, while technical professionals value the programme’s depth and progression.

• Applied learning focus: Weekly quizzes, projects, and practical discussions are praised for reinforcing real-world understanding.

• Faculty excellence: Mentions of Prof. Amitendra, Mr. Satya, and Mr. Wajahat reflect appreciation for their clear explanations and supportive teaching approach.

• Support and platform experience: The support team is noted as responsive and proactive, improving learner experience with platforms like Canvas and Vocareum.

Areas for Improvement

• Learners suggest adding more domain-specific examples, extra practice assignments, and improved recording quality for lectures.

• A few recommend deeper theoretical coverage for advanced learners and more discussion around projects for non-technical participants.

Overall sentiment: Learners describe the programme as “a great experience,” “rewarding,” and “a crucial platform for upskilling.” Many credit it with boosting their confidence in AI and ML and bridging the gap between traditional roles and modern AI-driven work.

Yes, there is an optional two-day campus immersion available to learners at the IIT Madras Research Park where they will get to meet the programme faculty. The learners will also get a chance to connect with fellow AI, ML, and deep learning experts on the campus.

The AI, Machine Learning, and Deep Learning course by IITM Pravartak is a deep dive into the technical applications of AI from baseline. The 10 month curriculum is designed for more comprehensive learning and includes concepts from both GenAI and Agentic AI. Its primary focus is to impart a fundamental understanding about how AI, ML, and deep learning work.

On the other hand, the Generative AI and Machine Learning Programme by IITM Pravartak is a course that focuses on the primary application of Generative AI and ML. At just 7 months, the course is designed to help learners grasp advanced implementations of the GenAI through dedicated projects, tools, specialisations, and use cases for business use.