logo

Course Starts
4th January, 2025

Course Fees
₹1,69,000 + GST

Duration
06 Months

Programme Overview

Secure your future in the exciting field of transformative technologies with IIT Delhi’s Certificate Programme in Machine Learning and Deep Learning. This programme is designed to equip professionals with a comprehensive understanding of machine learning and deep learning techniques, along with their practical applications in addressing real-world business challenges. The IIT Delhi Machine Learning and Deep Learning programme programme encompasses a variety of topics, including supervised and unsupervised learning, deep neural networks, convolutional neural networks, and natural language processing

Course Highlights

Design and train your custom-built Neural Networks using Keras and TensorFlow

Masterclasses on ChatGPT

Learn industry relevant tools

Campus visit at IIT Delhi

76 hours of live online sessions by IIT Delhi faculty and industry experts

Flexibility to custom create your Capstone Project

Course Content

Module 1 - Fundamentals of Python for Machine Learning

  • Foundations of Python Programming
  • Functional Programming in Python
  • Data Structures, Loops, and Control Structures

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.

Module 2 - Data Processing for Machine Learning

  • 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.

Module 3 - Mathematical Foundations for Machine Learning

  • Linear Algebra: Vectors, Matrices, Norms, Subspaces, Projections, SVD, EVD, Derivatives of Matrices, Vector Derivative Identities, Least Squares
  • Optimization: Constrained and Unconstrained Optimization, Maxima and Minima, Convex and Non-Convex, Gradient and Hessian, Positive Definite and Semi-Definite, Second Derivative Test, Steepest Descent, Adam, AdaGrad, RMSProp, KKT
  • Probability Theory: Discrete and Continuous Random Variables, Conditional Probability, Joint Probability Distribution, Multivariate, MAP Criterion, 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.
  • Delves into optimisation techniques, including gradient descent and convex optimisation, empowering to optimise models and algorithms effectively.

Module 4 - Artificial Intelligence Terminologies and Data Analysis

  • 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

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.

Read More >

Module 5 - Fundamentals of Machine Learning and Algorithms

  • Machine Learning Problems: Classification, Regression, Interpolation, and Density Estimation
  • Linear Regression Model, Classification Model, and Classification Evaluation
  • Learning Algorithms: Supervised and Unsupervised
  • Bayesian Decision Theory: Bayesian Classifier, Discriminant Functions, 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), Density Estimation
  • K-means Clustering
  • Decision Tree (Entropy, Gini Impurity Index)
  • Support Vector Machine (SVM)
  • Random Forest, Ensemble Learning, Bagging, Boosting

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).

Module 6 - Neural Networks

  • 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, Regularization, Cross-Validation, Early-Stopping Criteria
  • Demonstration of All Machine Learning Algorithms 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.

Module 7 - Fundamentals of Deep Learning, Architectures and Recent Advances

  • Basics of Deep Learning
    1. Importance of deep learning
    2. Learning from large datasets
    3. Types of data and architectures
    4. End-to-end model design for feature learning and decision-making
  • Convolutional neural network (CNN)
    1. Architecture design
    2. Training methodology of CNN
    3. Use cases
    4. State-of-the-art CNN models
    5. Python demo on object detection/image classification
  • Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM)
    1. Modeling of time-series data
    2. Architecture design of RNN
    3. Training methodology of RNN
    4. Architectures of LSTM and advantages over RNN
    5. Use cases
    6. Python demo on machine translation, stock prediction
  • Autoencoder (AE)
    1. Deep learning for unsupervised learning
    2. Architecture design of AE
    3. Convolutional AE
    4. Training with unlabeled data
    5. Use cases
    6. Python demo in denoising, dimensionality reduction
  • Generative Modelling

      Subtopic 1 - Variational Autoencoder (VAE):

    1. Fundamentals of generative modeling
    2. Architecture of VAE
    3. Estimating data distribution
    4. Training methodology of VAE
    5. Use cases
    6. Python demo for image generation

      Subtopic 2 - Generative Adversarial Network (GAN):

    1. Generative modeling as a game-theoretic approach
    2. Architecture design of GAN
    3. Training methodology of GAN
    4. Use cases
    5. Python demo on image generation, style transfer

      Subtopic 3 - Diffusion:

    1. Generative modeling through denoising
    2. Architecture design of diffusion models
    3. Training of diffusion models
    4. Python demo on high-quality image generation
  • Attention and Transformer:
    1. Attention mechanism
    2. Advantages of Attention
    3. Architecture design of Transformers
    4. Training of Transformer
    5. Python demo on language translation using Transformer
  • Transfer learning
    1. Leverage knowledge from one task to improve performance on another task
    2. Pre-training on large datasets
    3. Fine-tuning DL models on small dataset
    4. Use cases
    5. Python demo on transfer learning in computer vision
  • Knowledge distillation
    1. Optimization of DL models
    2. Transfer knowledge from a complex teacher model to a simpler student model
    3. Training methodology for distillation
    4. Use cases
    5. Python demo on knowledge distillation in computer vision and natural language processing

Learning Outcomes

  • Understand the advantages of deep learning.
  • Gain in-depth knowledge of deep architectures such as CNNs, RNNs, LSTMs, GRUs, Attention mechanisms, Transformers, and Autoencoders.
  • Theoretical and practical understanding of the architectures, along with insights into design choices for better model development.
  • Learn essential model training concepts like regularisation, dropout, data augmentation, batch normalisation, and hyperparameter tuning are explored for effective optimisation.
  • Understand popular generative methods for AI applications such as VAEs, GANs, and Diffusion models are discussed alongside advanced topics like transfer learning, knowledge distillation, network pruning, and quantisation.
  • Hands-on demos using TensorFlow and PyTorch on images, text, time series, language data, etc., are included for all architectures, equipping with practical skills to excel in the field of deep learning.

Module 8 - Computer Vision

  • Industry use cases and applications of computer vision
  • Case studies in computer vision
  • Latest trends in computer vision

Learning Outcomes

Gain an overview of computer vision and its industry applications.

Module 9 - Speech Recognition

  • Latest industry use cases and applications of speech recognition
  • Case studies in speech recognition
  • Latest trends in speech recognition

Learning Outcomes

  • Gain fundamental understanding of speech recognition.
  • Acquire the knowledge about applications and latest trends of speech recognitions along with the challenges involved.

Module 10 - Natural Language Processing

  • Latest industry use cases and applications of NLP
  • Case studies in NLP
  • Latest trends in NLP

Learning Outcomes

  • Get introduced to the concept of NLP.
  • Also, learn about the industry applications and common tasks of NLP.

Capstone Project

  • Bring Your Own Project

Read Less <

ML/DL TOOLS USED

CERTIFICATION

  • Candidates who score at least 50% marks overall and have a minimum attendance of 50%, will receive a ‘Certificate of Successful Completion'
  • Candidates who score less than 50% marks overall and have a minimum attendance of 50%, will receive a ‘Certificate of Participation’.
  • The organising department of this programme is the Department of Electrical Engineering, IIT Delhi.

Note: For more details download brochure.

Testimonials

Mathematics can do magic! During my academic years I was just doing the math to pass exams, but after this course, I know now from here where I need to go. I had to go through the recordings 3-4 times but every time I learned something new and understood why IIT is awesome.
Brajesh, System Administrator

Now I have an in-depth understanding of how any AI application works. I am confident that I can explore and innovate some new AI-based applications for our OTT/Broadcast industry. Overall, excellent experience and a very knowledgeable faculty.
Sunil, IT Engineer

The knowledge that is given is very nice and the lecturers conveyed that knowledge easily. The knowledge that was given was lucid and concepts were cleared at every step. There were doubts clearing sessions. The study material that was provided was very easily understood. The teacher to student ratio was also precise. The video quality was very clear and there were video lectures recorded that can be downloaded for use. The reading material provided detail understanding.
Shubhrans Kukareti

ELIGIBILITY CRITERIA

  • Educational Background:
    - BE/B.Tech/ME/MTech/BIT/MIT/BCA/MCA/MCM (any stream)
    - BSc/MSc/BS/MS in Mathematics, Statistics, Electronics, Physics, Computer Science, AI, DS

Class Schedule

Weekend Session: Saturdays & Sundays: 10:00 A.M. to 12:00 P.M.

Meet Our Programme Coordinator

Dr. Manav Bhatnagar
Professor, Department of Electrical Engineering, Indian Institute of Technology Delhi

Dr. Manav Bhatnagar is currently a Professor with the Department of Electrical Engineering, IIT Delhi, New Delhi, India, where he is also a Brigadier Bhopinder Singh Chair Professor. He holds a global rank of 517 in the area of Networking and Telecommunications among the top 2% of scientists in a global list compiled by the prestigious Stanford University. He is a Fellow of IET, INAE, NASI, IETE, and OSI. He has received the prestigious NASI-Scopus Young Scientist Award, the Shri Om Prakash Bhasin Award, and the Dr. Vikram Sarabhai Research Award. He has been an Editor of the IEEE Transactions on Wireless Communications during 2011–2014. Currently, he is an Editor of the IEEE Transactions on Communications. He has published more than 100 high-quality IEEE journal papers, of which 10 are single-authored. His research interests include signal processing for MIMO systems, free-space optical communication, satellite communications, and machine learning.

Meet Our Expert Faculty

DR. TANMOY CHAKRABORTY
Associate Professor, Department of Electrical Engineering, Indian Institute of Technology Delhi

Dr. Tanmoy Chakraborty holds the positions of Associate Professor of Electrical Engineering and Associate Faculty of the Yardi School of AI at IIT Delhi. Previously, he served as an Associate Professor of Computer Science at IIIT Delhi, where he also held the roles of head of the Infosys Centre for AI and Project Director of the Technology Innovation Hub. He leads the Laboratory for Computational Social Systems (LCS2), a research group specializing in Natural Language Processing, Computational Social Science, and Graph Mining. His current research primarily focuses on empowering frugal language models for applications such as mental health and Cyber-informatics.

Tanmoy obtained his PhD from IIT Kharagpur in 2015 as a Google PhD scholar and worked as a postdoctoral researcher at the University of Maryland, College Park. Tanmoy has received numerous awards and honors, including the Ramanujan Fellowship, faculty awards/gifts/grants from industries like Facebook, Google, Accenture, LinkedIn, the PAKDD'22 Early Career Award, IEI Young Engineers Award, and the Paired Indo-German Early Career Award, and several faculty excellence awards. He is an ACM Distinguished Speaker and has authored two books: "Social Network Analysis'' (a textbook) and "Data Science for Fake News.

Read More >

DR. MANOJ B R
Assistant Professor, Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati

Dr. Manoj B R is an Assistant Professor in the Department of Electronics and Electrical Engineering at the Indian Institute of Technology Guwahati, India. He received a B.E. degree in Electronics and Communication Engineering from the Visvesvaraya Technological University, India, in 2007, a M.Tech. degree in Signal Processing from the Indian Institute of Technology Guwahati, in 2011, and a Ph.D. in Wireless Communications from the Indian Institute of Technology Delhi, in 2019. He has gained a mixed exposure to academic and industrial backgrounds.

Before joining IIT Guwahati, he was an Early Doctoral Research Fellow with the Indian Institute of Technology Delhi; a Postdoctoral Researcher with the Division of Communication Systems, Department of Electrical Engineering, Linköping University, Sweden; and a Senior Researcher with the Radio Transmission Technology Lab, Huawei Technologies, Stockholm, Sweden. His research interests include wireless communication and networks, machine learning, deep learning for wireless communications and signal processing, security and robustness of deep learning-based wireless systems, large-scale sensing using radio signals, buffer-aided relaying networks, Markov chains and their applications, diversity combining, and multi-hop communications.

DR. ANIRBAN DASGUPTA
Assistant Professor, Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati

Dr. Anirban Dasgupta is an Assistant Professor in the Department of Electronics and Electrical Engineering at the Indian Institute of Technology (IIT) Guwahati. He received his doctorate (Ph.D.) in Electrical Engineering from the Indian Institute of Technology Kharagpur in 2019, his Master of Science (MS) by research in Electrical Engineering from the Indian Institute of Technology Kharagpur in 2014, and his Bachelor of Technology (B.Tech.) in Electrical Engineering from the National Institute of Technology, Rourkela, in 2010. He was the co-founder of the start-up company 'Humosys Technologies Private Limited', and worked there as a Chief Technical Officer (CTO) from January 2019 to July 2021. In July 2021, he joined Boeing India Private Limited, Bengaluru, as a Data Scientist, and worked there till November 2021. From December 2021 onwards, he is associated with IIT Guwahati. He has ten publications in peer-reviewed international journals, which include five IEEE Transactions.

He has also filed three Indian patents and published 16 IEEE conferences and one book chapter. His research areas include machine learning, the internet of things, digital signal and image processing for human cognition, and affective computing. He has served as a reviewer in more than 10 journals, which include IEEE Transactions on Signal Processing, IEEE Transactions on Image Processing, and IEEE Transactions on Pattern Recognition and Machine Learning.

DR. AASHISH MATHUR
Assistant Professo, Department of Electrical Engineering, Indian Institute of Technology Jodhpur

Dr. Aashish Mathur (Senior Member, IEEE) received the B.E. degree (Hons.) in Electronics and Instrumentation Engineering from the Birla Institute of Technology and Science, Pilani, Pilani, Rajasthan, India, in 2011, the M.Tech. degree in Telecommunication Technology and Management from IIT Delhi, New Delhi, India, in 2013, and the Ph.D. degree in power line communications from the Department of Electrical Engineering, IIT Delhi. He was a Software Engineer with Intel Technology India Pvt. Ltd., Bangalore, India, briefly before joining IIT Delhi for his PhD in 2013. He is currently an Assistant Professor with the Department of Electrical Engineering, IIT Jodhpur, India. He has also worked as an Assistant Professor with the Department of Electrical and Electronics Engineering, BITS Pilani, Pilani Campus, and the Department of Electronics Engineering, IIT (BHU), Varanasi.

He was engaged as a visiting faculty at the Indian Institute of Information Technology, Kota, India, for the 2nd Semester, 2018-19. He received the Best Student Paper Award for his co-authored paper at the 2017 Conference on Decision and Game Theory for Security (GameSec 2017), Vienna, Austria. He was awarded the Early Career Research Award by the Science and Engineering Research Board, DST, Government of India, in 2019. He was awarded the Teaching Excellence Award at IIT Jodhpur in 2019. He served as an Adjunct Faculty (part-time) from 2019–2022 on the 5G testbed project at IIT Delhi. He was recognised as an Exemplary Reviewer 2021 for IEEE Transactions on Communications. His research interests include power line communications, visible light communications, free-space optical communications, and physical layer security. He has published research papers in reputed IEEE journals and conferences. Some of his research works have appeared as popular articles in IEEE Communications Letters. He has also served as a reviewer for reputed IEEE journals and conferences.

Nayan Moni Baishya
Senior Research Scholar, Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati

Nayan Moni Baishya is a Senior Research Scholar in the Image Processing and Computer Vision (IPCV) Lab at the Department of Electronics and Electrical Engineering, IIT Guwahati, under the guidance of Prof. P.K. Bora and Prof. Salil Kashyap. His current research interest focuses on developing end-to-end deep learning (DL)-based systems for image manipulation detection and localization. He is also a Junior Research Fellow under Prof. Manoj B. R., working on the project "Secure and Reliable Techniques for Deep Learning-based 5G and Beyond Wireless Systems". He received his B.Tech. degree in Electronics and Electrical Engineering from IIT Guwahati in 2016. His broader research interests include Computer Vision, Multimedia Forensics, Applied DL, and DL security. He has 7+ years of practice experience in applying ML and DL algorithms for different problem scenarios, with in-depth technical expertise in Python, TensorFlow, PyTorch, Scikit-Learn, NumPy, etc. He has conducted workshops on the foundations and applications of ML and DL at IIT Guwahati.

Dr. Pratiti Paul
Presidential Postdoctoral Fellow, Virginia Tech, USA

Dr. Pratiti Paul is the recipient of the Presidential Postdoctoral Fellowship and is currently working at Virginia Tech, Arlington, USA. Before joining Virginia Tech, she had worked as a Research Associate at the University of Edinburgh, UK. She received her Ph.D. from the Indian Institute of Technology, Delhi, in 2023. She has published multiple research papers in reputed peer-reviewed IEEE journals, magazines, and conferences. She is also serving as a technical reviewer for IEEE Transactions on Communication and the IETE Journal of Research. Her research interests include free-space optical communications, multiple-input multiple-output systems, radar signal detection, signal processing, physical layer security, and machine learning applications in wireless communications.

Read Less <