Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study, Virtual Classroom, Campus Based/Physical Classroom | Video and Text Based |
Course Overview
The Certificate Programme in Machine Learning and Deep Learning course provides a comprehensive understanding of methodologies, applications, and principles of ML and DL. The course is a 6-month duration programme and is conducted in Direct-to-device mode. This course in collaboration with Timespro equips the participants with the required skills and insights of Artificial Intelligence (AI).
The course provides programming with Python, an introduction to data analytics, applied mathematics and applications of ML and DL. The Certificate Programme in Machine Learning and Deep Learning by IIT Delhi is designed for graduates of Science or Engineering and professionals working in the Software, and IT industry, and aspiring Data Engineers, Data Scientists, and ML Engineers.
The Highlights
- 6 Months Duration Course
- E-certificate from CEP, IIT Delhi
- 76 Hours of Live Online Sessions
- 3 weeks Capstone Project
- 4 - 6 hours Masterclass on ChatGPT
Important dates
Course Commencement Date
Start Date : 04 Jan, 2025
Programme Offerings
- live online sessions
- Direct-to-Device Mode
- One-Day Campus Immersion
- career support
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | IIT Delhi |
The Certificate Programme in Machine Learning and Deep Learning total fee is Rs 1,99,420 with GST of 18%. The candidates can pay the course fee to the IITD CEP Account only.
Certificate Programme in Machine Learning and Deep Learning Fee Structure
Certification Course | Fees |
Certificate Programme in Machine Learning and Deep Learning | Rs 1,69,000 |
GST@18% | Rs 30,420 |
Total Fees | Rs 1,99,420 |
Eligibility Criteria
Academic Qualifications
The eligibility criteria to join the Certificate Programme in Machine Learning and Deep Learning course is that the students must have pursued a B.E/B.Tech/M.E/M.Tech/BIT/MIT/BCA/MCA/MCM (any stream) or B.Sc/M.Sc/BS/MS in Mathematics, Statistics, Electronics, Physics, Computer Science, AI, and DS.
Certification Qualifying Details
To obtain a certificate, the candidates must gain at least 50% marks overall and have a minimum attendance of 50% to receive a ‘Certificate of Successful Completion.’ The candidates who score less than 50% marks overall and have a minimum attendance of 50%, will receive a ‘Certificate of Participation’.
What you will learn
Upon completion of the Certificate Programme in Machine Learning and Deep Learning syllabus, students will become efficient in Python programming and will be able to develop, load and pre-process the data from online to offline using various applications. They will also gain a deep understanding of various challenges in ML and its fundamental aspects.
After completing the Certificate Programme in Machine Learning and Deep Learning training, the participants will be able to apply various ML and DL techniques in real-world applications. They will also gain an in-depth understanding of popular ML approaches and will be able to design and train their neural networks using Keras and TensorFlow modules.
Who it is for
This certification course is designed for aspiring students and working professionals in the field of machine learning and deep learning to enhance their required knowledge and skills. This certification course is also beneficial for:
Admission Details
To join the Certificate Programme in Machine Learning and Deep Learning classes, follow the steps mentioned below:
Step 1: Browse the link mentioned below:
https://timespro.com/executive-education/iit-delhi-certificate-programme-in-machine-learning-and-deep-learning
Step 2: Click on the "Enroll Now" button, fill out the application form and submit it.
Step 3: Log in with the registered email ID or continue with Google.
Step 4: Select the course and register.
Step 5: The programme advisors will contact the participants and provide counselling.
Step 6: Submit the required documents and get them verified.
Step 7: Aspirants are required to attend the interview.
Step 8: Participants will obtain an offer letter and they are required to provide acceptance.
Step 9: Students can pay the preliminary course fee, complete onboarding and begin the course.
The Syllabus
- Foundations of Python Programming
- Functional Programming in Python
- Data Structures, Loops, and Control Structures
- Numerical Computations and Linear Algebra using NumPy
- Data Pre-processing using Pandas
- Data Visualisation using Matplotlib
- Introduction to Scikit-learn
- 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
- 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
- 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
- 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 online 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
Basics of Deep Learning
- Importance of deep learning
- Learning from large datasets
- Types of data and architectures
- End-to-end model design for feature learning and decision-making
Convolutional Neural Network (CNN)
- Architecture design
- Training methodology of CNN
- Use cases
- State-of-the-art CNN models
- Python demo on object detection/image classification
Autoencoder (AE)
- Deep learning for unsupervised learning
- Architecture design of AE
- Convolutional AE
- Training with unlabeled data
- Use cases
- Python demo in denoising, dimensionality reduction
Generative Modelling
- Subtopic 1 - Variational Autoencoder (VAE)
- Fundamentals of generative modeling
- Architecture of VAE
- Estimating data distribution
- Training methodology of VAE
- Use cases
- Python demo for image generation
Generative Modelling
- Subtopic 2 - Generative Adversarial Network (GAN)
- Generative modeling as a game-theoretic approach
- Architecture design of GAN
- Training methodology of GAN
- Use cases
- Python demo on image generation, style transfer
- Subtopic 3 - Diffusion
- Generative modeling through denoising
- Architecture design of diffusion models
- Training of diffusion models
- Python demo on high-quality image generation
Attention and Transformer
- Attention mechanism
- Advantages of Attention
- Architecture design of Transformers
- Training of Transformer
- Python demo on language translation using Transformer
Special Topics
- Transfer learning
- Leverage knowledge from one task to improve performance on another task
- Pre-training on large datasets
- Fine-tuning DL models on a small dataset
- Use cases
- Python demo on transfer learning in computer vision
Special Topics
- Knowledge distillation
- Optimization of DL models
- Transfer knowledge from a complex teacher model to a simpler student model
- Training methodology for distillation
- Use cases
- Python demo on knowledge distillation in computer vision and natural language processing
Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM)
- Modelling of time-series data
- Architecture design of RNN
- Training methodology of RNN
- Architectures of LSTM and advantages over RNN
- Use cases
- Python demo on machine translation, stock prediction
- Industry use cases and applications of computer vision
- Case studies in computer vision
- Latest trends in computer vision
- Latest industry use cases and applications of speech recognition
- Case studies in speech recognition
- Latest trends in speech recognition
- Latest industry use cases and applications of NLP
- Case studies in NLP
- Latest trends in NLP
Evaluation process
The students must score 50% marks in the MCQ-based exam, 20% marks in the assignments and quizzes, 20% marks in the Capstone Project and 10% in Attendance.
Instructors
IIT Delhi Frequently Asked Questions (FAQ's)
The duration of this certification programme is 6 months. The certification course provides 76 hours of live online sessions by IIT Delhi faculty and industry experts.
Yes, the certificate course is available on weekends only. The timings of this course are Saturdays and Sundays from 10:00 a.m. to 12:00 p.m.
80% of the total fee is refunded (excluding the applicable tax amount) if candidates withdraw from the course within 15 days from the programme start date. Withdrawing after 15 days is not applicable.
Participants can register for this certification course by visiting the TimesPro website, clicking on the "Enrol Now” button, filling in the details and submitting. Students will get a callback for further processing.
The selection process of the candidates is based on the review of the application and an interview conducted by the faculty if required.