IIT Delhi Certificate Programme in Machine Learning and Deep Learning

About Course

It has been proven in recent years that deep learning and machine learning approaches provide far higher accuracy than previous approaches. Deep Learning and Machine Learning are going to impact every area of computing, including data analysis, software engineering, and artificial intelligence. Professionals like you are expected to have a solid understanding of Machine Learning and Deep Learning. IIT Delhi’s Certificate Programme in Machine Learning and Deep Learning is designed for those who are looking to gain hands-on experience in solving real-life problems using Deep Learning and Machine Learning.

Programme Page: https://timespro.com/executive-education/iit-delhi-certificate-programme-in-machine-learning-and-deep-learning

Brochure: https://timesproweb-static-backend-prod.s3.ap-south-1.amazonaws.com/IITD_PGCMLDL_f87ab7b8c0.pdf

Have a good grasp of efficient Python programming including developing the skill to load and pre-process the data from online and offline databases using pandas
Have a good understanding of the fundamental aspects and challenges of ML: data, model selection, model complexity, etc.
Understanding of the strengths and weaknesses of popular ML approaches
Able to design and train your own neural networks using Keras and TensorFlow modules
Able to design and implement various ML/DL techniques in a range of real-world applications

Course Content

Module 1: Programming with Python

Foundations of Python Programming
Data structures in python, loops, and control structures
Functional programming in python
Linear Algebra using NumPy
Data pre-processing using Pandas
Data Visualization using Matplotlib
Scikit-learn

Module 2: Mathematical Foundation

Module 3: Machine Learning & Neural Networks

Introduction to AI/ML/DL and Data Analysis
Linear regression model
Introduction: Supervised & Unsupervised Learning, Classification & Regression Models
Bayesian Decision Theory: Bayesian Classifier, Discriminant Functions, Minimum Error Rate Classification
Naïve Bayes Theory with example
Logistic regression model
Parameter Estimation-Maximum likelihood
Principal component analysis
Non-parametric techniques: k-nearest neighbor, density estimation
Decision Tree with example (Entropy, Gini impurity index)
Neurons, Perceptron, Multilayer Perceptron, LMS, Feedforward Operation, Backpropagation Algorithm, Activation Function, Loss Function, XOR problem, Cross-validation, Regularisation, Demonstration on classification and regression applications
Radial Basis Functions and K-means clustering
Support Vector Machine (SVM)
Random Forest, Ensemble Learning, Bagging, Boosting

Module 4: Deep Learning

Module 5: Applications of Machine Learning

Tools

Hands-on Projects and Case Studies

MNIST digit recognition using DNN, CNN, and SVM
Classification of Real news and Fake news using decision trees
Prediction of the iris flower species using Naive Bayes classification
Classify Photos of Dogs and Cats using Deep Convolutional Neural Network
To build a movie recommender model using K-means clustering
Identification of IoT devices using experimental radio spectrum dataset and deep learning
German Traffic Sign Recognition Benchmark: Develop a Feed Forward Neural Network and then a Convolutional Neural Network to classify between the different Road Signs in the dataset given below. Test it using images from the internet to validate the functioning of your model
CIFAR-10 Object Recognition: Develop a Convolutional Neural Network to classify between the different classes of the Dataset given below. Test it using images from the internet
Sentiment Analysis using Naive Bayes Classifier
Application of Deep Learning in Medical Diagnosis using Health Data
Credit Card Fraud Detection using Random Forest Classifier
Music Recommendation System using K-NN Algorithm
Image Compression using K-means Clustering

About Course

What Will You Learn?

Course Content

Module 1: Programming with Python

Foundations of Python Programming

Data structures in python, loops, and control structures

Functional programming in python

Linear Algebra using NumPy

Data pre-processing using Pandas

Data Visualization using Matplotlib

Scikit-learn

Module 2: Mathematical Foundation

Linear Algebra: Vectors, Matrices, Norms, Subspaces, Projections, SVD, EVD, Derivatives of matrices, Vector derivative identities, least squares

Optimization: Gradient Descent, Second derivative test, constrained optimization, KKT

Probability Theory: Discrete and continuous random variables, conditional probability, joint probability distribution, multivariate, MAP criterion, ML criterion

Module 3: Machine Learning & Neural Networks

Introduction to AI/ML/DL and Data Analysis

Linear regression model

Introduction: Supervised & Unsupervised Learning, Classification & Regression Models

Bayesian Decision Theory: Bayesian Classifier, Discriminant Functions, Minimum Error Rate Classification

Naïve Bayes Theory with example

Logistic regression model

Parameter Estimation-Maximum likelihood

Principal component analysis

Non-parametric techniques: k-nearest neighbor, density estimation

Decision Tree with example (Entropy, Gini impurity index)

Neurons, Perceptron, Multilayer Perceptron, LMS, Feedforward Operation, Backpropagation Algorithm, Activation Function, Loss Function, XOR problem, Cross-validation, Regularisation, Demonstration on classification and regression applications

Radial Basis Functions and K-means clustering

Support Vector Machine (SVM)

Random Forest, Ensemble Learning, Bagging, Boosting

Module 4: Deep Learning

Basics of Deep Learning

Deep learning architectures: DNN, CNN, RNN, LSTM, Autoencoder

Methodology and Applications

Demonstration of deep learning applications

Module 5: Applications of Machine Learning

Computer Vision

Speech Recognition

Natural Language Processing

Tools

Python

MatplotLib

Pandas

Keras

NumPy

OpenCV

TensorFlow

SciKit Learn

SciPy

Hands-on Projects and Case Studies

MNIST digit recognition using DNN, CNN, and SVM

Classification of Real news and Fake news using decision trees

Prediction of the iris flower species using Naive Bayes classification

Classify Photos of Dogs and Cats using Deep Convolutional Neural Network

To build a movie recommender model using K-means clustering

Identification of IoT devices using experimental radio spectrum dataset and deep learning

German Traffic Sign Recognition Benchmark: Develop a Feed Forward Neural Network and then a Convolutional Neural Network to classify between the different Road Signs in the dataset given below. Test it using images from the internet to validate the functioning of your model

CIFAR-10 Object Recognition: Develop a Convolutional Neural Network to classify between the different classes of the Dataset given below. Test it using images from the internet

Sentiment Analysis using Naive Bayes Classifier

Application of Deep Learning in Medical Diagnosis using Health Data

Credit Card Fraud Detection using Random Forest Classifier

Music Recommendation System using K-NN Algorithm

Image Compression using K-means Clustering