Description:

This course provides a comprehensive introduction to the field of Artificial Intelligence (AI) and explores its various applications in different domains. Students will learn about the foundations of AI, including problem-solving, knowledge representation, and reasoning. They will also gain hands-on experience with popular AI techniques such as machine learning, natural language processing, and computer vision. Through a combination of lectures, practical exercises, and real-world examples, students will develop a strong understanding of AI principles and techniques.

Key Highlights:

• Gain a solid understanding of the fundamentals of AI
• Learn about popular AI techniques like machine learning and natural language processing
• Develop practical skills through hands-on exercises and real-world examples

What you will learn:

• Learning Outcome 1
  Develop a strong understanding of the foundations and principles of AI
• Learning Outcome 2
  Gain hands-on experience with popular AI techniques such as machine learning and deep learning techniques.
• Learning Outcome 3
  Explore real-world examples and applications of AI in various domains

Module 1: Foundations: Python (12 hrs)

• Introduction to Python 
• Python Basics (Variables, Comments, Indentation, Input/output, if else, loop statements, break, continue, etc.)
• Data Structures 
• Functions 
• Object Oriented Programming 
• Introduction to commonly used libraries 
• Interview Questions
• Hands-on Sessions (Installation of Jupyter Notebook, executing python programs covering the concepts discussed in this module) 

Module 2: Exploratory Data Analysis and Dimensionality Reduction (8 hrs)

• Plotting for exploratory data analysis
• Dimensionality Reduction
• Principal Component Analysis
• T-Sne
• Interview Questions
• Hands-on Sessions (Executing python program covering various dimensionality reduction techniques)

Module 3: Basics of Machine Learning (6 hrs)

• Introduction to Machine learning
• Regression
• Classification
• Clustering
• Performance Metrics for regression, classification, and clustering
• Interview Questions

 

Module 4: Supervised Machine Learning algorithms (15 hrs)

• KNN
• Naive Bayes
• Logistic Regression
• Linear Regression
• Support Vector Machine
• Decision Trees
• Ensemble Model
• Feature Engineering for Machine Learning 
• Interview Questions
• Hands-on Sessions (Utilising the algorithms discussed in this module with different datasets

Module 5: Unsupervised Machine Learning (6 hrs)

• K-Means and K-Means++ Algorithm
• DBSCAN Technique
• Hierarchical Clustering
• Interview Questions
• Hands-on Sessions (Implementation of different clustering algorithms discussed in this module)

Module 6:  Deep Learning Basics (10 hrs)

• Introduction to Artificial Neural Network
• Backpropagation 
• Activation Functions
• Optimizers
• The Vanishing / Exploding Gradients Problems
• Underfitting and Overfitting 
• Bias Variance trade-off
• Practical Guidelines to Train Deep Neural Networks
• Interview Questions
• Hands-on Sessions (Implementing MLPs using Keras with TensorFlow Backend and covering the different concepts studied in this module)

Module 7:   Deep Learning for Image Data (15 hrs)

• Introduction to CNN 
• AlexNet
• VGGNet
• Residual Network
• LeNet
• Inception Network
• ImageNet dataset
• Transfer learning
• Interview Questions
• Hands-on Sessions (Utilizing various algorithms covered in this module with MNIST dataset, Cats/Dogs dataset, ImageNet dataset) 

Module 8:   Deep Learning for Text Data (10 hrs)

• Introduction to Recurrent Neural Network
• Types of RNNs 
• Bidirectional RNN
• Interview Questions
• Hands-on Sessions (IMDB Sentiment classification, Amazon Fine Food reviews)

Module 9:  Deployment of machine learning /deep learning models as web server (4hrs)

• Introduction to the platform where the model will be deployed
• Introduction to Front End 
• Introduction to Back End 
• Building of machine learning and deep learning models and their deployment

Module 10:  Projects

• Netflix Movie Recommendation system

To predict whether someone will enjoy a movie based on how much they liked or disliked other movies.

• Taxi Demand Prediction

Given a region and a particular time interval, predict the number of pickups as accurately as possible in that region and nearby regions

• StackoverflowTagPrediction

Suggest the tags based on the content that was there in the question posted on Stack overflow.

• Amazon Fashion Discovery Engine

Build a recommendation engine which suggests similar products to the given product in any e-commerce websites.

• Microsoft Malware Detection

To predict a Windows machine’s probability of getting infected by various families of malware, based on different properties of that machine.

• Predict rating given product reviews on amazon

Predict ratings given Amazon product text reviews

• Quora Question PairSimilarity

So given two questions, our main objective is to find whether they are similar.