A. Supervised Learning

Supervised Learning is a machine learning technique where the model is trained using labelled data.

1. Linear Regression

Linear Regression is used to predict continuous numerical values.

Topics Covered:

• Linear Equation
• Slope
• Intercept
• R-Square Value

2. Logistic Regression

Logistic Regression is used for classification problems where the output is usually binary, such as yes/no or success/failure.

Topics Covered:

• Odds Ratio
• Probability of Success
• Probability of Failure
• Bias Variance Tradeoff
• ROC Curve

Hands-on Exercise

Students will review the main ways to approach data modelling problems using simple and well-defined machine learning techniques. They will learn how to model past data using mathematical functions and predict new outputs based on trained models.

B. Unsupervised Learning

Duration: 4 Hours

Unsupervised Learning is used when the data does not have labelled outputs. The model identifies hidden patterns and groups in the data.

Topics Covered:

• K-Means Clustering
• K-Means++
• Hierarchical Clustering

C. Support Vector Machine

Duration: 2 Hours

Support Vector Machine is a powerful supervised learning algorithm used for classification and regression tasks.

Topics Covered:

• Support Vectors
• Hyperplanes
• 2-D Case
• Linear Hyperplane

D. SVM Kernel

Duration: 2 Hours

SVM Kernel helps transform data into higher dimensions to make classification easier.

Topics Covered:

• Linear Kernel
• Radial Kernel
• Polynomial Kernel

E. Other Machine Learning Algorithms

Duration: 10 Hours

Topics Covered:

• K-Nearest Neighbour
• Naïve Bayes Classifier
• Decision Tree – CART
• Decision Tree – C5.0
• Random Forest

Hands-on Exercise

Students will work on practical machine learning models and understand how different algorithms solve real-world problems. They will also explore regression techniques, clustering methods, and mathematical tools used for approximating unknown values.

Module 1: AI Introduction

Duration: 9 Hours

Artificial Intelligence focuses on creating intelligent systems that can think, learn, and make decisions.

Topics Covered:

• • Perceptron
  • Multi-Layer Perceptron
  • Markov Decision Process
  • Logical Agent
  • First Order Logic
  • AI Applications

Module 1: Deep Learning Algorithms

Duration: 10 Hours

Deep Learning is a subset of Machine Learning that uses neural networks to solve complex problems such as image recognition, speech recognition, and natural language processing.

Topics Covered:

• CNN – Convolutional Neural Network
• RNN – Recurrent Neural Network
• ANN – Artificial Neural Network

Hands-on Exercise

Students will learn how to implement their first neural network and understand the foundation of deep learning architectures. This module will help students apply previously learned concepts to advanced neural network models.

A. Introduction to NLP

Duration: 5 Hours

Natural Language Processing helps machines understand, process, and analyze human language.

Topics Covered:

• Text Pre-processing
• Noise Removal
• Lexicon Normalization
• Lemmatization
• Stemming
• Object Standardization

B. Text to Features / Feature Engineering

Duration: 5 Hours

Feature Engineering converts raw text into structured data that can be used by machine learning models.

Topics Covered:

• Syntactical Parsing
• Dependency Grammar
• Part of Speech Tagging
• Entity Parsing
• Named Entity Recognition
• Topic Modelling
• N-Grams
• TF-IDF
• Frequency / Density Features
• Word Embeddings

C. Tasks of NLP

Duration: 2 Hours

Topics Covered:

• Text Classification
• Text Matching
• Levenshtein Distance
• Phonetic Matching
• Flexible String Matching

Hands-on Exercise

Students will learn how to create customized NLP models. They will work on text-based problems and understand how machine learning models can process and classify natural language data.

Project 1: Board Game Review Prediction

Students will perform Linear Regression analysis to predict average reviews for board games.

Project 2: Credit Card Fraud Detection

Students will focus on Anomaly Detection using probability densities to detect credit card fraud.

Project 3: Stock Market Clustering

Students will use K-Means Clustering to find related companies by analyzing correlations among stock market movements over a given time span.

Project 4: Getting Started with Natural Language Processing

Students will learn basic NLP methodology, including:

• Tokenizing words and sentences
• Part of speech identification
• Tagging
• Phrase analysis

Project 5: Object Recognition Using Deep Learning

Students will use the CIFAR-10 object recognition dataset as a benchmark to implement a deep neural network model for object recognition.

Project 6: Image Super Resolution with SRCNN

Students will learn how to implement and use the TensorFlow version of the Super Resolution Convolutional Neural Network, also known as SRCNN, to improve image quality.

Project 7: Natural Language Processing – Text Classification

Students will solve a text classification task using multiple classification algorithms and advanced NLP techniques.

Project 8: K-Means Clustering for Image Analysis

Students will use K-Means Clustering as an unsupervised learning method to analyze and classify 28 x 28 pixel images from the MNIST dataset.

Project 9: Data Compression & Visualization Using PCA

Students will learn how to compress the Iris dataset into a 2D feature set and visualize it through a normal X-Y plot using K-Means Clustering.