Artificial Intelligence - AI

Artificial intelligence (AI, also machine intelligence, MI) is intelligence displayed by machines, in contrast with the natural intelligence (NI) displayed by humans and other animals. In computer science AI research is defined as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of success at some goal. 

Artificial intelligence is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using the rules to reach approximate or definite conclusions), and self-correction. Particular applications of AI include expert systems, speech recognition and machine vision.

Topics to be covered in Workshop (20% Theory & 80% Hands-On Session)

Day 1

Python Overview: Introduction to Python Programming

• What is Python
• Understanding the IDLE
• Python basics and string manipulation
• lists, tuples, dictionaries, variables
• Control Structure – If loop, For loop and while Loop
• Single line loops
• Writing user-defined functions
• Classes
• File Handling
• OOPS concept with Classes 

Data Structure & Data Manipulation in Python

• Intro to Numpy Arrays
• Creating Arrays
• Creating Matrices
• Creating Vectors
• Indexing, Data Processing using Arrays
• Mathematical computing basics
• Basic statistics
• File Input and Output
• Getting Started with Pandas
• Data Acquisition (Import & Export)
• Selection and Filtering
• Combining and Merging Data Frames
• Removing Duplicates & String Manipulation 

Understanding the Machine Learning Libraries

• Numpy
• Pandas
• Opencv 

Visualization in Python 

• Introduction to Visualization
• Visualization Importance
• Working with Python visualization libraries
• Matplotlib
• Creating Line Plots, Bar Charts, Pie Charts, Histograms, Scatter Plots

Machine Learning: Introduction

• Machine Learning vs. Data Science vs. AI
• Discussion on Various ML Learnings
• Regression vs. Classification
• Features , Labels , Class
• Supervised Learning | Unsupervised Learning Using Opencv
• Real implementation
• AI Algorithms
• Cost Function
• Optimizers 

Linear Regression Using Opencv

• Regression Problem Analysis
• Mathematical modelling of Regression Model
• Gradient Descent Algorithm
• Use cases
• Regression Table
• Model Specification
• L1 & L2 Regularization
• Data sources for Linear regression

Math of Linear Regression 

• Linear Regression Math
• Cost Function
• Cost Optimizer: Gradient Descent Algorithm
• Regression R Squared

Linear Regression – Case Study & Project

• Programming Using Python
• Building simple Univariate Linear Regression Model
• Multivariate Regression Model
• Apply Data Transformations
• Identify Multicollinearity in Data Treatment on Data
• Identify Heteroscedasticity
• Modelling of Data
• Variable Significance Identification
• Model Significance Test
• Bifurcate Data into Training / Testing Dataset
• Build Model of Training Data Set
• Predict using Testing Data Set
• Validate the Model Performance
• Best Fit Line and Linear Regression
• Model Predictions
• Model Accuracy
• Graphical Plotting

 Logistic Regression Using Opencv 

• Assumptions
• Reason for the Logit Transform
• Logit Transformation
• Hypothesis
• Variable and Model Significance
• Maximum Likelihood Concept
• Log Odds and Interpretation
• Null Vs Residual Deviance
• Chi-Square Test
• ROC Curve
• Model Specification
• Case for Prediction Probe
• Model Parameter Significance Evaluation
• Drawing the ROC Curve
• Optimization of threshold value
• Estimating the Classification Model Hit Ratio
• Isolating the Classifier for Optimum Results
• Model Accuracy
• Model Prediction

Practical on Machine Linear & Logistic Regression

Day 2

Support Vector Machine Using Opencv

• Concept and Working Principle
• Mathematical Modelling
• Optimization Function Formation
• The Kernel Method and Nonlinear Hyperplanes
• Optimal separating hyperplane
• Drawing Margins
• Use Cases & Programming SVM using Python
• Anomaly Detection with SVM
• Use Cases & Programming using Python
• Case study of KNN Vs SVM
• Applying KNN & SVM for Supervised Problems of Classification & Unsupervised problems like Clustering.

RANDOM FOREST & Decision Tree Algorithm:

• Concept and Working Principle
• Mathematical Modelling
• Optimization Function Formation
• Analysis of Classification Problem case
• Math: Role of Gini Index in Decision Trees
• Analysis of Regression Problem case
• Use Cases & Programming using Python
• Classification with Random Forest
• Pros & Cons

Gradient descent variants (Theory)

Introduction to TensorFlow & Keras 

• Introduction Tensorflow
• Tensorflow
• MNIST
• The Programming Model
• Data Model, Tensor Board
• Introducing Feed Forward Neural Nets
• Softmax Classifier &ReLU Classifier
• Deep Learning Applications
• Working with Keras
• Building Neural Network with keras
• Examples and use cases

Unsupervised Learning Clustering:

• Clustering Introduction
• K-Means Clustering
• Handling K-Means Clustering
• Maths behind KMeans Clustering
• K Means from scratch
• Mean shift Introduction
• Dynamically weight

PROJECTS:

• Boston Housing Prediction
• Face Detection Using Image Classification
• Optical Character Recognition Using Opencv Lib
• Image Morphing Using Face Classifier

Duration: The duration of this workshop will be two consecutive days, with eight hour session each day in a total of sixteen hours properly divided into theory and hands on sessions.

Certification Policy:

• Certificate of Participation for all the workshop participants.
• At the end of this workshop, a small competition will be organized among the participating students and winners will be awarded with a 'Certificate of Excellence'.
• Certificate of Coordination for the coordinators of the campus workshops.

Eligibility: There are no prerequisites. Anyone interested, can join this workshop.