Please see the video to learn how you can utilise our containers to perform hands on labs

Introduction and Course Overview - What is AI

2-AI is todays life

3 -Subfields of AI

4-Context of AI

5-Expectations from AI

6 -Wrapping Up

Problem Solving using Search Techniques - Intro

2 - Let-s play Missionaries and Cannibals

3- Solving Missionaries and Cannibals

4 - Solving Tower of Hanoi

5-Exercise - Frog Problem

6-Dealing with Navigation Problems and Mazes

7 - Wrapping up

Heuristic Based Searches -1-Intro

2- Unit 3-2 - Recap

3-Unit 3-3 - Limitations using Exhaustive Search

4-Unit 3-4- Heuristics

5-Unit 3-5 - Good or Bad Heuristic

6-Unit 3-6 - Heuristic Based Searches

7-Unit 3-7 - Best-First Method

8 -Unit 3-8 - Best First - A greedy approach

9-Unit 3-9 - AStar Search

10-Unit 3-10 - AStar Dry Run

11-Unit 3-10 - AStar Optimality

12-Unit 3-12 - Wrapping Up

Heuristic Based Searches - 1 - Intro

2 - Gary Kasparov vs Deep Blue

3 - Adversarial Games

4 - Game Tree for TicTacToe

5 - Minimax Algorithm

6 - Minimax Assumptions and Examples

7 - Evaluation Function in Minimax

8 - Pruning in Game Trees

9 - Alpha-beta Pruning

10 - Alpha-beta Pruning - Example II

11 - Interactive Example

12 - Wrapping Up

AI in Adversarial Games -1 - Intro

Module 1 - Hands on - 1-Code Walk through - Solving Puzzles using Search techniques

2 - Classification using Decision Tree

Machine Learning - Intro

2-What is Machine Learning

3 - Supervised Learning

4 - Unsupervised Learning

5-Classification vs Regression

6-Classification vs Regression

7- Machine Learning Process

8- Wrapping Up

1 - Intro - Classification using Decision Tree

2 - Classification - Recap

3 - Decision Tree - Introduced

4 - Classification using Decision Tree

5 - Measuring Node Impurity

6 - Determining the best split

7 - Decision Tree Induction

8 - Stopping Criteria

9 - Concluding Decision Trees

Measuring Classification Accuracy - Intro

2-Dividing data into train-test

3-Confusion Matrix and Accuracy

4-Class Imbalance Problem

5-Precision and Recall

6-Sensitivity and Specificity

7 - ROC Curve

Artificial Neural Networks - Intro

2 - Outline

3 - A quick History

4 - MLP - Introduction

5 - One-hot encoding

6 - Deciding Input and output Neurons

7 - Activations Functions

8 - Learning a Neural Network

9 - Forward Pass

10 - Backward Pass

11 - Summarizing

12 - Learning Rate

13 - Limitations

Classification using Naive Bayes - Intro

2 - Outline

3 - Probabilities Recap

4 - Bayes Theorem and Total Probability

5- Example

6 - Estimating probabilities from data

7- Learning Naive Bayes Model

8 - Another Example

9 - Classification using Naive Bayes

10 - Points to consider for Naive Bayes

Clustering using KMeans Intro

1 - Outline

2 - What is Clustering

3 - Clustering Examples

4 - Cluster Quality

5 - Types of Clustering

6 - Distance and Center Measures

7 - Working of KMeans

8 - KMeans Calculation

9 - Initial Centroids

10 - Limitations of KMeans

Recommendation Systems - Intro

2 - Outline

3 - Examples

4 - Data for Recommendations

5 - Content-based Recommendation

7 - Measuring Similarity

8 - Latent Factor Model

9 - Adding Biases

10 - Challenges

1-Code Walkthrough - Making Predictions using scikit-learn

2 - Code Walkthrough - Classifying Fashion Products

3 - Data Clustering

1 - Intro - Logic and Reasoning

2 - Outline

3 - Why reasoning

4 - Logic based Systems

5 - Induction vs Deduction

6 - Propositional Logic

7 - First Order Logic

8 - FOL Example

9 - Working with Prolog

10 - Family Tree Example in Prolog

11 - Inference - Forward and Backward Chaining

1 - Intro - Bayesian Networks

2 - Outline

3 - Dealing with uncertainty

4 - Earthquake Example

5 - Bayesian Networks

6 - Reasoning through

7 - Belief Propagation

8 - Inference in a singly connected BN

9 - dSeperation and Markov Blanket

AI - Social and Ethical Concerns - User Content and Data Bias

2 - Robustness

3 - Fake Content

4 - Autonomy of Machines

5 - Transparency

6 - Wrapping up

Feedback

Lec 02 - Setting up Envmt - Part 01

Lec 02 - IDLE Demo Part 02

Lec 02 - Setting up Envmt - Urdu - Part 03

Lec 02 - Jupyter Demo - Urdu - Part 04

Lec 02 - Programming without IDE - Part 05

Lec 03 - Setting the Envmt - VSC -

Lec 03 - VSC Demo -

Quiz 1 - Introduction to Python

Lec 04 - Basics - IO - Urdu

Lec 05 - Python Basic Syntax

Lec 06 - Variables and Data Types

Python Programming Exercises - Basics

Quiz 2 - Basic Input Output, Variables

Lec 07 - Strings

Programming Exercises - Strings

Quiz 3- Strings

Lec 08 - Compund Data Types

Programming Exercises - Compound Data Types

Quiz 4 - Compound and Datetime Data Types

Lec 10 - Operators and Precedence

Lec 11 - Decisions

Quiz 5 - if else- Decisions

Lec 12 - Loops

Python Programming Exercises - Decisions and Loops

Quiz 6 - Loops

Lec 13 - Functions - Part 1

Lec 14 - Functions - Part 2

Programming Exercises - Functions

Quiz 7 - Functions

Lec 15 - Modules

Lec 16 - Packages

Lec 17 - Files and Directories

Programming Exercises - Files and Directories

Quiz 9 - Files and Directories

Lec 18 - Exception Handling

Quiz 10 - Exception Handling

Python Basics Cheat Sheet

Lec 19 - Python - Introduction

Lec 20 - Numpy - Part 1

Lec 20 - Numpy - Part 2

Programming Exercises - Numpy

Quiz 1 - Numpy

Numpy - Cheat Sheet

Lec 21 - Pandas

Lec 21 - Pandas - Part 2

Programming Exercises - Pandas

Quiz 2 - Pandas

Pandas - Cheat Sheet

010102 - Biological Neurons

010103 - Brains and ANN

010104 - Evolution of Deep Learning

010105 - Types of ANN

020101 - Logical Computations with MP Neuron

020102 - Perceptron

020104 - Sigmoid Neurons

020105 - Other Activation Function

030101 - FFNN

030102 - Backpropagation

030103 - Backpropagation Numerical Example - Urdu

030103 - Backpropagation - A More Complex Numerical Example

030104 - Neural Network - Python Implementation

Convolutional Neural Networks - P5C1L01 - Introduction

P5C1L02 - Overcoming Limitations of FFNN - Urdu

P5C1L03 - CNN Details - Part 1

P5C1L04 - CNN Details - Part 2

P5C1L05 - Parameter Computation for CNN

P5C1L06 - Deep Learning Architectures - Urdu

Feedback

110102 - Flipped Programming Paradigm of ML

110103 - Success Stories of ML

110104 - Terminologies

110105 - Types of ML

110106 - Workflow of Machine Learning Problem

110107 - Challenges of ML

110108 - Demo ML Project

Quiz 1 - Introduction

210101 - Linear Algebra and Matrices

210102 - Probability

210103 - Calculus

Supervised Learning

310101 - Classification Inutition

310103 - Classification - Geometry

310104 - Linear Classification

310105 - Parametrization of Linear Classifiers

310106 - Perceptron

310107 - Perceptron - Numerical Example

310108 - Perceptron - Python Implementation

Quiz 2 - Linear Classification - Perceptron

Practice Exercises - Perceptron

410101 - Large Margin Classifier

410102 - Regularization

410103 - Convex Surrogate Loss Functions

410104 - Objective Function

410105 - Support Vector Machine and Gradient Descent

410107 - SVM - Python Implementation

Quiz 3 - Support Vector Machine

Practice Exercises - Linear SVM

510101 - Logistic Regression - Intro

510102 - Logistic Regression - odds vs logit

510103 - Logistic Regression - Problem Setting

510104 - Logistic Regression - Gradient Descent

510105 - Logistic Regression - Python Implementation

610101 - Discriminative vs Generative Models

610102 - Bayesian Classification

610103 - Bayesian Model

610104 - Bayes Classifier - Numerical Example

Quiz 4 - Naive Bayes

710101 - Nearest Neighbours - Introduction

710102 - Nearest Neighbours - Numerical Example

710103 - Nearest Neighbours - Issues

Quiz 5 - Nearest Neighbours

Practice Exercises - kNN

80101 - Introduction to Regression

80102 - Simple Linear Regression Procedure

80103 - Goodness of Fit

Quiz - Linear Regression and Goodness of Fit

Unsupervised Learning

Clustering Algorithms

910101 - kMeans - Introduction

910102 - kMeans - Numerical Example

910103 - kMeans - Final Words

910104 - k-Medoids

Quiz - k Means

Practice Exercise - k Means and k Medoid

050701 - Neural Networks - Motivation -

050702 - Biological Neurons

050703 - Brains and ANN

050704 - Types of ANN

050706 - Backpropagation

050708 - Neural Network - Python Implementation

C01L02 - Over and Under Fitting - Part 1

C01L03 - Over and Under Fitting - Part 2

C01L04 - Regularization

C01L05 - Mathematics of Regularization

C01L06 - L1 vs L2 Regularization

C01L07 - Cross Validation

C01L08 - Stratified Sampling

C02L01 - End to End Machine Learning Project - Part 1

C02L02 - End to End Machine Learning Project - Part 2

C02L03 - End to End Machine Learning Project - SRS

C02L04 - End to End Machine Learning Project - visualization

C02L06 - End to End Machine Learning Project - Training

C02L07 - End to End Machine Learning Project - Fine Tuning

C03L01 - Introduction

C03L02 - Constructing Decision Trees

C03L03 - Information Gain

C03L04 - Entropy-Based Automatic Decision Tree Construction

C03L05 - Gini Impurity

C04S02L01 - Bagging

C04S03L02 - Adaboost

C04S03L03 - Adaboost Numerical Example1

C04S02L02 - Bagging Example

C04S01L01 - Introduction

C04S01L02 - Types of Ensemble Learning

C04S03L09 - Gradient Boosting - Numerical Example

C04S03L10 - gboost_impl

C05S01L01 - Multiclass Classification - Intro

C05S01L02 - One Against All Strategy

C05S01L06 - Multinomial Logistic Regression

C05S01L05 - Multi-Class SVM

Part 3 - Model Development and Prediction - Classification

Part 4 - Model Development and Prediction - Regression

Chap 2 - Image Recognition Using PyTorch

Part 1 - Introduction

Part 2 - Data Exploration

Part 3 - Model Dev-Training-Validation

Chap 3 - Medical Diagnosis

Part 1 - Introduction

Part 2 - Explore the Data

Part 3 - Model Dev and Training

Data Preprocessing

Train Test Split

Building ANN

Training ANN

Evaluating Model

Codes and datasets

Convolutional Neural Networks - Dataset Info

Preprocessing Images

Building CNN

Training CNN

Predicting Results

Codes

Recurrent Neural Networks - Dataset Info

Recurrent Neural Networks - Data Preprocessing

Recurrent Neural Networks - Building RNN and LSTM

Recurrent Neural Networks - Training Model

Recurrent Neural Networks - Predicting Results

Recurrent Neural Networks - Visualising Results

Recurrent Neural Networks - Visualisation Correction

Recurrent Neural Networks - Codes and dataset

Self Organizing Maps - Dataset Info

Self Organizing Maps - Preprocessing Data

Self Organizing Maps - Training SOM

Self Organizing Maps - Visualising Results

Self Organizing Maps - Finding Frauds

Self Organizing Maps - Codes and datasets

Self Organizing Maps - Boltzmann Machine - Dataset Info

Self Organizing Maps - Datapreprocessing I

Self Organizing Maps - Datapreprocessing II

Self Organizing Maps -Datapreprocessing III

Self Organizing Maps - Datapreprocessing IV

Self Organizing Maps - Codes and datasets

Auto Encoders - Data Preprocessing

Auto Encoders - Transform Data

Auto Encoders - Tensor

Auto Encoders - Auto Encoder Architecture

Auto Encoders - Training and Testing

Auto Encoders - Codes and datasets

Feedback

Virtual Environments - Creating Virtual Environments

Libraries Installation

Image Processing with OpenCV - Introduction to Images

Image Processing with OpenCV - Reading Images I

Image Processing with OpenCV - Reading Images II

Image Processing with OpenCV - Understanding Pixels

Image Processing with OpenCV - Resize Images I

Image Processing with OpenCV - Resize Images II

Image Processing with OpenCV - Face Detection on Images

Image Processing with OpenCV - Face Detection on Videos

Facial Recognition Model Development - Data Understanding

Facial Recognition Model Development - Cropping an Image

Facial Recognition Model Development - Data Processing I

Facial Recognition Model Development - Data Processing II

Facial Recognition Model Development - Eigen Faces I

Facial Recognition Model Development - Eigen Faces II

Facial Recognition Model Development - Training Machine Learning Model

Facial Recognition Model Development - Evaluation Metrics

Facial Recognition Model Development - Hyper Parameter Tuning

Facial Recognition Model Development - Model Pipeline

Basics of Flask - Setup VS Code and Flask

Basics of Flask - Flask Routing

Basics of Flask - Variable Rules

Basics of Flask - Jinja Template I

Basics of Flask - Jinja Template II

Basics of Flask - Jinja Template III

Basics of Flask - Inheritance

Static Files

Basics of Flask - HTTP Methods

Basics of Flask - Upload Files

Basics of Flask - First Flask App

Flask App - Folder Structure

Flask App - Main.py Basic App

Flask App - Views.py File

Flask App - Base HTML I

Flask App - Base HTML II

Flask App - Home Page

Flask App - App Page

Flask App - Gender App Page I

Flask App - Gender App Page II

Flask App - Gender App Page III

Flask App - Gender App Page IV

Flask App - Gender App Page VII

Model Deployment - Setup Code for Deployment

Model Deployment - Push App to Github

Model Deployment - Deploy App to Heroku

Model Deployment - Ending Remarks

Feedback

Virtual Platform

Basic operations Using Tensors

Linear Regression I

Linear Regression II

Linear Regression III

Logistic Regression I

Logistic Regression II

Logistic Regression III

Logistic Regression VI

Logistic Regression V

2 Section 1 - Importing Libraries

Dataset Info

Create DataLoader

Building our CNN

Loss Function

Training Model

Prediction I

Prediction II

3 Section - Introduction to opencv

Introduction to open cv 2

Reading Images

Reading Webcam

Color Spaces

Translation and Rotation

BlurImage

WarpPerspective

Add Shapes

Add Text

JoinImages

Bitwise_or_not

Histogram Computation

Shape Detection

Document scanner

Project Setup

Detections SSD

result on Images

Results on live videos

Edge Detection

06 Object Detection - YOLO-NAS Implementation

01 Facial Landmark using DLIB_edited

SSD - Funny Dog

Data

Layers

SSD

4. Some history

5. Why is it hard

Unit 01 - Intro.

Chapter 2 Regular Expressions - 1-What is RE

2 - Code Demo I

3 - Code Demo II

4 - Code Demo III

Unit 02 - Regular Expressions

Chapter 3 Basic Text Processing using NLTK and spacy Introduction

2 - Outline

3.1 - Text Processing Steps

3.2 - Text Processing Steps

4 - About NLTK

5 - NLTK Demo

6 - Spacy Demo

7 - NLTK vs Spacy

Unit 03 - Basic Text Processing

Chapter 4. Pattern Matching and Topic Modeling - Introduction

2 - Outline

3 - PatternMatching in spacy

4 - about LDA and NMF

5 - LDA and NMF in scikit-learn

Unit 04 - Topic Modeling

Chapter 5.- Text Vectorization - Introduction

2 - Outline

3 - Text Classifiation

4 - Text Vectorization

5 - Code Demo

Unit 05 - Converting text into vectors

6. Text Classification using NB - Introduction

2 - Outline

3 - Naive Bayes

4 - Naive Bayes - Example

5 - Naive Bayes - Strength and Weaknesses

6 - Code Demo

Unit 06 - Learning Classifiers - NB

Chapter 7. Text Classification using ANN - Intro

2 - Outline

3 - ANN Introduced

4 - Topology of ANN

5 - Backpropagation

6 - Learning Rate and Bias

7 - Limitations

8 - Code Demo

Unit 07 - Learning Classifiers - ANN

Chapter 8 - Intro Word Embeddings

2 - Outline

3 - Learning Word Embeddings

4 - Visualising Embeddings

5 - Pretrained Embedding

6 - Using pretrained word2vec and glove embeddings

7 - Learning your word2vec model using gensim

8 - Switching to Keras

Unit 08 - Word Embeddings

Chapter 9. Recurrent Neural Networks - Intro

2 - Outline

3 - What is RNN

4 - Working of RNN

5 - Types of RNN

6 - Short term memory

7 - Bidirectional RNN

8 - Implementing RNN and BRNN in Keras

Unit 09 - Recurrent Neural Networks (RNN)

Chapter 10 .LSTM_GRUs - Intro

2 - Outline

3 - LSTM Intuition

4 - RNN Recap

5 - LSTM Cell

6 - LSTM Architecture

7 - GRU

8 - Code Demo

LSTM_GRU

Chapter 11. Transformers and Hugging Face - Intro

2 - Outline

3 - What is attention

4 - Self attention in transformers

5 -Generating Text

6 - Architecture Overview

7 - Applications

8 - Introducing Hugging Face

9 - Using Hugging Face Pipelines

Unit 11 - Transformers