How to succeed in this course

Introduction of the course

Introduction of the section

Drive mounting and data reading

Reading more datasets

Uploading Course Material to Google drive and observing course organization

Reading and displaying images

Comparison and logical operations

Arithmetic with python

Conditional Statements

Arrays with Numpy part01

Arrays with Numpy part02

Plotting and Visualization part01

Plotting and Visualization part02

Plotting and Visualization part03

Arrays with Numpy part03

Plotting and Visualization part04

Lists in python

For loop part01

For loop part02

while loop

Strings in Python

Print formatting with strings

Dictionaries part01

Dictionaries part02

Seaborn part01

Seaborn part02

Seaborn part03

Pandas part01

Pandas part02

Pandas part03

Pandas part04

Functions in python part01

Functions in python part02

Tuples in Python

Classes in Python

lambda function

map function

filter function

zip function

join function

Pre-requisites section

Data Normalization and MinMax scaling

Need of data preprocessing

Project01 Data Normalization and MinMax scaling part01

Data Standardization

Project02 Data Standardization

Project01 Data Normalization and MinMax scaling part02

Project03 Dealing with missing values

Project05 Feature Engineering

Project04 Dealing with categorical features

Project06 Feature Engineering by window method

Origin of the Regression

Definition of Regression

Simple Linear Regression

Requirement from Regression

Multiple Linear Regression

Target and predicted values

Loss function

Numerical example on least square method

Evaluation metrics for regression

Least square method

Project01 simple regression part01

Project01 simple regression part02

Project02 multiple regression part01

Project02 multiple regression part02

Project01 simple regression part03

Project02 multiple regression part03

Regression by Gradient descent

Polynomial Regression

Project04 Gradient descent on simple linear regression

Project05 Gradient descent on multiple linear regression

Cross-validation

Project03 multiple regression

Project06 Polynomial Regression

Bias-variance tradeoff ( Overfitting and underfitting )

Concept of regularization

Project07 Cross-validation

Ridge regression OR L2 regularization

Elastic Net regularization

Comparing Ridge and Lasso regularization

Lasso regression OR L1 regularization

Grid search cross-validation

Project08 Regularization

Project09 Grid search CV

Basic concept

Limitations of regression models

Transforming Linear regression into logistic regression

Project01 Getting class probabilities part01

Project01 part02

Loss function for logistic regression

Model evaluation - Confusion Matrix

ROC curves and area under ROC

Accuracy, precision, recall, f1-score

Project02 Evaluating Logistic Regression Model

Project03 Logistic Regression Model with cross-validation

Project05 Logistic Regression on challenging data part01

Project04 Multiclass classification with logistic regression

Project05 Logistic Regression on challenging data part02

Project05 Logistic Regression on challenging data part03

Grid search CV

The perceptron

Features, weights and Activation function

Learning of Neural Network

Rise of deep learning

Classification by perceptron part01

Classification by perceptron part02

Adding Activation function to Neural Network

Why we need Activation functions

Sigmoid as activation function

ReLU and Leaky ReLU functions

Hyperbolic tangent function

MSE Loss function

Softmax function

Cross Entropy Loss function

Forward Propagation

Back propagation part02

Back propagation part01

Gradient descent

Stochastic Gradient descent ( SGD )

Exponentially weighted averages

Concept of momentum

RMS Prop

ADAM Optimizer

Creating Neural Network using class

Project01 Neural Network for simple regression part01

Project02 Neural Network for multiple regression

Project01 Neural Network for simple regression part02

Project01 Neural Network for simple regression

Project02 Neural Network for multiple regression

Epoch, Batchsize and Iteration

Code preparation for iris dataset

Project00 Tensor dataset and tensor dataloader

Code preparation for MNIST Dataset

Project01 Neural Network for iris data classification

Save and load the trained model

Code Preparation for custom images

Project01 Neural Network for simple regression part02

Project02 Neural Network for MNIST classification part01

Code preparation for human action recognition dataset

Project03 Neural Network for custom images classification

Project05 Neural Network on Feature Engineered dataset

Project04 Neural Network for human action recognition

Project01 Neural Network for iris data classification

Project02 Neural Network for MNIST data classification

Project03 Neural Network for custom images classification

Introducing WESAD Dataset

Dropout Regularization

Batch Normalization

Project02 Dropout Regularization

Project01 Dropout Regularization

Project04 Batch Normalization

Project03 Batch Normalization

Creating custom loss function with TensorFlow

Creating custom loss function with Pytorch

Scheduling Learning Rate with Pytorch

Scheduling Learning Rate with TensorFlow

Creating Custom Layer with Pytorch

Creating Custom Layer with TensorFlow

CNN Architecture and main operations

D Convolution

Shapes of Feature Maps after convolution

Pooling to classification

Average and Maximum pooling

Project00 CNN Shapes

An Efficient Lazy Linear layer

Project01 CNN for MNIST Classification part02

Project01 CNN for MNIST Classification part01

Transfer Learning

Project02 CNN for custom images classification

Project03 Transfer Learning with VGG-16

Project03 Transfer Learning with ResNet-18

Project01 CNN Shapes

Project02 CNN for custom images classification

Project03 Transfer Learning

Stopping Criterion Part01

Stopping Criterion Part02

Project02 Early Stopping Criterion with TensorFlow

Project01 Early Stopping Criterion with Pytorch

Why we need RNN

Sequential Data

ANN to RNN

Back Propagation Through time

Long Short-term Memory ( LSTM ) Network

LSTM Gates

Project02 LSTM Basics

Concept of batchsize, sequence length and feature dimension

Project01 LSTM Shapes

Project03 Interpolation and extrapolation with LSTM

Project05 Multivariate Time series classification with LSTM part02

Project04 Time series classification with LSTM

Project05 Multivariate Time series classification with LSTM part01

MNIST Classification with LSTM

Project02 LSTM Time series prediction

Project03 MNIST Classification with LSTM part01

Project03 MNIST Classification with LSTM part02

Project01 LSTM Shapes

Text Classification

Project04 Text preprocessing

Project05 Text Classification with LSTM

Introduction of the Section

Working of Bidirectional LSTM

Project02 Bidirectional LSTM for MNIST data classification

Project01 Shapes of Bidirectional LSTM

Dual Bidirectional LSTM for Image Classification

Project03 Dual Bidirectional LSTM for MNIST Classification

Project01 Shapes of bidirectional LSTM

Project02 Bidirectional LSTM for tome series classification

Project01 1DCNN Shapes

Project01 1DCNN for univariate time series classification

Project02 1DCNN for multivariate time series classification

Project01 IDCNN Shapes

Project02 1DCNN for Multivariate time series classification

Applications of Autoencoder

Architecture of Autoencoder

Project02 Autoencoder as image occlusion removal

Project03 Autoencoder as image classifier

Project01 Autoencoder as image noise removal

Project01 CNN Autoencoder shapes

Project02 Image reconstruction and classification with CNN Autoencoder

Project02 LSTM Autoencoder for Sine Wave reconstruction part02

Project01 LSTM Autoencoder shapes

Project02 LSTM Autoencoder for Sine Wave reconstruction part01

Project03 LSTM Autoencoder for Sawtooth Wave reconstruction

Introduction to VAE

Project03 CNN VAE for Regenerating MNIST Images from Noise

Project01 Fully connected layers based VAE

Project02 CNN VAE Shapes

Discriminative and Generative Models

Training of GAN

Project01 GAN for MNIST data regeneration

Shapes of DCGAN

Project01 DCGAN on MNIST data

Project02 DCGAN for 64 x 64 images

Introduction to Transformer sections

Project02 Text Generation

Project01 Sentiment Analysis

Project03 Masked language Modeling

Project04 Text Summarization

Project06 Question Answering

Project05 Machine Translation

Fundamental Building Blocks of Transformer

Encoder and decoder

Positional encoding

Attention Mechanism

Project01 Model and Tokenization

Project03 Fine tune transformer on custom dataset

Project02 Fine tune transformer for sentiment analysis

Masked Autoencoders

Project02 Fine tune Vision Transformer ( ViT ) on Custom dataset

Project03 Masked Autoencoder ( MAE ) on CIFAR-10 dataset

Project01 Fine tune Vision Transformer ( ViT ) on CIFAR-10 dataset

Project04 Masked Autoencoder ( MAE ) on Custom dataset

Project03 Time Series Transformer Shapes

Project01 Shapes of Encoder

Project02 Time series classification

Project04 Time series reconstruction using time series transformer

Introduction to Neural Style Transfer

Project02 Neural Style Transfer with AlexNet

Project01 Neural Style Transfer with VGG-16

Introduction to unsupervised machine learning sections

Definition, Intuition and steps of K-mean clustering

K-mean algorithm in one-D ( Numerical Example )

K-means algorithm in 2D ( Numerical Example )

Objective function of K-mean algorithm

Selecting Optimal Clusters ( Elbow Method )

Evaluating K-means clustering

Project01 K-means Clustering part03

Project01 K-means Clustering part01

Project02 K-means Clustering

Project01 K-means Clustering part02

Project03 K-means Clustering

Key Concepts of PCA

Why we need PCA

Understanding PCA with numerical example

Project01 PCA

Project03 PCA

Project02 PCA

Project04 PCA

Project05 PCA

Project06 PCA