Learn Web Application Development with Machine Learning

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Chapter 2: Setup and Creating Environment

Lecture 1: Install anaconda on your machine

Chapter 3: Introduction to Machine Learning for Absolute Beginners

Lecture 1: Types of Data in Machine Learning

Lecture 2: Introduction to numpy

Lecture 3: Introduction to pandas

Lecture 4: Train and Test split of data

Lecture 5: Miscellaneous Concept of Machine Learning

Chapter 4: Linear Regression in detail

Lecture 1: Lecture: Intro to Linear Regression

Lecture 2: Lecture: Learn about OLS [Ordinary Least Squares] algorithm

Lecture 3: Lecture: Introduction to working of Linear Regression

Lecture 4: Lecture: Introduction to MSE, MAE, RMSE

Lecture 5: Lecture: Introduction to R squared

Lecture 6: Tutorial: Implement Simple linear regression numerical [calculate best fit line]

Lecture 7: Workshop: Implement Simple Linear Regression

Lecture 8: Lecture: Difference between Simple and Multiple Regression

Lecture 9: Workshop: Implement Multiple Linear Regression

Lecture 10: Workshop: Implement Multiple Linear Regression

Chapter 5: Logistic Regression [optional]

Lecture 1: Lecture: Learn about Logistic Regression

Lecture 2: Lecture: Learn about hypothetical function [sigmoid/logit function]

Lecture 3: Lecture: Logistic Math Overview

Lecture 4: Lecture: Learn about decision boundary

Lecture 5: Lecture: Learn about Cost function of Logistic Regression

Lecture 6: Lecture: Learn about Gradient Descent

Lecture 7: Workshop: Implement Logistic Regression

Lecture 8: Workshop final: Implement Logistic Regression

Chapter 6: Neural Network in detail

Lecture 1: Introduction to Neural Networks

Lecture 2: Example of neural network

Lecture 3: Updating the weights [partial differentiation]

Lecture 4: Introduction to partial differentiation

Lecture 5: Introduction to the Activation Function

Lecture 6: Why do we need bias in the program

Lecture 7: Why we use regularization in the Neural Network

Lecture 8: Introduction to the gradient descent [review]

Lecture 9: Introduction to Stochastic Gradient Descent and Adam Optimizer

Lecture 10: Introduction to mini-batch SGD

Chapter 7: Coding Neural Network from Scratch [optional]

Lecture 1: Setting up environment and coding single neuron

Lecture 2: Coding neuron layer

Lecture 3: Using dot product to code neuron layer

Lecture 4: Coding dense layer [must know Object Oriented Programming]

Lecture 5: Introduction to Activation Function

Chapter 8: Activation Functions

Lecture 1: Implementation of activation function [step and sigmoid]

Lecture 2: Implementation of activation function [tanh and ReLu]

Chapter 9: Introduction to Tensorflow and Keras

Lecture 1: Introduction to Deep Learning

Lecture 2: Tensor Ranks in Tensorflow

Lecture 3: Program Elements in Tensorflow

Lecture 4: Coding in Tensorflow

Lecture 5: Introduction to Keras

Lecture 6: Keras Model [Most Important Video]

Lecture 7: Implementing neural network with Keras

Chapter 10: Creating Simple Flask Application ("Hello World")

Lecture 1: Flask: Display Hello World

Chapter 11: Web App: Implementing Regression using Keras

Lecture 1: Introduction to the dataset

Lecture 2: Project structure

Lecture 3: Load the data

Lecture 4: Handle Missing values

Lecture 5: Dependent and Independent variable

Lecture 6: Train Test split of data

Lecture 7: Building the model

Lecture 8: Make predictions

Lecture 9: Save the model

Lecture 10: Load model and make predictions

Lecture 11: Finding range: min and max value of each attributes

Lecture 12: Making range as dictionary

Lecture 13: Creating an Flask App to test API endpoint

Lecture 14: Testing the model

Lecture 15: Restrictions for Input to the model

Lecture 16: Using POSTMAN to test API endpoint

Chapter 12: Basics of Convolution Neural Network

Lecture 1: Introduction to Convolution Neural Network

Lecture 2: Kernel or filter

Lecture 3: Example of Kernel

Lecture 4: Stride

Lecture 5: Padding

Lecture 6: Pooling

Lecture 7: Flatten

Lecture 8: Layers of CNN

Chapter 13: Introduction to Transfer Learning

Lecture 1: What is Transfer Learning

Lecture 2: Traditional ML vs Transfer Learning

Lecture 3: How to use Transfer Learning

Lecture 4: MobileNet

Lecture 5: Architecture of MobileNet

Chapter 14: Web App: Implementing CNN (Mobile Net)

Lecture 1: Introducing Project

Lecture 2: Creating function to check allowed files

Lecture 3: Creating basic route

Lecture 4: Loading all libraries for the model

Lecture 5: Instantiating the model

Lecture 6: The "upload_image" function

Lecture 7: Checking if image is uploaded