Machine Learning: Learn By Building Web Apps In Python
Published 9/2022
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz
Language: English | Size: 7.08 GB | Duration: 18h 2m
Published 9/2022
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz
Language: English | Size: 7.08 GB | Duration: 18h 2m
Learn basic to advanced Machine Learning algorithms by creating web applications using Flask!!
What you'll learn
Master Machine Learning on Python
Learn about Regression, Classification tasks
Learn about neural networks
Learn about Deep neural networks with projects
Create web applications using flask
Simple Model building with Scikit-Learn , TensorFlow and Keras
Creating REST API for Machine Learning models
Learn about Exploratory Data Analysis
Implement linear, logistic regression
Implement convolution neural network
Learn about Postman to test API endpoints
Requirements
Any laptop and an internet connection
Basic knowledge of Python programming is must
Description
Machine learning is a branch of artificial intelligence (AI) focused on building applications that learn from data and improve their accuracy over time without being programmed to do so.In data science, an algorithm is a sequence of statistical processing steps. In machine learning, algorithms are 'trained' to find patterns and features in massive amounts of data in order to make decisions and predictions based on new data. The better the algorithm, the more accurate the decisions and predictions will become as it processes more data.Machine learning has led to some amazing results, like being able to analyze medical images and predict diseases on-par with human experts.Google's AlphaGo program was able to beat a world champion in the strategy game go using deep reinforcement learning.Machine learning is even being used to program self driving cars, which is going to change the automotive industry forever. Imagine a world with drastically reduced car accidents, simply by removing the element of human error.Topics covered in this course:1. Warm-up with Machine learning Libraries: numpy, pandas2. Implement Machine Learning algorithms: Linear, Logistic Regression3. Implement Neural Network from scratch4. Introduction to Tensorflow and Keras5. Start with simple "Hello World" flask application6. Create flask application to implement linear regression and test the API's endpoints7. Implement transfer learning and built an app to implement image classification
Overview
Section 1: Introduction
Lecture 1 Introduction
Section 2: Setup and Creating Environment
Lecture 2 Install anaconda on your machine
Lecture 3 Set up environment and Download Machine Learning Libraries
Section 3: Introduction to Machine Learning for Absolute Beginners
Lecture 4 Types of Data in Machine Learning
Lecture 5 Introduction to numpy
Lecture 6 Introduction to pandas
Lecture 7 Train and Test split of data
Lecture 8 Miscellaneous Concept of Machine Learning
Section 4: Linear Regression in detail
Lecture 9 Lecture: Intro to Linear Regression
Lecture 10 Lecture: Learn about OLS [Ordinary Least Squares] algorithm
Lecture 11 Lecture: Introduction to working of Linear Regression
Lecture 12 Lecture: Introduction to MSE, MAE, RMSE
Lecture 13 Lecture: Introduction to R squared
Lecture 14 Tutorial: Implement Simple linear regression numerical [calculate best fit line]
Lecture 15 Workshop: Implement Simple Linear Regression
Lecture 16 Lecture: Difference between Simple and Multiple Regression
Lecture 17 Workshop: Implement Multiple Linear Regression
Lecture 18 Workshop: Implement Multiple Linear Regression
Section 5: Logistic Regression [optional]
Lecture 19 Lecture: Learn about Logistic Regression
Lecture 20 Lecture: Learn about hypothetical function [sigmoid/logit function]
Lecture 21 Lecture: Logistic Math Overview
Lecture 22 Lecture: Learn about decision boundary
Lecture 23 Lecture: Learn about Cost function of Logistic Regression
Lecture 24 Lecture: Learn about Gradient Descent
Lecture 25 Workshop: Implement Logistic Regression
Lecture 26 Workshop final: Implement Logistic Regression
Section 6: Neural Network in detail
Lecture 27 Introduction to Neural Networks
Lecture 28 Example of neural network
Lecture 29 Updating the weights [partial differentiation]
Lecture 30 Introduction to partial differentiation
Lecture 31 Introduction to the Activation Function
Lecture 32 Why do we need bias in the program
Lecture 33 Why we use regularization in the Neural Network
Lecture 34 Introduction to the gradient descent [review]
Lecture 35 Introduction to Stochastic Gradient Descent and Adam Optimizer
Lecture 36 Introduction to mini-batch SGD
Section 7: Coding Neural Network from Scratch [optional]
Lecture 37 Setting up environment and coding single neuron
Lecture 38 Coding neuron layer
Lecture 39 Using dot product to code neuron layer
Lecture 40 Coding dense layer [must know Object Oriented Programming]
Lecture 41 Introduction to Activation Function
Section 8: Activation Functions
Lecture 42 Implementation of activation function [step and sigmoid]
Lecture 43 Implementation of activation function [tanh and ReLu]
Section 9: Introduction to Tensorflow and Keras
Lecture 44 Introduction to Deep Learning
Lecture 45 Tensor Ranks in Tensorflow
Lecture 46 Program Elements in Tensorflow
Lecture 47 Coding in Tensorflow
Lecture 48 Introduction to Keras
Lecture 49 Keras Model [Most Important Video]
Lecture 50 Implementing neural network with Keras
Section 10: Creating Simple Flask Application ("Hello World")
Lecture 51 Flask: Display Hello World
Section 11: Web App: Implementing Regression using Keras
Lecture 52 Introduction to the dataset
Lecture 53 Project structure
Lecture 54 Load the data
Lecture 55 Handle Missing values
Lecture 56 Dependent and Independent variable
Lecture 57 Train Test split of data
Lecture 58 Building the model
Lecture 59 Make predictions
Lecture 60 Save the model
Lecture 61 Load model and make predictions
Lecture 62 Finding range: min and max value of each attributes
Lecture 63 Making range as dictionary
Lecture 64 Creating an Flask App to test API endpoint
Lecture 65 Testing the model
Lecture 66 Restrictions for Input to the model
Lecture 67 Using POSTMAN to test API endpoint
Section 12: Basics of Convolution Neural Network
Lecture 68 Introduction to Convolution Neural Network
Lecture 69 Kernel or filter
Lecture 70 Example of Kernel
Lecture 71 Stride
Lecture 72 Padding
Lecture 73 Pooling
Lecture 74 Flatten
Lecture 75 Layers of CNN
Section 13: Introduction to Transfer Learning
Lecture 76 What is Transfer Learning
Lecture 77 Traditional ML vs Transfer Learning
Lecture 78 How to use Transfer Learning
Lecture 79 MobileNet
Lecture 80 Architecture of MobileNet
Section 14: Web App: Implementing CNN (Mobile Net)
Lecture 81 Introducing Project
Lecture 82 Creating function to check allowed files
Lecture 83 Creating basic route
Lecture 84 Loading all libraries for the model
Lecture 85 Instantiating the model
Lecture 86 The "upload_image" function
Lecture 87 Checking if image is uploaded
Lecture 88 Checking whether or not image is selected
Lecture 89 Load the image
Lecture 90 Transform the image and store in numpy array
Lecture 91 Make Predictions
Programmer who wants to learn machine learning by creating web applications,Data Scientists who want to know how to test & monitor their models beyond,Beginner Python programmer,Machine Learning engineer who wants to create fun projects using their basic skills