Machine Learning: Learn By Building Web Apps in Python
- Description
- Curriculum
- FAQ
- Reviews
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, pandas
2. Implement Machine Learning algorithms: Linear, Logistic Regression
3. Implement Neural Network from scratch
4. Introduction to Tensorflow and Keras
5. Start with simple “Hello World” flask application
6. Create flask application to implement linear regression and test the API’s endpoints
7. Implement transfer learning and built an app to implement image classification
-
8
Lecture: Intro to Linear Regression -
9
Lecture: Learn about OLS [Ordinary Least Squares] algorithm
-
10
Lecture: Introduction to working of Linear Regression
-
11
Lecture: Introduction to MSE, MAE, RMSE
-
12
Lecture: Introduction to R squared
-
13
Tutorial: Implement Simple linear regression numerical [calculate best fit line]
-
14
Workshop: Implement Simple Linear Regression
-
15
Lecture: Difference between Simple and Multiple Regression
-
16
Workshop: Implement Multiple Linear Regression
-
17
Workshop: Implement Multiple Linear Regression
-
18
Lecture: Learn about Logistic Regression
-
19
Lecture: Learn about hypothetical function [sigmoid/logit function]
-
20
Lecture: Logistic Math Overview
-
21
Lecture: Learn about decision boundary
-
22
Lecture: Learn about Cost function of Logistic Regression
-
23
Lecture: Learn about Gradient Descent
-
24
Workshop: Implement Logistic Regression
-
25
Workshop final: Implement Logistic Regression
-
26
Introduction to Neural Networks
-
27
Example of neural network
-
28
Updating the weights [partial differentiation]
-
29
Introduction to partial differentiation
-
30
Introduction to the Activation Function
-
31
Why do we need bias in the program
-
32
Why we use regularization in the Neural Network
-
33
Introduction to the gradient descent [review]
-
34
Introduction to Stochastic Gradient Descent and Adam Optimizer
-
35
Introduction to mini-batch SGD
-
51
Introduction to the dataset
-
52
Project structure
-
53
Load the data
-
54
Handle Missing values
-
55
Dependent and Independent variable
-
56
Train Test split of data
-
57
Building the model
-
58
Make predictions
-
59
Save the model
-
60
Load model and make predictions
-
61
Finding range: min and max value of each attributes
-
62
Making range as dictionary
-
63
Creating an Flask App to test API endpoint
-
64
Testing the model
-
65
Restrictions for Input to the model
-
66
Using POSTMAN to test API endpoint
