Astronomy Data Science With Python Programming
 

What you'll learn
Master Python programming, including data structures, loops, and libraries like NumPy and Matplotlib.
Learn digital image processing and apply convolution, edge detection, and filters on real-world datasets.
Understand and implement machine learning models like Linear and Logistic Regression using Python.
Build and train neural networks and convolutional neural networks (CNNs) from scratch using TensorFlow and Keras.
Requirements
No Programming or Astronomy Experience Required
Description
This course is designed to take you from a beginner to a confident practitioner in Python programming, image processing, and machine learning. Through step-by-step lessons and hands-on projects, you will build a solid foundation in these essential skills and apply them to real-world problems.What You'll Learn:Python Programming: Master Python basics, including data types, variables, loops, conditional statements, and libraries like NumPy and Matplotlib.Image Processing: Learn how to process digital images using Python, including convolution operations, edge detection, and filters.Machine Learning: Gain a strong understanding of core ML concepts, including Linear and Logistic Regression, with practical coding examples.Deep Learning and CNNs: Build neural networks from scratch, train them using TensorFlow and Keras, and explore convolutional neural networks (CNNs).Hands-on Projects:You'll work on engaging projects such as:Analyzing real astronomical image datasets like NGC3184 and M87.Building and training machine learning models for classification and regression tasks.Implementing neural networks and CNNs to solve real-world problems using Kaggle datasets.Who This Course Is For:Beginners with no prior experience in Python or machine learning.Students and professionals looking to strengthen their knowledge of AI and data science.Anyone interested in exploring how programming and AI are applied to real-world scenarios, such as image processing and astronomy.By the end of this course, you'll have the skills to confidently build Python programs, process digital images, and implement machine learning models. Whether you're a student, researcher, or tech enthusiast, this course will empower you to take the next step in your learning journey.Let me know if you'd like to adjust this further!
Overview
Section 1: Python Module
Lecture 1 Introduction
Lecture 2 Python Module
Lecture 3 Python Comments
Lecture 4 Data Type - Strings
Lecture 5 Variables and Constants
Lecture 6 Data Type - Numerical
Lecture 7 Data Types Conversion
Lecture 8 Data Type - Boolean and Python Operators
Lecture 9 String Methods
Lecture 10 Data Structure - List
Lecture 11 Data Structure - Tuple
Lecture 12 Data Structure - Set
Lecture 13 Data Structure - Dictionary
Lecture 14 Data Structure Conversions
Lecture 15 Conditional Statements
Lecture 16 For Loop
Lecture 17 While Loop
Lecture 18 Functions
Lecture 19 Object Oriented Programming
Lecture 20 Numpy Library - 1
Lecture 21 Numpy Library - 2
Lecture 22 Matplotlib Library
Lecture 23 Module 1 Conclusion
Section 2: Image Processing
Lecture 24 Image Processing Module
Lecture 25 Digital Images
Lecture 26 Bits and Bits per Pixel
Lecture 27 Digital Image Processing and Computer Vision
Lecture 0 Images in Python - 1
Lecture 28 Images in Python - 2
Lecture 29 Convolutions
Lecture 30 Gaussian Kernel
Lecture 31 Unsharp Mask
Lecture 32 Canny Edge Detector
Lecture 33 Basic Multiscale Features
Lecture 34 FITS Files
Lecture 35 Galaxies Morphology Classification
Lecture 0 Header - NGC3184
Lecture 36 Image Data - NGC3184
Lecture 37 Wide Scale and Nucleus Scale - NGC3184
Lecture 38 Implement Filters on Image Data - NGC3184
Lecture 39 Concluding - NGC3184 Project
Lecture 40 Introducing M87 and M87*
Lecture 41 Exploring M87 using Python - 1
Lecture 42 Exploring M87 using Python - 2
Lecture 43 Exploring M87 using Python - 3
Lecture 44 Module 2 Conclusion
Section 3: Introduction to Machine Learning
Lecture 45 Introduction to Machine Learning
Lecture 46 Introduction to Artificial Intelligence and Machine Learning
Lecture 47 Applications of Artificial Intelligence
Lecture 48 Supervised vs Unsupervised vs Reinforcement
Lecture 49 Linear Regression: Intuition
Lecture 50 Linear Regression: Cost Function
Lecture 51 Linear Regression: Gradient Descent
Lecture 52 Get ready with the Code Along file!
Lecture 0 Generate the Dummy Training Dataset
Lecture 53 Customise the Plot and Get Ready with Model Parameters
Lecture 54 Build functions for prediction and cost
Lecture 0 Build function for Updating Parameters
Lecture 55 Build function for Training and Train the Model
Lecture 56 Check the Model Performance
Lecture 57 Generate the Testing Dataset and Evaluate the Model
Lecture 58 Introduction to Logistic Regression
Lecture 0 Dataset and Aim
Lecture 59 Explore the Dataset
Lecture 0 Prepare the Dataset and Pipeline
Lecture 0 Use Pipeline for Training and Testing
Lecture 60 Download the Pipeline and Test it
Lecture 61 Module 3 Conclusion
Section 4: Introduction to Deep Learning
Lecture 62 Introduction to Deep Learning
Lecture 63 What is Deep Learning?
Lecture 0 Artificial Neuron and Biological Neuron
Lecture 64 Introduction to Multi-Layer Perceptron
Lecture 0 Most Commonly used Activation Functions
Lecture 65 Problem Statement to Build a Neural Network from scratch
Lecture 0 Understanding the Network to Build
Lecture 0 Equations - Cost Function, Forward and Backward Propagation
Lecture 66 Derivation of Backward Propagation Equations
Lecture 67 Code the Neural Network from Scratch
Lecture 0 Problem Statement and Adding Data to Notebook
Lecture 0 Read the csv file and explore the data
Lecture 68 Create Visualisations
Lecture 69 Split the Data into Training and Testing
Lecture 70 Preprocessing the Data
Lecture 71 Build the Network using Tensorflow and Keras and Compile it
Lecture 0 Train the Network and Visualise the Training
Lecture 0 Test the Model on the Unseen Data
Lecture 0 Concluding the Problem Statement and Saving the Model
Lecture 0 Module 4 Conclusion
Section 5: Convolutional Neural Networks (CNNs)
Lecture 0 Convolutional Neural Networks (CNNs)
Lecture 0 Example of a CNN Architecture
Lecture 72 Calculate the Output Shape of Conv2D layer
Lecture 0 Calculate total trainable Parameters in Conv2D layer
Lecture 73 Example of a complete Convolution Calculation
Lecture 74 Summary of convolution operation
Lecture 0 Pooling Operation
Lecture 75 Fully Connected Layers
Lecture 76 Kaggle Setup
Lecture 77 Intro to Dataset and Problem Statement
Lecture 78 Get the Dataset in the notebook
Lecture 79 Importing libraries
Lecture 80 Read the csv file and perform the train test split
Lecture 81 Visualise random images in the data
Lecture 82 Create a function to preprocess one image
Lecture 83 Create a function to preprocess all the images in the data
Lecture 84 Build, Compile the CNN Model
Lecture 85 Train the CNN Model
Lecture 86 Make the predictions on the test dataset
Lecture 87 Module 5 Conclusion
Lecture 88 Course Conclusion
Aspiring Data Scientists and ML Engineers,Students and Professionals,Tech Enthusiasts,Researchers and Hobbyists
Screenshot