HomeCoursesMake Your Own Neural Network in Python

4.5

Beginner

Make Your Own Neural Network in Python

Gain insights into building and optimizing neural networks in Python. Delve into fundamental concepts, mathematical explanations, and practical implementations to enhance your machine learning skills.

Join 2.7 million developers at

Overview

Content

Reviews

Machine learning is one of the fastest growing fields, and we cannot emphasize enough about its importance. This course aims to teach one of the fundamental concepts of machine learning, i.e., Neural Network. You will learn the basic concepts of building a model as well as the mathematical explanation behind Neural Network and based on that; you will build one from scratch (in Python). You will also learn how to train and optimize your network to achieve a better result.

Machine learning is one of the fastest growing fields, and we cannot emphasize enough about its importance. This course aims to ...Show More

Content

83 Lessons

Prologue

3 Lessons

Get familiar with AI's evolution, neural networks, and building your own in Python.

The Search for Intelligent Machines

A Nature Inspired New Golden Age

Introduction

A Little Background

10 Lessons

Grasp the fundamentals of neural network basics, prediction models, classification, and training processes.

Humans vs. Computers

A Simple Prediction Machine

Estimate the Constant Iteratively

Classify vs. Predict

Build a Simple Classifier

Errors in the Training Classifier

Refine the Parameters of the Training Classifier

Set Up a Learning Rate in the Training Classifier

Limitations of Linear Classifiers

Represent Boolean Functions with Linear Classification

Let's Get Started!

11 Lessons

Explore the foundational concepts of neural networks, from biological neurons to matrix calculations.

Neurons: Nature’s Computing Machines

How Neurons Work

Activation Functions

Replicate Neurons in an Artificial Model

Follow Signals through a Simple Network

Calculate Neural Network Output

Matrix Multiplication

Calculate the Inputs for Internal Layers

A Three-Layer Example: Working on the Input Layer

A Three-Layer Example: Working on the Hidden Layer

A Three-Layer Example: Working on the Output Layer

Backward Propagation of Error

5 Lessons

Break down the steps to efficient error correction using backpropagation in neural networks.

Learn Weights from More than One Node

Error Backpropagation from More Output Nodes

Backpropagation: Splitting the Error

Backpropagation: Recombine the Error

Error Backpropagation with Matrix Multiplication

Adjusting the Link Weights

10 Lessons

Dig into updating link weights, gradient descent optimization, and preparing neural network data.

Update Weights

Embrace Pessimism

Gradient Descent Algorithm

Transform the Output into an Error Function

Use Gradient Descent to Update Weights

Choose the Right Weights Iteratively

The Error Slope between the Input and Hidden Layers

Weight Updates Calculated

Prepare Data: Inputs and Outputs

Prepare Data: Random Initial Weights

A Gentle Start with Python

7 Lessons

Simplify complex topics in Python, loops, functions, arrays, plotting, objects, and methods.

An Introduction to Python

Neural Network with Python

8 Lessons

Learn how to improve your skills in building, training, and initializing neural networks in Python.

Build the Neural Network Class

Initialize the Neural Network

Weights: The Heart of the Network

Query the Network

Apply the Sigmoid Function

Python Code for a Basic Neural Network

Train the Network

Complete Code for a Neural Network

Testing Neural Network against MNIST Dataset

11 Lessons

Step through evaluating and testing your neural network using the MNIST dataset.

The MNIST Dataset

MNIST Data File

Get the Dataset Ready

Plot the Data Points

Prepare the MNIST Training Data

Rescale the Target Output

Create a Target Array

Update the Neural Network Code

Test the Network on a Subset

Test the Network on the Whole Dataset

Evaluate the Performance of the Neural Network

Some Suggested Improvements

4 Lessons

Unpack the core of optimizing neural network performance through learning rate, epochs, and structure adjustments.

Tweak the Learning Rate

Do Multiple Runs

Change the Network Shape

The Final Neural Network for MNIST Dataset

10.

Even More Fun!

4 Lessons

Examine neural networks' adaptability with personal handwriting, internal visualization, and data augmentation through rotations.

Query on Our Own Handwriting

Inside the Mind of a Neural Network

More Brain Scans

Create New Training Data with Rotations

11.

Epilogue

1 Lessons

Grasp the fundamentals of neural networks and their impact on AI advancements.

Conclusion

12.

Appendix: A Small Guide to Calculus

9 Lessons

Dig into core calculus concepts and their applications in understanding variable changes.

A Gentle Introduction to Calculus

A Flat Line

A Sloped Straight Line

A Curved Line

Calculus Not by Hand

Calculus without Plotting Graphs

Patterns

Chain Rule

Handling Independent Variables

Certificate of Completion

Showcase your accomplishment by sharing your certificate of completion.

Course Author:

Tariq Rashid

Developed by MAANG Engineers

Every Educative lesson is designed by a team of ex-MAANG software engineers and PhD computer science educators, and developed in consultation with developers and data scientists working at Meta, Google, and more. Our mission is to get you hands-on with the necessary skills to stay ahead in a constantly changing industry. No video, no fluff. Just interactive, project-based learning with personalized feedback that adapts to your goals and experience.

Trusted by 2.7 million developers working at companies

"These are high-quality courses. Trust me. I own around 10 and the price is worth it for the content quality. EducativeInc came at the right time in my career. I'm understanding topics better than with any book or online video tutorial I've done. Truly made for developers. Thanks"

Anthony Walker

@_webarchitect_

"Just finished my first full #ML course: Machine learning for Software Engineers from Educative, Inc. ... Highly recommend!"

Evan Dunbar

ML Engineer

"You guys are the gold standard of crash-courses... Narrow enough that it doesn't need years of study or a full blown book to get the gist, but broad enough that an afternoon of Googling doesn't cut it."

Software Developer

Carlos Matias La Borde

"I spend my days and nights on Educative. It is indispensable. It is such a unique and reader-friendly site"

Souvik Kundu

Front-end Developer

"Your courses are simply awesome, the depth they go into and the breadth of coverage is so good that I don't have to refer to 10 different websites looking for interview topics and content."

Vinay Krishnaiah

Software Developer

Hands-on Learning Powered by AI

See how Educative uses AI to make your learning more immersive than ever before.

Personalized Interview Prep

Skip the LeetCode grind with a custom roadmap that adapts to your goals. Hands-on practice for Coding Interviews, System Design, and more.

Mock Interviews

Test your skills in a simulated interview setting. Receive personalized feedback based on your performance. Available for Coding Interviews, System Design, and more.

AI Prompt

Build prompt engineering skills. Practice implementing AI-informed solutions.

Code Feedback

Evaluate and debug your code with the click of a button. Get real-time feedback on test cases, including time and space complexity of your solutions.

Explain with AI

Select any text within any Educative course, and get an instant explanation — without ever leaving your browser.

AI Code Mentor

AI Code Mentor helps you quickly identify errors in your code, learn from your mistakes, and nudge you in the right direction — just like a 1:1 tutor!

Free Resources

FOR TEAMS

Interested in this course for your business or team?

Unlock this course (and 1,000+ more) for your entire org with DevPath