Neural Networks in Python from Scratch- Learning by Doing

Neural Networks in Python from Scratch: Learning by Doing, available at $74.99, has an average rating of 4.7, with 31 lectures, 2 quizzes, based on 46 reviews, and has 605 subscribers.

You will learn about Program neural networks for 3 different problems from scratch in plain Python Start simple: Understand input layer, output layer, weights, error function, accuracy, training & testing at an intuitive example Complicate the problem: Introduce hidden layers & activation functions for building more useful networks Real-life application: Use this network for image recognition This course is ideal for individuals who are This beginner-friendly course is for everyone! Especially if you: or Are curious about neural networks and want to really understand how they operate or Work in machine learning or data science but have not yet programed a neural network yourself from scratch or Want to really learn about machine learning without fancy frameworks/modules – Just you, me & standard python It is particularly useful for This beginner-friendly course is for everyone! Especially if you: or Are curious about neural networks and want to really understand how they operate or Work in machine learning or data science but have not yet programed a neural network yourself from scratch or Want to really learn about machine learning without fancy frameworks/modules – Just you, me & standard python.

Enroll now: Neural Networks in Python from Scratch: Learning by Doing

Summary

Title: Neural Networks in Python from Scratch: Learning by Doing

Price: $74.99

Average Rating: 4.7

Number of Lectures: 31

Number of Quizzes: 2

Number of Published Lectures: 31

Number of Published Quizzes: 2

Number of Curriculum Items: 33

Number of Published Curriculum Objects: 33

Original Price: $24.99

Quality Status: approved

Status: Live

What You Will Learn

Program neural networks for 3 different problems from scratch in plain Python

Start simple: Understand input layer, output layer, weights, error function, accuracy, training & testing at an intuitive example

Complicate the problem: Introduce hidden layers & activation functions for building more useful networks

Real-life application: Use this network for image recognition

Who Should Attend

This beginner-friendly course is for everyone! Especially if you:

Are curious about neural networks and want to really understand how they operate

Work in machine learning or data science but have not yet programed a neural network yourself from scratch

Want to really learn about machine learning without fancy frameworks/modules – Just you, me & standard python

Target Audiences

This beginner-friendly course is for everyone! Especially if you:

Are curious about neural networks and want to really understand how they operate

Work in machine learning or data science but have not yet programed a neural network yourself from scratch

Want to really learn about machine learning without fancy frameworks/modules – Just you, me & standard python

** The quickest way to understanding (and programming) neural networks using Python **

This course is for everyone who wants to learn how neural networks work by hands-on programming!

Everybody is talking about neural networks but they are hard to understand without setting one up yourself. Luckily, the mathematics and programming skills (python) required are on a basic levelso we can progam 3 neural networks in just over 3 hours. Do not waste your time! This course is optimized to give you the deepest insight into this fascinating topic in the shortest amount of time possible.

The focus is fully on learning-by-doing and I only introduce new concepts once they are needed.

What you will learn

After a short introduction, the course is separated into three segments – 1 hour each:

1) Set-up the most simple neural network: Calculate the sum of two numbers.
You will learn about:

Neural network architecture

Weights, input & output layer

Training & test data

Accuracy & error function

Feed-forward & back-propagation

Gradient descent

2) We modify this network: Determine the sign of the sum.
You will be introduced to:

Hidden layers

Activation function

Categorization

3) Our network can be applied to all sorts of problems, like image recognition: Determine hand-written digits!
After this cool and useful real-life application, I will give you an outlook:

How to improve the network

What other problems can be solved with neural networks?

How to use pre-trained networks without much effort

Why me?

My name is B?rge G?bel and I am a postdoc working as a scientist in theoretical physics where neural networks are used a lot.
I have refined my advisor skills as a tutor of Bachelor, Master and PhD students in theoretical physics and have other successful courses here on Udemy.

“Excellent course! In a simple and understandable way explained everything about the functioning of neural networks under the hood.” – Srdan Markovic

I hope you are excited and I kindly welcome you to our course!

Course Curriculum

Chapter 1: Introduction: Interpolation & Machine learning

Lecture 1: Overview of the course

Lecture 2: Template files for this course

Lecture 3: Interpolation (or regression) – The fundamental principle of machine learning

Chapter 2: Your first neural network: Sum of two numbers

Lecture 1: Lets get started!

Lecture 2: From interpolation to neural networks

Lecture 3: What are neural networks?

Lecture 4: [Project 1] Most simple neural network: Sum of two numbers

Lecture 5: Prepare the training and testing data

Lecture 6: Initialize the weights & Calculate the output

Lecture 7: Accuracy & Error functions

Lecture 8: Gradient of the error function

Lecture 9: Training the neural network via gradient descent

Lecture 10: Using the trained network on the test data

Lecture 11: Playing with the parameters

Chapter 3: Modifying the problem: Sign of the sum of two numbers

Lecture 1: [Project 2] Complete neural network: Sign of the sum of two numbers

Lecture 2: Modify input, output & weights

Lecture 3: Add an activation function to the neural network

Lecture 4: Modify accuracy and error functions

Lecture 5: Modify gradient of the error function

Lecture 6: Training & Testing the modified neural network

Chapter 4: Same code, different problem: Image recognition

Lecture 1: [Project 3] Same neural network: Applied to recognize hand-written digits

Lecture 2: Apply our neural network to the new problem: Number recognition

Lecture 3: Improve the gradient function

Lecture 4: Analysis of the trained neural network

Chapter 5: Outlook & Goodbye

Lecture 1: How to improve the network?

Lecture 2: Outlook: Pretrained neural networks & Machine learning in Wolfram Mathematica

Lecture 3: Goodbye!

Chapter 6: [Resources]

Lecture 1: [Installation] Python and Jupyter Notebook via Anaconda

Lecture 2: Template files

Lecture 3: Finalized jupyter notebooks

Lecture 4: Congratulations! Bonus Content!

Instructors

Dr. B?rge G?bel
Scientist in Quantum Physics, Programmer and Instructor

Rating Distribution

1 stars: 0 votes

2 stars: 2 votes

3 stars: 1 votes

4 stars: 10 votes

5 stars: 33 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!