Neural Networks In Python From Scratch. Build step by step!
What you'll learn
- The basic functions for any neural network, by coding linear regression, cost functions and back propagation
- Understand the properties of neural networks by adjusting learning rates and biases
- Train a network by implementing a gradient descent algorithm
- Normalizing inputs for multi-input networks
- Create classification networks by implementing multiple output neurons and activation
- Improve network accuracy by implementing hidden layers for non-linear data
Requirements
- You have an interest in neural networks.
- You have some programming experience in Python or another language.
Description
You will learn how to build Neural Networks with Python. Without the need for any library, you will see how a simple neural network from 4 lines of code, evolves into a artificial intelligence network that is able to recognize handwritten digits.
During this process, you will learn concepts like: Feed forward, Cost functions, Back propagation, Hidden layers, Linear regression, Gradient descent and Matrix multiplication. And all this with plain Python.
Target audience
Developers who especially benefit from this course, are:
Developer who want to learn the mechanics of neural networks
Developers who want to avoid using neural network libraries and frameworks
Or developers who use frameworks but want to learn the meaning of the individual network parameters
Challenges
Many tutorials claim to start from scratch, but import external libraries or rapidly type in code and before executing even once, you are looking at 50 lines of code. When finally the code is run, you are totally lost and still stuck trying to understand line 3.
This causes many students to give up learning Neural Networks.
This course is different! It starts with the absolute beginning and each topic is a continuation of a previous example. This way, you will learn neural networks from the ground up, step by step.
What can you do after this course?
You understand neural network concepts and ideas, like back propagation and gradient descent.
You are able to build a neural network in any programming language of choice, without the help of frameworks and libraries.
You understand how to better configure the network by plugging in different cost functions and adding hidden layers.
Topics
Linear regression
Cost functions
Bias
Multiple inputs
Normalisation
Gradient descent
Classification
Activation
Multi-class classification
Non-linear data
Hidden layers
Duration
3 hour video time. This course has no exercises.
The teacher
This course is taught by Loek van den Ouweland, a senior software engineer with 25 years of professional experience. Loek is the creator of Wunderlist for windows, Microsoft To-do and Mahjong for Windows and loves to teach software engineering.
Students of this course tell me:
* * * * * “Great, simple explanations. Perfect for beginners that have little pre knowledge of the topic.”
* * * * * “Straight to the point starting with the foundations.”
* * * * * “Clearly explained step by step how Neural Networks work and can be developed in a pure development language of choice without the usage of any external package..”
Who this course is for:
- Developer who want to learn the mechanics of neural networks
- Developers who want to avoid using neural network libraries and frameworks
- Developers who use frameworks but want to learn the meaning of the individual network parameters
Instructor
- 4.8 Instructor Rating
- 1,123 Reviews
- 3,457 Students
- 10 Courses
Loek van den Ouweland (Wunderlist, Microsoft Todo) is a born teacher. Right from the start of his career, he was told that a programmer helps his customers best when he shows what his products can do and how they are built.
He worked in many companies as programmer and trainer and enjoys to share the secrets of programming with others.
Loek has 25 years of experience training people with different backgrounds, all ages, working in branches ranging from medical systems to manufacturing and academics to aerospace.