Neural Networks for Machine Learning From Scratch

Neural Networks for Machine Learning From Scratch, available at $49.99, has an average rating of 4.2, with 17 lectures, 1 quizzes, based on 93 reviews, and has 595 subscribers.

You will learn about They can develop their own neural networks / deep learning framework Without any need to high level deep learning frameworks Tuning neural networks models Understand how neural networks work Learn how to apply neural networks in real world examples Even though, python is used in the course, you can easily adapt the logic into other programming languages This course is ideal for individuals who are Anyone who wants to learn mathematical background of neural networks and deep learning or Interested in Data Science, Artificial Intelligence and Machine Learning or Anyone who wants to develop their own deep learning framework or Anyone who wants to transform neural networks theory to practice It is particularly useful for Anyone who wants to learn mathematical background of neural networks and deep learning or Interested in Data Science, Artificial Intelligence and Machine Learning or Anyone who wants to develop their own deep learning framework or Anyone who wants to transform neural networks theory to practice.

Enroll now: Neural Networks for Machine Learning From Scratch

Summary

Title: Neural Networks for Machine Learning From Scratch

Price: $49.99

Average Rating: 4.2

Number of Lectures: 17

Number of Quizzes: 1

Number of Published Lectures: 17

Number of Published Quizzes: 1

Number of Curriculum Items: 20

Number of Published Curriculum Objects: 20

Original Price: $89.99

Quality Status: approved

Status: Live

What You Will Learn

They can develop their own neural networks / deep learning framework
Without any need to high level deep learning frameworks
Tuning neural networks models
Understand how neural networks work
Learn how to apply neural networks in real world examples
Even though, python is used in the course, you can easily adapt the logic into other programming languages

Who Should Attend

Anyone who wants to learn mathematical background of neural networks and deep learning
Interested in Data Science, Artificial Intelligence and Machine Learning
Anyone who wants to develop their own deep learning framework
Anyone who wants to transform neural networks theory to practice

Target Audiences

Anyone who wants to learn mathematical background of neural networks and deep learning
Interested in Data Science, Artificial Intelligence and Machine Learning
Anyone who wants to develop their own deep learning framework
Anyone who wants to transform neural networks theory to practice

Deep learning would be part of every developer’s toolbox in near future. It wouldn’t just be tool for experts.

In this course, we will develop our own deep learning framework in Python from zero to one whereas the mathematical backgrounds of neural networks and deep learning are mentioned concretely. Hands on programming approach would make concepts more understandable. So, you would not need to consume any high level deep learning framework anymore. Even though, python is used in the course, you can easily adapt the theory into any other programming language.

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Chapter 2: Single Layer Perceptrons

Lecture 1: What is perceptron?

Lecture 2: Perceptron from scratch

Chapter 3: Constructing Neural Networks Model

Lecture 1: Constructing Nodes

Lecture 2: Creating Weight Connections Between Nodes

Chapter 4: Feedforward Neural Networks

Lecture 1: Applying Feed Forward Neural Networks

Chapter 5: Neural Networks Learning: Backpropagation

Lecture 1: Backpropagation Theory

Lecture 2: Applying Backpropagation

Lecture 3: Loss function

Chapter 6: Tuning Neural Networks

Lecture 1: Activation Functions

Lecture 2: Sigmoid Function As A Neural Networks Activation Function

Lecture 3: Hyperbolic Tangent As A Neural Networks Activation Function

Lecture 4: Softplus as a neural networks activation function

Lecture 5: Adaptive Learning

Lecture 6: Momentum

Lecture 7: Feature Normalization

Chapter 7: Bonus

Lecture 1: Math Behind Backpropgation

Instructors

Sefik Ilkin Serengil
Software Engineer

Rating Distribution

1 stars: 6 votes
2 stars: 3 votes
3 stars: 6 votes
4 stars: 10 votes
5 stars: 68 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!

Menu