Machine Learning: Neural networks from scratch

Machine Learning: Neural networks from scratch, available at $39.99, has an average rating of 4.5, with 30 lectures, based on 17 reviews, and has 104 subscribers.

You will learn about What are neural networks Implement a neural network from scratch (Python, Java, C, …) Training neural networks Activation functions and the universal approximation theorem Strengthen your knowledge in Machine Learning and Data Science Implementation tricks: Jacobian-Vector product & log-sum-exp trick This course is ideal for individuals who are For developers who would like to implement a neural network without using dedicated libraries or For those who study machine learning and would like to strengthen their knowledge about neural networks and automatic differentiation frameworks or For those preparing for job interviews in data science or To artificial intelligence enthusiasts It is particularly useful for For developers who would like to implement a neural network without using dedicated libraries or For those who study machine learning and would like to strengthen their knowledge about neural networks and automatic differentiation frameworks or For those preparing for job interviews in data science or To artificial intelligence enthusiasts.

Enroll now: Machine Learning: Neural networks from scratch

Summary

Title: Machine Learning: Neural networks from scratch

Price: $39.99

Average Rating: 4.5

Number of Lectures: 30

Number of Published Lectures: 30

Number of Curriculum Items: 30

Number of Published Curriculum Objects: 30

Original Price: $39.99

Quality Status: approved

Status: Live

What You Will Learn

What are neural networks
Implement a neural network from scratch (Python, Java, C, …)
Training neural networks
Activation functions and the universal approximation theorem
Strengthen your knowledge in Machine Learning and Data Science
Implementation tricks: Jacobian-Vector product & log-sum-exp trick

Who Should Attend

For developers who would like to implement a neural network without using dedicated libraries
For those who study machine learning and would like to strengthen their knowledge about neural networks and automatic differentiation frameworks
For those preparing for job interviews in data science
To artificial intelligence enthusiasts

Target Audiences

For developers who would like to implement a neural network without using dedicated libraries
For those who study machine learning and would like to strengthen their knowledge about neural networks and automatic differentiation frameworks
For those preparing for job interviews in data science
To artificial intelligence enthusiasts

In this course, we will implement a neural network from scratch, without dedicated libraries. Although we will use the python programming language, at the end of this course, you will be able to implement a neural network in any programming language.

We will see how neural networks work intuitively, and then mathematically. We will also see some important tricks, which allow stabilizing the training of neural networks (log-sum-exp trick), and to prevent the memory used during training from growing exponentially (jacobian-vector product). Without these tricks, most neural networks could not be trained.

We will train our neural networks on real image classification and regression problems. To do so, we will implement different cost functions, as well as several activation functions.

This course is aimed at developers who would like to implement a neural network from scratch as well as those who want to understand how a neural network works from A to Z.

This course is taught using the Python programming language and requires basic programming skills. If you do not have the required background, I recommend that you brush up on your programming skills by taking a crash course in programming. It is also recommended that you have some knowledge of Algebra and Analysis to get the most out of this course.

Concepts covered :

Neural networks
Implementing neural networks from scratch
Gradient descent and Jacobian matrix
The creation of Modules that can be nested in order to create a complex neural architecture
The log-sum-exp trick
Jacobian vector product
Activation functions (ReLU, Softmax, LogSoftmax, …)
Cost functions (MSELoss, NLLLoss, …)

This course will be frequently updated, with the addition of bonuses.

Don’t wait any longer before launching yourself into the world of machine learning!

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Lecture 2: Neural networks: intuitive explanation

Chapter 2: Forward propagation

Lecture 1: Forward propagation: explanation

Lecture 2: Forward propagation: implementation

Lecture 3: Activation function: ReLU

Lecture 4: Sequential neural networks

Chapter 3: Image classification

Lecture 1: Saving and loading neural network parameters

Lecture 2: Image classification: part 1

Lecture 3: Image classification: part 2

Lecture 4: Activation function: Softmax

Chapter 4: Backward propagation

Lecture 1: Optimization by gradient descent

Lecture 2: Jacobian matrix

Lecture 3: Jacobian matrix: implementation

Lecture 4: Chain rule

Lecture 5: Chain rule: implementation

Chapter 5: Regression

Lecture 1: Mean Square Error Loss

Lecture 2: Testing

Lecture 3: Neural network training

Lecture 4: Optimizers

Lecture 5: Regression problem: quantitative measure of diabetes progression

Lecture 6: Activation function: LogSoftmax

Lecture 7: The Log-Sum-Exp Trick

Lecture 8: Negative Log-Likelihood Loss

Chapter 6: Improvements and tricks

Lecture 1: Batching: Multilayer Perceptron (MLP)

Lecture 2: Batching: losses

Lecture 3: Batching: activation functions

Lecture 4: Jacobian-vector product

Lecture 5: Xavier Initialization

Chapter 7: Image classification and conclusion

Lecture 1: Image classification

Lecture 2: Conclusion

Instructors

Maxime Vandegar
Ingénieur de recherche

Rating Distribution

1 stars: 1 votes
2 stars: 0 votes
3 stars: 2 votes
4 stars: 2 votes
5 stars: 12 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