Course Information
Registration period
Year-round Recruitment
Course Level
Study Mode
Duration
3 Hour(s) 38 Minute(s)
Language
English
Taught by
Holczer Balazs
Rating
Course Overview
Neural networks, gradient descent and backpropagation algorithms explained step by step
This course is about artificial neural networks. Artificial intelligence and machine learning are getting more and more popular nowadays. In the beginning, other techniques such as Support Vector Machines outperformed neural networks, but in the 21th century neural networks again gain popularity. In spite of the slow training procedure, neural networks can be very powerful. Applications ranges from regression problems to optical character recognition and face detection.
Section 1:
what are neural networks
modeling the human brain
the big picture
Section 2:
what is back-propagation
feedforward neural networks
optimizing the cost function
error calculation
backpropagation and gradient descent
Section 3:
the single perceptron model
solving linear classification problems
logical operators (AND and XOR operation)
Section 4:
applications of neural networks
clustering
classification (Iris-dataset)
optical character recognition (OCR)
smile-detector application from scratch
In the first part of the course you will learn about the theoretical background of neural networks, later you will learn how to implement them.
If you are keen on learning methods, let's get started!
In the first part of the course you will learn about the theoretical background of neural networks, later you will learn how to implement them.
If you are keen on learning methods, let's get started!
Course Content
- 10 section(s)
- 41 lecture(s)
- Section 1 Introduction
- Section 2 Artificial Intelligence Basics
- Section 3 Neural Networks With Backpropagation Theory
- Section 4 Single Perceptron Model
- Section 5 Backpropagation Implementation
- Section 6 Logical Operators
- Section 7 Clustering
- Section 8 Classification - Iris Dataset
- Section 9 Optical Character Recognition (OCR)
- Section 10 Course Materials (DOWNLOADS)
What You’ll Learn
- Basics of neural networks
- Hopfield networks
- Concrete implementation of neural networks
- Backpropagation
- Optical character recognition
Skills covered in this course
Reviews
-
RRoberto Ceccarelli
I really enjoyed it! I did not know anything about it and I now have more than a rough idea! Thanks!
-
NNata Kanevel
How can this theory be used in practice? I missed half of it because it all sounds incomprehensible. What is the usefulness of this theory?
-
PPawel Jasinski
I've attended the other Udemy course of the author: "Artificial Intelligence I: Optimization and Games in Java" which was good. But this one is better as I can see a huge progress in using English or presenting skills. Also, the material covered here is more advanced but taught in a nice and understandable way. Unfortunately, there are some errors in the slights (i.e. in the backprogation mathematical explanation). I do not recommend this course for students who are very new to the concept of the artificial intelligence as quite complex topics are mentioned. If you are not familiar with AI, then please try "Artificial Intelligence I: Optimization and Games in Java" first.
-
EEitan Mizrahi
The course is fine and enthusiasm, becuase the subject of AI is very attractive. The lecturer is fine (has quite knowledge), but get his knowledge by his own perspective, and not always the things are understood. Little disapponted by that I cannot download a document of some basic functions So I need to run all over again the whole course, and write in some notebook the formulas + some explanation. Some of the concept are intuative clear, and some of them not clear enough - The lecturer provide way solving problem. Not always ways how he reached that calculations Better knowing "what behind scense" is important to understand. Also, give some quiz - to check myself. I persume I failed if I tried passing a test just after the lecture. To summaraize - the lecturer is fine, giving the most basic needed for learning AI. The rest - need to work very hard to implements some basic AI algorithms, bulding the network! Maybe reading some more lectures and examples.
