Neural network C++ Guided project tutorial

Neural network Simulator design in C++ Guided project

4.56 (8 reviews)
Udemy
platform
English
language
Other
category
instructor
Neural network C++ Guided project tutorial
40
students
2 hours
content
Dec 2022
last update
$39.99
regular price

What you will learn

The student will learn how to design the structure of a neural network including its neurons, bias, input layer, hidden layers, output layers and weights

The student will have a clear understanding of how the feed forward mechanism is used to shift inputs from the input layer through the output layer

The student will learn how to calculate the Root Mean Square error, output and hidden gradient, transfer function and the derivatives for a neural network

The student will also carryout back propagation on a neural network after the feed forward and use it for adjusting the weights of the neurons.

The student will learn how to generate training samples

Why take this course?

This course teaches the practical design of a Neural network simulator using C++. It is recommended for all levels of C++ programmers with a theoretical knowledge of Neural network and looking forward to implement them in practice. The course interactively simulates the Neural network from the design of the class called Neuron, to the implementation of the Neuron layers in Vectors and finally the top level design consisting of the input layer, hidden layer and the output layer. Some random training samples will be generated which will be feed to the input layer through a vector and progress to the output layer through feed forward. The back propagation is also implemented which enables us to calculate the error and update the weight for a more accurate result. The training samples used in this course is for demonstration as the concept of sample generation is well explained. At the end of the course the student should be able generate real samples for testings.

Some of the Core concepts we will learn in this course includes:

Feed forward .

Bias Neuron.

Transfer function.

Back propagation.

Activation function.

Root mean square error.

Transfer function derivative.

Generating training samples.

Output and hidden layer Gradient.


Some of the C++ concepts used includes:

Assert()

prototyping

Class design

Nested Vectors

Reference Variables

Static class variables

Data hiding and encapsulation



Reviews

Intars
December 27, 2023
[-] first, about shortcomings (weaker spots) of the course: to many natively English-speaking persons the first reflex possibly may be of immediately giving a less favorable review due to author's English speech accent which sometimes do and will call for careful and patient rewind of audio to 'learn', to get accustomed to nuances of pronunciation. Still, taking into account that for author English is not native language, i found that he does good job at explaining everything needed and everything going on in the code. The code's English itself is in very understandable English to any programmer (Subtitles for spoken text could be one possible enhancement for course material.) [+] good value: course could be of great value to anyone brave and curious enough to step outside of the usual and now overly fashionable Python/libraries/Tensorflow-encapsulated high abstractions comfort zone while dealing with the construction and implementation of neural network architectures in all their details. I found it very rewarding to follow the author in his efforts to demonstrate and showcase a possible way of creating a topology-wise customizable neural network architecture in a way that is more harder, less forgiving for mistakes, and more patience-demanding - in a C++ code with no AI-dedicated libraries in use. Author's C++ code is very logical; he introduces and brings to viewer's attention necessary additions to classes, new functions when a need for such addition/function arises first time - it helps to see how neural network procedural mechanics actually get chained and interrelated and what leads to what. Patient viewers will get a good reward for their efforts - a mental training and mental "muscle-stretching" for capacity of envisioning data structures, their parameters coming into complex dynamics interplay to enable mathematical abstractions like a neuron, hidden layers and backtracking coming into existence :) It is a great exercise to any programmer! Another of the course pluses is that the course demands some C/C++ knowledge: the viewer must come prepared or, metaphorically speaking - with some homework done already. That is a great thing.

Charts

Price

Neural network C++ Guided project tutorial - Price chart

Rating

Neural network C++ Guided project tutorial - Ratings chart

Enrollment distribution

Neural network C++ Guided project tutorial - Distribution chart

Related Topics

5022054
udemy ID
12/12/2022
course created date
12/23/2022
course indexed date
Bot
course submited by