Reader small image

You're reading from  Hands-On Neuroevolution with Python.

Product typeBook
Published inDec 2019
Reading LevelExpert
PublisherPackt
ISBN-139781838824914
Edition1st Edition
Languages
Right arrow
Author (1)
Iaroslav Omelianenko
Iaroslav Omelianenko
author image
Iaroslav Omelianenko

Iaroslav Omelianenko occupied the position of CTO and research director for more than a decade. He is an active member of the research community and has published several research papers at arXiv, ResearchGate, Preprints, and more. He started working with applied machine learning by developing autonomous agents for mobile games more than a decade ago. For the last 5 years, he has actively participated in research related to applying deep machine learning methods for authentication, personal traits recognition, cooperative robotics, synthetic intelligence, and more. He is an active software developer and creates open source neuroevolution algorithm implementations in the Go language.
Read more about Iaroslav Omelianenko

Right arrow

Visual discrimination experiment

Having done all of the necessary setup steps, we are ready to start the experiment.

In the visual discrimination experiment, we use the following configuration of the visual field:

Parameter

Value

Size of the visual field

11 x 11

Positions of the small objects in the visual field along each axis

[1, 3, 5, 7, 9]

Size of the small object

1 x 1

Size of the big object

3 x 3

Offset of the center of the big object from the small object

5

Next, we need to select the appropriate values of the HyperNEAT hyperparameters, allowing us to find a successful solution to the visual discrimination problem.

Note that the hyperparameter that we describe next determines how to evolve the connective CPPN using the neuroevolution process. The discriminator ANN is created by applying the connective CPPN to the substrate.
...
lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Hands-On Neuroevolution with Python.
Published in: Dec 2019Publisher: PacktISBN-13: 9781838824914

Author (1)

author image
Iaroslav Omelianenko

Iaroslav Omelianenko occupied the position of CTO and research director for more than a decade. He is an active member of the research community and has published several research papers at arXiv, ResearchGate, Preprints, and more. He started working with applied machine learning by developing autonomous agents for mobile games more than a decade ago. For the last 5 years, he has actively participated in research related to applying deep machine learning methods for authentication, personal traits recognition, cooperative robotics, synthetic intelligence, and more. He is an active software developer and creates open source neuroevolution algorithm implementations in the Go language.
Read more about Iaroslav Omelianenko