Artificial Intelligence


Using Student Learning Based on Fluency for the Learning Rate in a Deep Convolutional Neural Network

Authors: Abien Fred Agarap

This is a proposal for mathematically determining the learning rate to be used in a deep supervised convolutional neural network (CNN), based on student fluency. The CNN model shall be tasked to imitate how students play the game “Packet Attack”, a form of gamification of information security awareness training, and learn in the same rate as the students did. The student fluency shall be represented by a mathematical function constructed using natural cubic spline interpolation, and its derivative shall serve as the learning rate for the CNN model. If proven right, the results will imply a more human-like rate of learning by machines.

Comments: 23 Pages.

Download: PDF

Submission history

[v1] 2017-05-28 12:05:57

Unique-IP document downloads: 54 times is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus