Least Action Principles and Well-Posed Learning Problems

07/04/2019
by   Alessandro Betti, et al.
0

Machine Learning algorithms are typically regarded as appropriate optimization schemes for minimizing risk functions that are constructed on the training set, which conveys statistical flavor to the corresponding learning problem. When the focus is shifted on perception, which is inherently interwound with time, recent alternative formulations of learning have been proposed that rely on the principle of Least Cognitive Action, which very much reminds us of the Least Action Principle in mechanics. In this paper, we discuss different forms of the cognitive action and show the well-posedness of learning. In particular, unlike the special case of the action in mechanics, where the stationarity is typically gained on saddle points, we prove the existence of the minimum of a special form of cognitive action, which yields forth-order differential equations of learning. We also briefly discuss the dissipative behavior of these equations that turns out to characterize the process of learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/28/2018

Cognitive Action Laws: The Case of Visual Features

This paper proposes a theory for understanding perceptual learning proce...
research
07/14/2019

On the Role of Time in Learning

By and large the process of learning concepts that are embedded in time ...
research
09/01/2020

Developing Constrained Neural Units Over Time

In this paper we present a foundational study on a constrained method th...
research
01/16/2018

Convolutional Networks in Visual Environments

The puzzle of computer vision might find new challenging solutions when ...
research
11/01/2018

How the fundamental concepts of mathematics and physics explain deep learning

Starting from the Fermat's principle of least action, which governs clas...
research
07/14/2018

Motion Invariance in Visual Environments

The puzzle of computer vision might find new challenging solutions when ...
research
03/22/2019

Nonmodular architectures of cognitive systems based on active inference

In psychology and neuroscience it is common to describe cognitive system...

Please sign up or login with your details

Forgot password? Click here to reset