Fractally-organized Connectionist Networks: Conjectures and Preliminary Results

05/18/2015
by   Vincenzo De Florio, et al.
0

A strict interpretation of connectionism mandates complex networks of simple components. The question here is, is this simplicity to be interpreted in absolute terms? I conjecture that absolute simplicity might not be an essential attribute of connectionism, and that it may be effectively exchanged with a requirement for relative simplicity, namely simplicity with respect to the current organizational level. In this paper I provide some elements to the analysis of the above question. In particular I conjecture that fractally organized connectionist networks may provide a convenient means to achive what Leibniz calls an "art of complication", namely an effective way to encapsulate complexity and practically extend the applicability of connectionism to domains such as sociotechnical system modeling and design. Preliminary evidence to my claim is brought by considering the design of the software architecture designed for the telemonitoring service of Flemish project "Little Sister".

READ FULL TEXT

page 5

page 8

research
06/02/2023

Should Computers Be Easy To Use? Questioning the Doctrine of Simplicity in User Interface Design

That computers should be easy to learn and use is a rarely-questioned te...
research
07/01/2019

Information Kernels

Given a set X of finite strings, one interesting question to ask is whet...
research
08/16/2021

A Conjecture Equivalent to the Collatz Conjecture

We present a formulation of the Collatz conjecture that is potentially m...
research
06/06/2021

CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings

Without positional information, attention-based transformer neural netwo...
research
08/09/2023

Eigenvector Dreaming

Among the performance-enhancing procedures for Hopfield-type networks th...
research
10/12/2021

The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks

In this paper, we conjecture that if the permutation invariance of neura...
research
04/18/2023

Searching for ribbons with machine learning

We apply Bayesian optimization and reinforcement learning to a problem i...

Please sign up or login with your details

Forgot password? Click here to reset