Deep Information Networks
We describe a novel classifier with a tree structure, designed using information theory concepts. This Information Network is made of information nodes, that compress the input data, and multiplexers, that connect two or more input nodes to an output node. Each information node is trained, independe...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We describe a novel classifier with a tree structure, designed using
information theory concepts. This Information Network is made of information
nodes, that compress the input data, and multiplexers, that connect two or more
input nodes to an output node. Each information node is trained, independently
of the others, to minimize a local cost function that minimizes the mutual
information between its input and output with the constraint of keeping a given
mutual information between its output and the target (information bottleneck).
We show that the system is able to provide good results in terms of accuracy,
while it shows many advantages in terms of modularity and reduced complexity. |
---|---|
DOI: | 10.48550/arxiv.1803.02251 |