Unsupervised Digit Recognition Using Cosine Similarity In A Neuromemristive Competitive Learning System

This work addresses how to naturally adopt the l 2 -norm cosine similarity in the neuromemristive system and studies the unsupervised learning performance on handwritten digit image recognition. Proposed architecture is a two-layer fully connected neural network with a hard winner-take-all (WTA) lea...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	ACM journal on emerging technologies in computing systems 2022-04, Vol.18 (2), p.1-20
Hauptverfasser:	Ku, Bon Woong, Schuman, Catherine D., Adnan, Md Musabbir, Mintz, Tiffany M., Pooser, Raphael, Hamilton, Kathleen E., Rose, Garrett S., Lim, Sung Kyu
Format:	Artikel
Sprache:	eng
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!