logo
ResearchBunny Logo
Online dynamical learning and sequence memory with neuromorphic nanowire networks

Physics

Online dynamical learning and sequence memory with neuromorphic nanowire networks

R. Zhu, S. Lilak, et al.

Discover the groundbreaking advancements in online learning from spatio-temporal dynamical features with remarkable accuracy achieved by the researchers, Ruomin Zhu, Sam Lilak, Alon Loeffler, Joseph Lizier, Adam Stieg, James Gimzewski, and Zdenka Kuncic. Their work shows how dynamic learning not only enhances image classification but also enables effective sequence memory recall, unlocking the potential of memory in learning.

00:00
00:00
Playback language: English
Abstract
This study demonstrates online learning from spatio-temporal dynamical features using image classification and sequence memory recall tasks implemented on a neuromorphic nanowire network (NWN) device. Applied to the MNIST handwritten digit classification task, online dynamical learning achieves 93.4% accuracy. A correlation between classification accuracy and mutual information is observed. The sequence memory task reveals how memory patterns embedded in dynamical features enable online learning and recall of spatiotemporal sequences, demonstrating how memory enhances learning.
Publisher
Nature Communications
Published On
Nov 01, 2023
Authors
Ruomin Zhu, Sam Lilak, Alon Loeffler, Joseph Lizier, Adam Stieg, James Gimzewski, Zdenka Kuncic
Tags
online learning
spatio-temporal features
image classification
sequence memory
neuromorphic devices
memory patterns

Related Publications

Explore these studies to deepen your understanding of the subject.

Transistors with ferroelectric ZrxAl₁₋ₓOY crystallized by ZnO growth for multi-level memory and neuromorphic computing
Engineering and Technology

Transistors with ferroelectric ZrxAl₁₋ₓOY crystallized by ZnO growth for multi-level memory and neuromorphic computing

M. M. Islam, A. Ali, et al.

Profiles of learners based on their cognitive and metacognitive learning strategy use: occurrence and relations with gender, intrinsic motivation, and perceived autonomy support
Education

Profiles of learners based on their cognitive and metacognitive learning strategy use: occurrence and relations with gender, intrinsic motivation, and perceived autonomy support

D. Kwarikunda, U. Schiefele, et al.

A wearable sensor and machine learning estimate step length in older adults and patients with neurological disorders
Medicine and Health

A wearable sensor and machine learning estimate step length in older adults and patients with neurological disorders

A. Zadka, N. Rabin, et al.

Improved Fault Classification and Localization in Power Transmission Networks Using VAE-Generated Synthetic Data and Machine Learning Algorithms
Engineering and Technology

Improved Fault Classification and Localization in Power Transmission Networks Using VAE-Generated Synthetic Data and Machine Learning Algorithms

M. A. Khan, B. Asad, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny