Neural reuse can drive organisms to generalize knowledge across various tasks during learning. However, existing devices mostly focus on architectures rather than network functions, lacking the mimic capabilities of neural reuse. Here, we demonstrate a rational device designed based on ferroionic CuInPS, to accomplish the neural reuse function, enabled by dynamic allocation of the ferro-ionic phase. It allows for dynamic refresh and collaborative work between volatile and non-volatile modes to support the entire neural reuse process. Notably, ferroelectric polarization can remain consistent even after undergoing the refresh process, providing a foundation for the shared functionality across multiple tasks. By implementing neural reuse, the classification accuracy of neuromorphic hardware can improve by 17%, while the consumption is reduced by 40%; in multi-task scenarios, its training speed is accelerated by 2200%, while its generalization ability is enhanced by 21%. Our results are promising towards building refreshable hardware platforms based on ferroelectric-ionic combination capable of accommodating more efficient algorithms and architectures.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11735814 | PMC |
| http://dx.doi.org/10.1038/s41467-024-55701-0 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
An unconventional separation method of α-Terpineol from its isomer 1,8-Cineole via in situ-association formation of deep eutectic solvent and machine learning.
J Chromatogr A
January 2025
College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, PR China. Electronic address:
α-Terpineol and 1,8-cineole are two important compounds in essential oils. This study developed an efficient method to recover α-terpineol from model oil (MO) based on association extraction by in situ formations of deep eutectic solvent (DES) between α-terpineol and some quaternary ammonium salts (QASs) by hydrogen-bond (HB) interaction. Such interaction could be broken almost completely by the introduction of water, due to the stronger HB interaction between water and QASs, which could release α-terpineol by liquid-liquid separation and save the organic solvents consumption.
View Article and Find Full Text PDFEnhanced brain tumor detection and segmentation using densely connected convolutional networks with stacking ensemble learning.
Comput Biol Med
January 2025
Emerging Technologies Research Lab (ETRL), College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia; Department of Computer Science, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia. Electronic address:
- Brain tumors (BT), both benign and malignant, pose a substantial impact on human health and need precise and early detection for successful treatment. Analysing magnetic resonance imaging (MRI) image is a common method for BT diagnosis and segmentation, yet misdiagnoses yield effective medical responses, impacting patient survival rates. Recent technological advancements have popularized deep learning-based medical image analysis, leveraging transfer learning to reuse pre-trained models for various applications.
View Article and Find Full Text PDFSelf-supervised learning (SSL) is an approach to pretrain models with unlabeled datasets and extract useful feature representations such that these models can be easily fine-tuned for various downstream tasks. Self-pretraining applies SSL on curated task-specific datasets without using task-specific labels. Increasing availability of public data repositories has now made it possible to utilize diverse and large, task unrelated datasets to pretrain models in the "wild" using SSL.
View Article and Find Full Text PDFFast and accurate deep learning scans for signatures of natural selection in genomes using FASTER-NN.
Commun Biol
January 2025
University of Twente, Enschede, The Netherlands.
Deep learning classification models based on Convolutional Neural Networks (CNNs) are increasingly used in population genetic inference for detecting signatures of natural selection. Prevailing detection methods treat the design of the classifier as a discrete phase, assuming that high classification accuracy is the sole prerequisite for precise detection. This frequently steers method development toward classification-driven optimizations that can inadvertently impede detection.
View Article and Find Full Text PDFRefreshable memristor via dynamic allocation of ferro-ionic phase for neural reuse.
Nat Commun
January 2025
School of Optoelectronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.
Neural reuse can drive organisms to generalize knowledge across various tasks during learning. However, existing devices mostly focus on architectures rather than network functions, lacking the mimic capabilities of neural reuse. Here, we demonstrate a rational device designed based on ferroionic CuInPS, to accomplish the neural reuse function, enabled by dynamic allocation of the ferro-ionic phase.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!