The universal approximation theorem states that a neural network with one hidden layer can approximate continuous functions on compact sets with any desired precision. This theorem supports using neural networks for various applications, including regression and classification tasks. Furthermore, it is valid for real-valued neural networks and some hypercomplex-valued neural networks such as complex-, quaternion-, tessarine-, and Clifford-valued neural networks. However, hypercomplex-valued neural networks are a type of vector-valued neural network defined on an algebra with additional algebraic or geometric properties. This paper extends the universal approximation theorem for a wide range of vector-valued neural networks, including hypercomplex-valued models as particular instances. Precisely, we introduce the concept of non-degenerate algebra and state the universal approximation theorem for neural networks defined on such algebras.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2024.106632 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Development and external validation of a machine learning model for brain injury in pediatric patients on extracorporeal membrane oxygenation.
Crit Care
January 2025
Department of Pediatric, West China Second University Hospital, Sichuan University, Chengdu, China.
Background: Patients supported by extracorporeal membrane oxygenation (ECMO) are at a high risk of brain injury, contributing to significant morbidity and mortality. This study aimed to employ machine learning (ML) techniques to predict brain injury in pediatric patients ECMO and identify key variables for future research.
Methods: Data from pediatric patients undergoing ECMO were collected from the Chinese Society of Extracorporeal Life Support (CSECLS) registry database and local hospitals.
A robust multimodal brain MRI-based diagnostic model for migraine: validation across different migraine phases and longitudinal follow-up data.
J Headache Pain
January 2025
Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea.
Inter-individual variability in symptoms and the dynamic nature of brain pathophysiology present significant challenges in constructing a robust diagnostic model for migraine. In this study, we aimed to integrate different types of magnetic resonance imaging (MRI), providing structural and functional information, and develop a robust machine learning model that classifies migraine patients from healthy controls by testing multiple combinations of hyperparameters to ensure stability across different migraine phases and longitudinally repeated data. Specifically, we constructed a diagnostic model to classify patients with episodic migraine from healthy controls, and validated its performance across ictal and interictal phases, as well as in a longitudinal setting.
View Article and Find Full Text PDFResistive memory-based zero-shot liquid state machine for multimodal event data learning.
Nat Comput Sci
January 2025
Key Lab of Fabrication Technologies for Integrated Circuits and Key Laboratory of Microelectronic Devices and Integrated Technology, Institute of Microelectronics of the Chinese Academy of Sciences, Beijing, China.
The human brain is a complex spiking neural network (SNN) capable of learning multimodal signals in a zero-shot manner by generalizing existing knowledge. Remarkably, it maintains minimal power consumption through event-based signal propagation. However, replicating the human brain in neuromorphic hardware presents both hardware and software challenges.
View Article and Find Full Text PDFHypothalamic atrophy in primary lateral sclerosis, assessed by convolutional neural network-based automatic segmentation.
Sci Rep
January 2025
Dept. of Neurology, University of Ulm, Oberer Eselsberg 45, 89081, Ulm, Germany.
Primary lateral sclerosis (PLS) is a motor neuron disease (MND) which mainly affects upper motor neurons. Within the MND spectrum, PLS is much more slowly progressive than amyotrophic laterals sclerosis (ALS). `Classical` ALS is characterized by catabolism and abnormal energy metabolism preceding onset of motor symptoms, and previous studies indicated that the disease progression of ALS involves hypothalamic atrophy.
View Article and Find Full Text PDFAltered Static and Dynamic Functional Network Connectivity and Combined Machine Learning in Stroke.
Brain Topogr
January 2025
Department of Radiology, Jiangxi Provincial People's Hospital, The First Affiliated Hospital of Nanchang Medical College, No 152, Ai Guo Road, Dong Hu District, Nanchang, Jiangxi, 330006, China.
Stroke is a condition characterized by damage to the cerebral vasculature from various causes, resulting in focal or widespread brain tissue damage. Prior neuroimaging research has demonstrated that individuals with stroke present structural and functional brain abnormalities, evident through disruptions in motor, cognitive, and other vital functions. Nevertheless, there is a lack of studies on alterations in static and dynamic functional network connectivity in the brains of stroke patients.
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!