We present a comparative theoretical analysis of representation in artificial neural networks with two extreme architectures, a shallow wide network and a deep narrow network, devised to maximally decouple their representative power due to layer width and network depth. We show that, given a specific activation function, models with comparable VC-dimension are required to guarantee zero error modeling of real functions over a binary input. However, functions that exhibit repeating patterns can be encoded much more efficiently in the deep representation, resulting in significant reduction in complexity. This paper provides some initial theoretical evidence of when and how depth can be extremely effective.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2013.2296046 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
hERGAT: predicting hERG blockers using graph attention mechanism through atom- and molecule-level interaction analyses.
J Cheminform
January 2025
Department of Intelligent Electronics and Computer Engineering, Chonnam National University, Gwangju, Republic of Korea.
The human ether-a-go-go-related gene (hERG) channel plays a critical role in the electrical activity of the heart, and its blockers can cause serious cardiotoxic effects. Thus, screening for hERG channel blockers is a crucial step in the drug development process. Many in silico models have been developed to predict hERG blockers, which can efficiently save time and resources.
View Article and Find Full Text PDFImpacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance.
BMC Oral Health
January 2025
Bangkok Hospital Dental Center Holistic Care and Dental Implant, Bangkok Hospital, Bangkok, 10310, Thailand.
Background: Assessing the difficulty of impacted lower third molar (ILTM) surgical extraction is crucial for predicting postoperative complications and estimating procedure duration. The aim of this study was to evaluate the effectiveness of a convolutional neural network (CNN) in determining the angulation, position, classification and difficulty index (DI) of ILTM. Additionally, we compared these parameters and the time required for interpretation among deep learning (DL) models, sixth-year dental students (DSs), and general dental practitioners (GPs) with and without CNN assistance.
View Article and Find Full Text PDFArtificial intelligence methods applied to longitudinal data from electronic health records for prediction of cancer: a scoping review.
BMC Med Res Methodol
January 2025
Leeds Institute of Clinical Trials Research, University of Leeds, Clarendon Way, Leeds, LS2 9NL, UK.
Background: Early detection and diagnosis of cancer are vital to improving outcomes for patients. Artificial intelligence (AI) models have shown promise in the early detection and diagnosis of cancer, but there is limited evidence on methods that fully exploit the longitudinal data stored within electronic health records (EHRs). This review aims to summarise methods currently utilised for prediction of cancer from longitudinal data and provides recommendations on how such models should be developed.
View Article and Find Full Text PDFMHNet: Multi-view High-Order Network for Diagnosing Neurodevelopmental Disorders Using Resting-State fMRI.
J Imaging Inform Med
January 2025
Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong Special Administrative Region, China.
Deep learning models have shown promise in diagnosing neurodevelopmental disorders (NDD) like ASD and ADHD. However, many models either use graph neural networks (GNN) to construct single-level brain functional networks (BFNs) or employ spatial convolution filtering for local information extraction from rs-fMRI data, often neglecting high-order features crucial for NDD classification. We introduce a Multi-view High-order Network (MHNet) to capture hierarchical and high-order features from multi-view BFNs derived from rs-fMRI data for NDD prediction.
View Article and Find Full Text PDFLeveraging synthetic data to improve regional sea level predictions.
Sci Rep
January 2025
Department of Applied Mathematics and Statistics, State University of New York at Stony Brook, Stony Brook, NY, 11794, USA.
The rapid increase in sea levels driven by climate change presents serious risks to coastal communities around the globe. Traditional prediction models frequently concentrate on developed regions with extensive tide gauge networks, leaving a significant gap in data and forecasts for developing countries where the tide gauges are sparse. This study presents a novel deep learning approach that combines TimesGAN with ConvLSTM to enhance regional sea level predictions using the more widely available satellite altimetry data.
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!