Convolutional neural networks (CNNs) are powerful machine learning models that have become the state of the art in several problems in the areas of computer vision and image processing. Nevertheless, the knowledge of why and how these models present an impressive performance is still limited. There are visualization techniques that can help us to understand the inner working of neural networks. However, they have mostly been applied to classification models. In this paper, we evaluate the application of visualization methods to networks where the input and output are images of proportional dimensions. The results show that visualization brings visual cues associated with how these systems work, helping in their understanding and improvement. We use the knowledge obtained from the visualization of an image restoration CNN to improve the architecture's efficiency with no significant degradation of its performance.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNNLS.2018.2881194 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Computer-aided diagnosis of hepatic cystic echinococcosis based on deep transfer learning features from ultrasound images.
Sci Rep
January 2025
College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, 830017, China.
Hepatic cystic echinococcosis (HCE), a life-threatening liver disease, has 5 subtypes, i.e., single-cystic, polycystic, internal capsule collapse, solid mass, and calcified subtypes.
View Article and Find Full Text PDFA Faster Privacy-Preserving Medical Image Diagnosis Scheme with Machine Learning.
J Imaging Inform Med
January 2025
College of Computer, Chongqing University, No. 55 Daxuecheng South Rd, Shapingba, 401331, Chongqing, China.
Convolutional neural networks (CNNs) have become indispensable to medical image diagnosis research, enabling the automated differentiation of diseased images from extensive medical image datasets. Due to their efficacy, these methods raise significant privacy concerns regarding patient images and diagnostic models. To address these issues, some researchers have explored privacy-preserving medical image diagnosis schemes using fully homomorphic encryption (FHE).
View Article and Find Full Text PDFThe two sides of Phobos: Gray and white matter abnormalities in phobic individuals.
Cogn Affect Behav Neurosci
January 2025
Departamento de Psicología ClínicaPsicobiología y MetodologíaFacultad de Psicología, Universidad de La Laguna, La Laguna, 38200, Tenerife, Spain.
Small animal phobia (SAP) is a subtype of specific phobia characterized by an intense and irrational fear of small animals, which has been underexplored in the neuroscientific literature. Previous studies often faced limitations, such as small sample sizes, focusing on only one neuroimaging modality, and reliance on univariate analyses, which produced inconsistent findings. This study was designed to overcome these issues by using for the first time advanced multivariate machine-learning techniques to identify the neural mechanisms underlying SAP.
View Article and Find Full Text PDFDifferential gray matter correlates and machine learning prediction of abuse and internalizing psychopathology in adolescent females.
Sci Rep
January 2025
Department of Psychiatry, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA.
Childhood abuse represents one of the most potent risk factors for the development of psychopathology during childhood, accounting for 30-60% of the risk for onset. While previous studies have separately associated reductions in gray matter volume (GMV) with childhood abuse and internalizing psychopathology (IP), it is unclear whether abuse and IP differ in their structural abnormalities, and which GMV features are related to abuse and IP at the individual level. In a pooled multisite, multi-investigator sample, 246 child and adolescent females between the ages of 8-18 were recruited into studies of interpersonal violence (IPV) and/or IP (i.
View Article and Find Full Text PDFExploring transition states of protein conformational changes via out-of-distribution detection in the hyperspherical latent space.
Nat Commun
January 2025
Department of Chemistry, Theoretical Chemistry Institute, University of Wisconsin-Madison, Madison, WI, 53706, USA.
Identifying transitional states is crucial for understanding protein conformational changes that underlie numerous biological processes. Markov state models (MSMs), built from Molecular Dynamics (MD) simulations, capture these dynamics through transitions among metastable conformational states, and have demonstrated success in studying protein conformational changes. However, MSMs face challenges in identifying transition states, as they partition MD conformations into discrete metastable states (or free energy minima), lacking description of transition states located at the free energy barriers.
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!