AIMC Topic: Computer Graphics

Clear Filters Showing 161 to 170 of 233 articles

High Performance Implementation of 3D Convolutional Neural Networks on a GPU.

Computational intelligence and neuroscience
Convolutional neural networks have proven to be highly successful in applications such as image classification, object tracking, and many other tasks based on 2D inputs. Recently, researchers have started to apply convolutional neural networks to vid...

Classifying patient portal messages using Convolutional Neural Networks.

Journal of biomedical informatics
OBJECTIVE: Patients communicate with healthcare providers via secure messaging in patient portals. As patient portal adoption increases, growing messaging volumes may overwhelm providers. Prior research has demonstrated promise in automating classifi...

LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks.

IEEE transactions on visualization and computer graphics
Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential input. Researchers interested in better ...

What Would a Graph Look Like in this Layout? A Machine Learning Approach to Large Graph Visualization.

IEEE transactions on visualization and computer graphics
Using different methods for laying out a graph can lead to very different visual appearances, with which the viewer perceives different information. Selecting a "good" layout method is thus important for visualizing a graph. The selection can be high...

Discriminatively Trained Latent Ordinal Model for Video Classification.

IEEE transactions on pattern analysis and machine intelligence
We address the problem of video classification for facial analysis and human action recognition. We propose a novel weakly supervised learning method that models the video as a sequence of automatically mined, discriminative sub-events (e.g., onset a...

Fuzzy Object Skeletonization: Theory, Algorithms, and Applications.

IEEE transactions on visualization and computer graphics
Skeletonization offers a compact representation of an object while preserving important topological and geometrical features. Literature on skeletonization of binary objects is quite mature. However, challenges involved with skeletonization of fuzzy ...

Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction.

Journal of chemical information and modeling
The task of learning an expressive molecular representation is central to developing quantitative structure-activity and property relationships. Traditional approaches rely on group additivity rules, empirical measurements or parameters, or generatio...

Disease Compass- a navigation system for disease knowledge based on ontology and linked data techniques.

Journal of biomedical semantics
BACKGROUND: Medical ontologies are expected to contribute to the effective use of medical information resources that store considerable amount of data. In this study, we focused on disease ontology because the complicated mechanisms of diseases are r...

Learning from biomedical linked data to suggest valid pharmacogenes.

Journal of biomedical semantics
BACKGROUND: A standard task in pharmacogenomics research is identifying genes that may be involved in drug response variability, i.e., pharmacogenes. Because genomic experiments tended to generate many false positives, computational approaches based ...

Ontogenetic Shifts in Brain Organization in the Bluespotted Stingray Neotrygon kuhlii (Chondrichthyes: Dasyatidae).

Brain, behavior and evolution
Fishes exhibit lifelong neurogenesis and continual brain growth. One consequence of this continual growth is that the nervous system has the potential to respond with enhanced plasticity to changes in ecological conditions that occur during ontogeny....