[HTML][HTML] Cardiovascular disease/stroke risk stratification in deep learning framework: a review
The global mortality rate is known to be the highest due to cardiovascular disease (CVD).
Thus, preventive, and early CVD risk identification in a non-invasive manner is vital as …
Thus, preventive, and early CVD risk identification in a non-invasive manner is vital as …
Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey
This survey provides a comprehensive exploration of applications of Topological Data
Analysis (TDA) within neural network analysis. Using TDA tools such as persistent homology …
Analysis (TDA) within neural network analysis. Using TDA tools such as persistent homology …
UNet deep learning architecture for segmentation of vascular and non-vascular images: a microscopic look at UNet components buffered with pruning, explainable …
Biomedical image segmentation (BIS) task is challenging due to the variations in organ
types, position, shape, size, scale, orientation, and image contrast. Conventional methods …
types, position, shape, size, scale, orientation, and image contrast. Conventional methods …
Overfitting measurement of deep neural networks using no data
S Watanabe, H Yamana - 2021 IEEE 8th international …, 2021 - ieeexplore.ieee.org
Overfitting reduces the generalizability of deep neural networks (DNNs). Overfitting is
generally detected by comparing the accuracies and losses of training and validation data; …
generally detected by comparing the accuracies and losses of training and validation data; …
Overfitting measurement of convolutional neural networks using trained network weights
S Watanabe, H Yamana - International Journal of Data Science and …, 2022 - Springer
Overfitting reduces the generalizability of convolutional neural networks (CNNs). Overfitting
is generally detected by comparing the accuracies and losses of the training and validation …
is generally detected by comparing the accuracies and losses of the training and validation …
Pruning techniques for artificial intelligence networks: a deeper look at their engineering design and bias: the first review of its kind
Abstract Trained Artificial Intelligence (AI) models are challenging to install on edge devices
as they are low in memory and computational power. Pruned AI (PAI) models are therefore …
as they are low in memory and computational power. Pruned AI (PAI) models are therefore …
A comprehensive review of deep neural network interpretation using topological data analysis
B Zhang, Z He, H Lin - Neurocomputing, 2024 - Elsevier
Deep neural networks have achieved significant success across various fields, but their
intrinsic black-box nature hinders the further development. Addressing the interpretability …
intrinsic black-box nature hinders the further development. Addressing the interpretability …
Persistent homology captures the generalization of neural networks without a validation set
A Gutiérrez-Fandiño, DP Fernández… - 2021 - openreview.net
The training of neural networks is usually monitored with a validation (holdout) set to
estimate the generalization of the model. This is done instead of measuring intrinsic …
estimate the generalization of the model. This is done instead of measuring intrinsic …
Characterization of topological structures in different neural network architectures
P Świder - arXiv preprint arXiv:2407.06286, 2024 - arxiv.org
One of the most crucial tasks in the future will be to understand what is going on in neural
networks, as they will become even more powerful and widely deployed. This work aims to …
networks, as they will become even more powerful and widely deployed. This work aims to …
Characterizing Protein Conformational Spaces using Efficient Data Reduction and Algebraic Topology
Datasets representing the conformational landscapes of protein structures are high-
dimensional and hence present computational challenges. Efficient and effective …
dimensional and hence present computational challenges. Efficient and effective …