Search
Search Results
-
Improve Adversarial Robustness of MNIST Classification via Topological Data Analysis
Current defense methods for machine learning classification tasks against adversarial samples mostly focus on the propagation process of networks... -
An Algorithm for Constructing a Topological Skeleton for Semi-structured Spatial Data Based on Persistent Homology
The construction and use of a topological skeleton for processing semi-structured information based on persistent homology methods is considered in... -
A Study of Neural Collapse for Text Classification
In this study, we explore the phenomenon of neural collapse (NC) in text classification using convolutional neural networks (CNNs) applied to the AG... -
Overfitting measurement of convolutional neural networks using trained network weights
Overfitting reduces the generalizability of convolutional neural networks (CNNs). Overfitting is generally detected by comparing the accuracies and...
-
Machine reading comprehension model based on query reconstruction technology and deep learning
Machine reading comprehension is introduced to improve machines’ readability and understandability of human languages. This sophisticated version of...
-
Persistent 1-Cycles: Definition, Computation, and Its Application
Persistence diagrams, which summarize the birth and death of homological features extracted from data, are employed as stable signatures for... -
Towards Emotion Recognition: A Persistent Entropy Application
Emotion recognition and classification is a very active area of research. In this paper, we present a first approach to emotion classification using... -
Characterising Epithelial Tissues Using Persistent Entropy
In this paper, we apply persistent entropy, a novel topological statistic, for characterization of images of epithelial tissues. We have found out... -
Persistent Homology Computation Using Combinatorial Map Simplification
We propose an algorithm for persistence homology computation of orientable 2-dimensional (2D) manifolds with or without boundary (meshes) represented... -
Extractive Text Summarization Using Topological Features
The amount of text data generated these days is increasing exponentially, and it is becoming a very tedious process to extract meaningful information... -
Importance attribution in neural networks by means of persistence landscapes of time series
This article describes a method to analyze time series with a neural network using a matrix of area-normalized persistence landscapes obtained with...
-
Detecting Stress from Multivariate Time Series Data Using Topological Data Analysis
Stress can have dangerous effects to human mental and physical health. Statistics, machine learning and novel data analytics approaches have been... -
Topological Learning and Its Application to Multimodal Brain Network Integration
A long-standing challenge in multimodal brain network analyses is to integrate topologically different brain networks obtained from diffusion and... -
TDA-Clustering Strategies for the Characterization of Brain Organoids
We propose to use Topological Data Analysis (TDA) to characterize the morphological development of brain organoids. We combine TDA with clustering... -
Explicit Topological Priors for Deep-Learning Based Image Segmentation Using Persistent Homology
We present a novel method to explicitly incorporate topological prior knowledge into deep learning based segmentation, which is, to our knowledge,... -
Learning Topology: Bridging Computational Topology and Machine Learning
AbstractTopology is a classical branch of mathematics, born essentially from Euler’s studies in the XVII century, which deals with the abstract...
-
Tracing patterns and shapes in remittance and migration networks via persistent homology
Pattern detection in network models provides insights to both global structure and local node interactions. In particular, studying patterns embedded...
-
The Characterization of Rainfall Data Set Using Persistence Diagram and Its Relation to Extreme Events: Case Study of Three Locations in Kemaman, Terengganu
Floods are recurring phenomena at certain locations because of excessive rainfall, resulting in the overflow of lakes, drains, and rivers. In this... -
An Extension of DNAContainer with a Small Memory Footprint
Over the past decade, DNA has emerged as a new storage medium with intriguing data volume and durability capabilities. Despite its advantages, DNA...
-
On Topological Analysis of Cells Organization in Biological Images
There are many problems inside the field of biomedical image analysis that can be dealt from a topological (and geometric) point of view. One of them...