Homological Neural Networks: A Sparse Architecture for Multivariate Complexity
The rapid progress of Artificial Intelligence research came with the development of increasingly complex deep learning models, leading to growing challenges in terms of computational complexity, energy efficiency and interpretability. In this study, we apply advanced network-based information filtering techniques to design a novel deep neural network unit characterized by a sparse higher-order graphical architecture built over the homological structure of underlying data. We demonstrate its effectiveness in two application domains which are traditionally challenging for deep learning: tabular data and time series regression problems. Results demonstrate the advantages of this novel design which can tie or overcome the results of state-of-the-art machine learning and deep learning models using only a fraction of parameters.
Code (1)
Tasks
Deep LearningTime SeriesTime Series RegressionSimilar Papers 제목 키워드 기반
Persistent Homology in Sparse Regression and Its Application to Brain Morphometry
Sparse systems are usually parameterized by a tuning parameter that determines the sparsity of the system. How to choose the right tuning parameter is a fundamental and difficult problem in learning the sparse system. In…
Brain MorphometryregressionA Homological Theory of Functions
In computational complexity, a complexity class is given by a set of problems or functions, and a basic challenge is to show separations of complexity classes $A \not= B$ especially when $A$ is known to be a subset of $B…
LEMMAPersistent Topological Structures and Cohomological Flows as a Mathematical Framework for Brain-Inspired Representation Learning
This paper presents a mathematically rigorous framework for brain-inspired representation learning founded on the interplay between persistent topological structures and cohomological flows. Neural computation is reformu…
Representation LearningTime topological analysis of EEG using signature theory
Anomaly detection in multivariate signals is a task of paramount importance in many disciplines (epidemiology, finance, cognitive sciences and neurosciences, oncology, etc.). In this perspective, Topological Data Analysi…
Anomaly DetectionEEGEpidemiologyTopological Data AnalysisHomological Convolutional Neural Networks
Deep learning methods have demonstrated outstanding performances on classification and regression tasks on homogeneous data types (e.g., image, audio, and text data). However, tabular data still pose a challenge, with cl…
Deep Learning