7 papers
Manifold Navigation Learning Using Recurrent Networks: Efficient Training Techniques
Sarah Harkins Dayton, Sathya Rengaswami, Vasileios Maroulas +2
Position tracking is a well-studied problem in Euclidean navigation, yet comparatively little attention has been given to navigation on general manifolds, where motion is governed…
From Classical to Topological Neural Networks Under Uncertainty
Sarah Harkins Dayton, Layal Bou Hamdan, Ioannis D. Schizas +2
This chapter explores neural networks, topological data analysis, and topological deep learning techniques, alongside statistical Bayesian methods, for processing images, time seri…
Bayesian Topological Convolutional Neural Nets
Sarah Harkins Dayton, Hayden Everett, Ioannis Schizas +2
Convolutional neural networks (CNNs) have been established as the main workhorse in image data processing; nonetheless, they require large amounts of data to train, often produce o…
Complexity synchronization analysis of neurophysiological data: Theory and methods
Ioannis Schizas, Sabrina Sullivan, Scott E. Kerick +6
We apply modified diffusion entropy analysis (MDEA) to assess multifractal dimensions of ON time series (ONTS) and complexity synchronization (CS) analysis to infer information tra…
Bayesian Sheaf Neural Networks
Patrick Gillespie, Layal Bou Hamdan, Ioannis Schizas +2
Equipping graph neural networks with a convolution operation defined in terms of a cellular sheaf offers advantages for learning expressive representations of heterophilic graph da…
Spectral-Stimulus Information for Self-Supervised Stimulus Encoding
Jared Deighton, Wyatt Mackey, Ioannis Schizas +2
Mammalian spatial navigation relies on specialized neurons, such as place and grid cells, which encode position based on self-motion and environmental cues. While extensive researc…
Geometric sparsification in recurrent neural networks
Wyatt Mackey, Ioannis Schizas, Jared Deighton +2
A common technique for ameliorating the computational costs of running large neural models is sparsification, or the pruning of neural connections during training. Sparse models ar…