11 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…
Complexity synchronization as a diagnostic and control principle for adaptive systems
Korosh Mahmoodi, Scott E. Kerick, Piotr J. Franaszczuk +3
Adaptive systems can exhibit similar levels of performance while relying on fundamentally different internal modes of coordination. Standard metrics such as average cooperation or…
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…
EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deployment
Mikolaj Walczak, Romina Aalishah, Wyatt Mackey +5
Deep reinforcement learning agents are often fragile while humans remain adaptive and flexible to varying scenarios. To bridge this gap, we present EDEN, a biologically inspired na…
MapperEEG: A Topological Approach to Brain State Clustering in EEG Recordings
Brittany Story, Zhibin Zhou, Ramesh Srinivasan +3
Background: Topological data analysis (TDA) has exploded as a tool for analyzing and making sense of high dimensional datasets across a variety of fields. Mapper is a tool from TDA…
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…
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…
A Topological Deep Learning Framework for Neural Spike Decoding
Edward C. Mitchell, Brittany Story, David Boothe +2
The brain's spatial orientation system uses different neuron ensembles to aid in environment-based navigation. Two of the ways brains encode spatial information is through head dir…
Bayesian Topological Learning for Brain State Classification
Farzana Nasrin, Christopher Oballe, David L. Boothe +1
Investigation of human brain states through electroencephalograph (EEG) signals is a crucial step in human-machine communications. However, classifying and analyzing EEG signals ar…