6 papers
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…
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…
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…
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…
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…