Related papers: Beyond Activation Alignment: The Geometry of Neura…
The ventral, dorsal, and lateral streams in high-level human visual cortex are implicated in distinct functional processes. Yet, deep neural networks (DNNs) trained on a single task model the entire visual system surprisingly well, hinting…
A novel LEarning-based Spectrum Sensing and Access (LESSA) framework is proposed, wherein a cognitive radio (CR) learns a time-frequency correlation model underlying spectrum occupancy of licensed users (LUs) in a radio ecosystem;…
Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordings such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which…
Deep neural networks have achieved great success in many real-world applications, yet it remains unclear and difficult to explain their decision-making process to an end-user. In this paper, we address the explainable AI problem for deep…
We introduce Net2Brain, a graphical and command-line user interface toolbox for comparing the representational spaces of artificial deep neural networks (DNNs) and human brain recordings. While different toolboxes facilitate only single…
Visual explanation maps enhance the trustworthiness of decisions made by deep learning models and offer valuable guidance for developing new algorithms in image recognition tasks. Class activation maps (CAM) and their variants (e.g.,…
A method of data assimilation (DA) is employed to estimate electrophysiological parameters of neurons simultaneously with their synaptic connectivity in a small model biological network. The DA procedure is cast as an optimization, with a…
This paper presents a streamlined image analysis framework for correlating behavioral measures to anatomical measures on the cortex and detecting the regions of abnormal brain-behavior correlates. We correlated a facial emotion…
We propose a novel optimization framework to predict clinical severity from resting state fMRI (rs-fMRI) data. Our model consists of two coupled terms. The first term decomposes the correlation matrices into a sparse set of representative…
Understanding how the brain encodes stimuli has been a fundamental problem in computational neuroscience. Insights into this problem have led to the design and development of artificial neural networks that learn representations by…
Cortical pyramidal neurons receive inputs from multiple distinct neural populations and integrate these inputs in separate dendritic compartments. We explore the possibility that cortical microcircuits implement Canonical Correlation…
What can representational similarity matrices (RSMs) tell us about a neural code? As the popularity of these summary statistics grows, so too does the need for a more complete characterization of their properties. Here, we show that…
The rapid adoption of transformer-based models in computational pathology has enabled prediction of molecular and clinical biomarkers from H&E whole-slide images, yet interpretability has not kept pace with model complexity. While…
We consider active learning for binary classification in the agnostic pool-based setting. The vast majority of works in active learning in the agnostic setting are inspired by the CAL algorithm where each query is uniformly sampled from the…
Canonical Correlation Analysis (CCA) is a linear representation learning method that seeks maximally correlated variables in multi-view data. Non-linear CCA extends this notion to a broader family of transformations, which are more powerful…
A major challenge in neuroimaging is understanding the mapping of neurophysiological dynamics onto cognitive functions. Traditionally, these maps have been constructed by examining changes in the activity magnitude of regions related to…
We study spectral algorithms in the setting where kernels are learned from data. We introduce the effective span dimension (ESD), an alignment-sensitive complexity measure that depends jointly on the signal, spectrum, and noise level…
Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions…
Neural operators have emerged as data-driven surrogates for solving partial differential equations (PDEs), and their success hinges on efficiently modeling the long-range, global coupling among spatial points induced by the underlying…
Analyzing the similarity of internal representations has been an important technique for understanding the behavior of deep neural networks. Most existing methods for analyzing the similarity between representations of high dimensions, such…