arXiv research

Fine-grained atlases improve fMRI analysis of brain activity.

Wider networks learn more interpretable features and improve performance during fine-tuning.

Good atlases are defined for effective orbifolds, and a spark complex is constructed on each good atlas. It is proved that this process is 2-functorial with compatible systems playing as morphisms between good atlases, and that the spark character 2-functor factors through this 2-functor.

Probabilistic atlases provide essential spatial contextual information for image interpretation, Bayesian modeling, and algorithmic processing. Such atlases are typically constructed by grouping subjects with similar demographic information. Importantly, use of the same scanner minimizes inter-group variability. Howeve…

We give a definition of atlases for ineffective orbifolds, and prove that this definition leads to the same notion of orbifold as that defined via topological groupoids.

Starting with some motivating examples (classical atlases for a manifold, space of leaves of a foliation, group orbits), we propose to view a Lie groupoid as a generalized atlas for the "virtual structure" of its orbit space, the equivalence between atlases being here the smooth Morita equivalence. This "structure" kee…

We present two related methods for deriving connectivity-based brain atlases from individual connectomes. The proposed methods exploit a previously proposed dense connectivity representation, termed continuous connectivity, by first performing graph-based hierarchical clustering of individual brains, and subsequently a…

We study the number of Darboux charts needed to cover a closed connected symplectic manifold $(M,ω)$, and effectively estimate this number from below and from above in terms of the Lusternik--Schnirelmann category of $M$ and the Gromov width of $(M,ω)$.

We construct an infinite sequence of projectively flat manifolds by using castling transformations of prehomogeneous vector spaces. We also give a classification of manifolds equipped with a flat projective structure obtained by a finite number of castling transformations, and describe these flat projective structures …

The Jacobian conjecture is simplified using polynomial mappings.

Given the notion of suborbifold of the second author (based on ideas of Borzellino/Brunsden) and the classical correspondence (up to certain equivalences) between (effective) orbifolds via atlases and effective orbifold groupoids, we analyze which groupoid embeddings correspond to suborbifolds and give classes of subor…

In this paper, the task-related fMRI problem is treated in its matrix factorization formulation, focused on the Dictionary Learning (DL) approach. The new method allows the incorporation of a priori knowledge associated both with the experimental design as well as with available brain Atlases. Moreover, the proposed me…

New method uses entropy to generate multiple plausible causal maps.

Toric quasifolds extend toric geometry to non-rational polytopes.

We describe a bicategory $(\mathcal{R}ed\,\mathcal{O}rb)$ of reduced orbifolds in the framework of classical differential geometry (i.e. without any explicit reference to notions of Lie groupoids or differentiable stacks, but only using orbifold atlases, local lifts and changes of charts). In order to construct such a …

New bridge between diffeology and noncommutative geometry.

Accumulation of standardized data collections is opening up novel opportunities for holistic characterization of genome function. The limited scalability of current preprocessing techniques has, however, formed a bottleneck for full utilization of contemporary microarray collections. While short oligonucleotide arrays …

In this paper we compute the minimal number of Darboux chart needed to cover a Hermitian symmetric space of compact type in terms of the degree of their embeddings in $\mathbb{C} P^N$. The proof is based on the recent work of Y. B. Rudyak and F. Schlenk [18] and on the symplectic geometry tool developed by the first au…

DET unifies geometric and functional alignment for high-dimensional scientific data.

We study the minimal number C(M,ξ) of contact charts that one needs to cover a closed connected contact manifold (M,ξ). Our basic result is C(M,ξ) \le \dim M + 1. We compute C(M,ξ) for all closed connected contact 3-manifolds: C (M,ξ) = 2 if M = S^3 and ξis tight, 3 if M = S^3 and ξis overtwisted or if M = #_k (S^2 \ti…

We analyze the possibility of defining infinite-dimensional manifolds as ringed spaces. More precisely, we consider three definitions of manifolds modeled on locally convex spaces: in terms of charts and atlases, in terms of ringed spaces, and in terms of functored spaces, as introduced by Douady in his thesis. It is s…

The first, second and fourth Painlevé equations are studied by means of dynamical systems theory and three dimensional weighted projective spaces $\C P^3(p,q,r,s)$ with suitable weights $(p,q,r,s)$ determined by the Newton diagrams of the equations or the versal deformations of vector fields. Singular normal forms of t…

We propose a segmentation framework that uses deep neural networks and introduce two innovations. First, we describe a biophysics-based domain adaptation method. Second, we propose an automatic method to segment white and gray matter, and cerebrospinal fluid, in addition to tumorous tissue. Regarding our first innovati…

The specificty and sensitivity of resting state functional MRI (rs-fMRI) measurements depend on pre-processing choices, such as the parcellation scheme used to define regions of interest (ROIs). In this study, we critically evaluate the effect of brain parcellations on machine learning models applied to rs-fMRI data. O…

We study the family $Ω^1(-1^s)$ of rational 1--forms on the Riemann sphere, having exactly $-s \leq -2$ simple poles. Three equivalent $(2s-1)$--dimensional complex atlases on $Ω^1(-1^s)$, using coefficients, zeros--poles and residues--poles of the 1--forms, are recognized. A rational 1--form is isochronous when all th…

The paper develops a theory of Ehresmann structures in positive characteristic.

Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain ne…

Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an "activation ensemble" because it allows the use of multiple activation functio…

This paper studies activation sparsity in large language models, finding key trends and implications.

Activity recognition from sensor data deals with various challenges, such as overlapping activities, activity labeling, and activity detection. Although each challenge in the field of recognition has great importance, the most important one refers to online activity recognition. The present study tries to use online hi…

Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds the promise to reveal functional biomarkers of neuropsychiatric disorders. However, extracting such biomarkers is challenging for complex multi-faceted neuropatholo-gies, such as autism spectrum disorders. Large multi-site datasets increase sample sizes…

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the activation, and the weights capture the scale. Here we propose to train the netw…

BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.

Evolutionary algorithms improve neural network performance by discovering better activation functions.

Active learning method balances bias and variance under class imbalance.

New method learns neural network activation functions from data.

Study active learning of PTFs with derivative access.

Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples giv…

Bayesian adaptive designs can be biased by active learning, especially with misspecified models.

Derives time-averaged active inference from control principles.

RAN model recognizes multiple activities from unlabeled sensor data.

A new indicator measures project risk from activity durations.

Hidden Markov Models detect hand gestures from wearable sEMG signals.

Active testing reduces label costs for efficient model evaluation.

Survey of trainable activation functions in neural networks.

This paper analyzes and improves active learning techniques for real-world projects.

Study active nematic forces on curved surfaces, revealing new coupling mechanisms.

This paper provides an overview of activation functions in neural networks.