Related papers: Hierarchical Trait-State Model for Decoding Dyadic…
Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…
We show that gating mechanisms in recurrent neural networks (RNNs) induce lag-dependent and direction-dependent effective learning rates, even when training uses a fixed, global step size. This behavior arises from a coupling between…
Personality recognition aims to identify the personality traits implied in user data such as dialogues and social media posts. Current research predominantly treats personality recognition as a classification task, failing to reveal the…
The structure and dynamic of social network are largely determined by the heterogeneous interaction activity and social capital allocation of individuals. These features interplay in a non-trivial way in the formation of network and…
Transformer LMs show emergent reasoning that resists mechanistic understanding. We offer a statistical physics framework for continuous-time chain-of-thought reasoning dynamics. We model sentence-level hidden state trajectories as a…
Dynamical models underpin our ability to understand and predict the behavior of natural systems. Whether dynamical models are developed from first-principles derivations or from observational data, they are predicated on our choice of state…
Understanding the formation of social ties requires disentangling the roles of individual traits and local network structure. We analyse signed social relationships among 3,395 students using an interpretable machine learning model -- the…
We conduct a comprehensive investigation into the dynamics of gradient descent using large-order constant step-sizes in the context of quadratic regression models. Within this framework, we reveal that the dynamics can be encapsulated by a…
According to a popular viewpoint, neural networks learn from data by first identifying low-dimensional representations, and subsequently fitting the best model in this space. Recent works provide a formalization of this phenomenon when…
State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation is usually a vector without any explicit structure.…
Identifying preictal states -- periods during which seizures are more likely to occur -- remains a central challenge in clinical computational neuroscience. In this study, we introduce a novel framework that embeds functional brain…
From social networks to Internet applications, a wide variety of electronic communication tools are producing streams of graph data; where the nodes represent users and the edges represent the contacts between them over time. This has led…
Robotic arms are increasingly being used in collaborative environments, requiring an accurate understanding of human intentions to ensure both effectiveness and safety. Electroencephalogram (EEG) signals, which measure brain activity,…
Neural electromagnetic (EM) signals recorded non-invasively from individual human subjects vary in complexity and magnitude. Nonetheless, variation in neural activity has been difficult to quantify and interpret, due to complex, broad-band…
Contagion, a concept from epidemiology, has long been used to characterize social influence on people's behavior and affective (emotional) states. While it has revealed many useful insights, it is not clear whether the contagion metaphor is…
Time-varying covariates in longitudinal studies frequently evolve through reciprocal feedback, undergo role reversal, and reflect unobserved individual heterogeneity. Standard statistical frameworks often assume fixed covariate roles and…
Localized patterns are coherent structures embedded in a quiescent state and occur in both discrete and continuous media across a wide range of applications. While it is well-understood how domain covering patterns (for example stripes and…
The emergence of deep learning networks raises a need for explainable AI so that users and domain experts can be confident applying them to high-risk decisions. In this paper, we leverage data from the latent space induced by deep learning…
We have shortly reviewed the occurrence of the post-synaptic potentials between neurons, the relation between EEG and neuron dynamics, as well as methods of signal analysis. We supposed a simple stochastic model representing electrical…
Micro-expressions are involuntary facial movements that cannot be consciously controlled, conveying subtle cues with substantial real-world applications. The analysis of micro-expressions generally involves two main tasks: spotting…