9 citations · 18 across the 9 of their papers we have counts for
10 papers
Effective Latent Differential Equation Models via Attention and Multiple Shooting
Germán Abrevaya, Mahta Ramezanian-Panahi, Jean-Christophe Gagnon-Audet +5
Scientific Machine Learning (SciML) is a burgeoning field that synergistically combines domain-aware and interpretable models with agnostic machine learning techniques. In this wor…
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
Pascal Jr. Tikeng Notsawo, Hattie Zhou, Mohammad Pezeshki +2
This paper focuses on predicting the occurrence of grokking in neural networks, a phenomenon in which perfect generalization emerges long after signs of overfitting or memorization…
Attention Schema in Neural Agents
Dianbo Liu, Samuele Bolotta, He Zhu +2
Attention has become a common ingredient in deep learning architectures. It adds a dynamical selection of information on top of the static selection of information supported by wei…
Regularity of matrix coefficients of a compact symmetric pair of Lie groups
Guillaume Dumas
We consider symmetric Gelfand pairs where is a compact Lie group and a subgroup of fixed point of an involutive automorphism. We study the regularity of -bi-inva…
Sources of Richness and Ineffability for Phenomenally Conscious States
Xu Ji, Eric Elmoznino, George Deane +5
Conscious states (states that there is something it is like to be in) seem both rich or full of detail, and ineffable or hard to fully describe or recall. The problem of ineffabili…
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
Jean-Christophe Gagnon-Audet, Kartik Ahuja, Mohammad-Javad Darvishi-Bayazi +3
Machine learning models often fail to generalize well under distributional shifts. Understanding and overcoming these failures have led to a research field of Out-of-Distribution (…
Generative Models of Brain Dynamics -- A review
Mahta Ramezanian Panahi, Germán Abrevaya, Jean-Christophe Gagnon-Audet +3
The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-twentieth century. Recent developments in…
Social Neuro AI: Social Interaction as the "dark matter" of AI
Samuele Bolotta, Guillaume Dumas
This article introduces a three-axis framework indicating how AI can be informed by biological examples of social learning mechanisms. We argue that the complex human cognitive arc…
Superpermutation matrices
Guillaume Dumas
Superpermutations are words over a finite alphabet containing every permutation as a factor. Finding the minimal length of a superpermutation is still an open problem. In this arti…
Systems of Global Governance in the Era of Human-Machine Convergence
Eugenio Maria Battaglia, Jie Mei, Guillaume Dumas
Technology is increasingly shaping our social structures and is becoming a driving force in altering human biology. Besides, human activities already proved to have a significant i…