
Which Shortcut Cues Will DNNs Choose? A Study from the ParameterSpace Perspective
Deep neural networks (DNNs) often rely on easytolearn discriminatory f...
read it

ContinuousDepth Neural Models for Dynamic Graph Prediction
We introduce the framework of continuousdepth graph neural networks (GN...
read it

Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
Effective control and prediction of dynamical systems often require appr...
read it

Differentiable Multiple Shooting Layers
We detail a novel class of implicit neural models. Leveraging timeparal...
read it

Learning Stochastic Optimal Policies via Gradient Descent
We systematically develop a learningbased treatment of stochastic optim...
read it

Optimal Energy Shaping via Neural Approximators
We introduce optimal energy shaping as an enhancement of classical passi...
read it

Neural Ordinary Differential Equations for Intervention Modeling
By interpreting the forward dynamics of the latent representation of neu...
read it

TorchDyn: A Neural Differential Equations Library
Continuousdepth learning has recently emerged as a novel perspective on...
read it

Hypersolvers: Toward Fast ContinuousDepth Models
The infinitedepth paradigm pioneered by Neural ODEs has launched a rena...
read it

Stable Neural Flows
We introduce a provably stable variant of neural ordinary differential e...
read it

Dissecting Neural ODEs
Continuous deep learning architectures have recently reemerged as varia...
read it

Graph Neural Ordinary Differential Equations
We extend the framework of graph neural networks (GNN) to continuous tim...
read it

WATTNet: Learning to Trade FX via Hierarchical SpatioTemporal Representation of Highly Multivariate Time Series
Finance is a particularly challenging application area for deep learning...
read it

PortHamiltonian Approach to Neural Network Training
Neural networks are discrete entities: subdivided into discrete layers a...
read it
Michael Poli
is this you? claim profile