Search Results for author:
Found 13 papers, 6 papers with code
Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
On the other hand, mathematical analysis of dynamical systems inferred from data is often more convenient and enables additional insights if these are formulated in continuous time, i. e. as systems of ordinary (or partial) differential equations (ODE).
Multimodal Teacher Forcing for Reconstructing Nonlinear Dynamical Systems
The forcing signal for the RNN is generated by the MVAE which integrates different types of simultaneously given time series data into a joint latent code optimal for DS reconstruction.
Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems
In many scientific disciplines, we are interested in inferring the nonlinear dynamical system underlying a set of observed time series, a challenging task in the face of chaotic behavior and noise.
Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series
Here we propose a general framework for multi-modal data integration for the purpose of nonlinear DS reconstruction and the analysis of cross-modal relations.
On the difficulty of learning chaotic dynamics with RNNs
Here we offer a comprehensive theoretical treatment of this problem by relating the loss gradients during RNN training to the Lyapunov spectrum of RNN-generated orbits.
Tractable Dendritic RNNs for Identifying Unknown Nonlinear Dynamical Systems
In many scientific disciplines, we are interested in inferring the nonlinear dynamical system underlying a set of observed time series, a challenging task in the face of chaotic behavior and noise.
Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies
A main theoretical interest in biology and physics is to identify the nonlinear dynamical system (DS) that generated observed time series.
Inferring Dynamical Systems with Long-Range Dependencies through Line Attractor Regularization
Vanilla RNN with ReLU activation have a simple structure that is amenable to systematic dynamical systems analysis and interpretation, but they suffer from the exploding vs. vanishing gradients problem.
Identifying nonlinear dynamical systems via generative recurrent neural networks with applications to fMRI
A major tenet in theoretical neuroscience is that cognitive and behavioral processes are ultimately implemented in terms of the neural system dynamics.
LeMoNADe: Learned Motif and Neuronal Assembly Detection in calcium imaging videos
Neuronal assemblies, loosely defined as subsets of neurons with reoccurring spatio-temporally coordinated activation patterns, or "motifs", are thought to be building blocks of neural representations and information processing.
Sparse convolutional coding for neuronal assembly detection
Cell assemblies, originally proposed by Donald Hebb (1949), are subsets of neurons firing in a temporally coordinated way that gives rise to repeated motifs supposed to underly neural representations and information processing.
A State Space Approach for Piecewise-Linear Recurrent Neural Networks for Reconstructing Nonlinear Dynamics from Neural Measurements
In summary, the present work advances a semi-analytical (thus reasonably fast) maximum-likelihood estimation framework for PLRNNs that may enable to recover the relevant dynamics underlying observed neuronal time series, and directly link them to computational properties.
Cell assemblies at multiple time scales with arbitrary lag constellations
Hebb's idea of a cell assembly as the fundamental unit of neural information processing has dominated neuroscience like no other theoretical concept within the past 60 years.
