Neural Advances in Processing Nonlinear Dynamic Signals 2020

5 papers
The 2020 edition of Neural Advances in Processing Nonlinear Dynamic Signals featured nine papers centered on hierarchical temporal integration within deep recurrent networks. A primary research direction involved hierarchical temporal representations in linear reservoir computing, alongside the development of low-complexity nonlinear filters for addressing distorted speech signals. Mathematical frameworks were also a focus, specifically the application of 4-dimensional hypercomplex algebras in adaptive signal processing and the implementation of cubic spline interpolation for learning activation functions from data. Practical applications featured in this year’s research included the separation of drum and bass components from monaural audio tracks. Notable contributors to the volume included Aurelio Uncini, Danilo Comminiello, Michele Scarpiniti, and Claudio Gallicchio. The collective work reflects a trend toward combining deep recurrent architectures with specialized algebraic methods to enhance nonlinear signal processing. This edition emphasized both theoretical advancements in temporal modeling and efficient algorithmic solutions for complex audio and adaptive signal tasks.

Top Research Directions

The 5 research directions with Neural Advances in Processing Nonlinear Dynamic Signals 2020 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Hierarchical Temporal Scaling in Neural Networks120.0%
2Modeling Temporal Dependencies with Recurrent Neural Networks120.0%
3Overcoming Initialization Sensitivity in Gradient Descent120.0%
4Shifting Activation Functions from Nodes to Edges120.0%
5Spectral Band Decomposition of Neural Signals120.0%

Download all directions as CSV

Institutions

Institutions credited by Neural Advances in Processing Nonlinear Dynamic Signals 2020 papers: a paper credits every institution named in its affiliations, once. 2 institutions share 2 credited papers.

#InstitutionPapersShare20172017 rank
1Sapienza University of Rome 150.0%0—
2University of Pisa 150.0%11

Download all institutions as CSV

About this data

Papers. Neural Advances in Processing Nonlinear Dynamic Signals 2020 lists 5 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 2 of 5 papers (40.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Neural Advances in Processing Nonlinear Dynamic Signals 2020”, https://lacuna.tiptreesystems.com/venue/neural-advances-in-processing-nonlinear-dynamic-signals/2020.

Top Authors

AuthorPapers
Danilo Comminiello4
Aurelio Uncini3
Simone Scardapane3
Alessio Micheli1
Claudio Gallicchio1

Papers

Title
A Low-Complexity Linear-in-the-Parameters Nonlinear Filter for Distorted Speech Signals
Hierarchical Temporal Representation in Linear Reservoir Computing
Learning Activation Functions from Data Using Cubic Spline Interpolation
On 4-Dimensional Hypercomplex Algebras in Adaptive Signal Processing
Separation of Drum and Bass from Monaural Tracks