mlsanityData to 7 Oct 2026

Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification

arXiv 2202.04497 ↗First posted 9 Feb 2022cond-mat.dis-nn cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

A novel strategy to automated classification is introduced which exploits a fully trained dynamical system to steer items belonging to different categories toward distinct asymptotic attractors. These latter are incorporated into the model by taking advantage of the spectral decomposition of the operator that rules the linear evolution across the processing network. Non-linear terms act for a transient and allow to disentangle the data supplied as initial condition to the discrete dynamical system, shaping the boundaries of different attractors. The network can be equipped with several memory kernels which can be sequentially activated for serial datasets handling. Our novel approach to classification, that we here term Recurrent Spectral Network (RSN), is successfully challenged against a simple test-bed model, created for illustrative purposes, as well as a standard dataset for image processing training.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 8 of its 34 references that are in the map. First posted on arXiv 9 Feb 2022.

Builds on

8 of 34 references.

References · 8

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 415
  3. 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 401
  4. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  5. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  6. 2021Next Generation Reservoir Computingcited by 160
  7. 2020Machine learning in spectral domaincited by 20
  8. 2021On the training of sparse and dense deep neural networks: less parameters, same performancecited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1.

4 papers.

  1. 2023How a student becomes a teacher: learning and forgetting through Spectral methodscited by 5
  2. 2023Complex Recurrent Spectral Networkcited by 5
  3. 2024Estimating Global Input Relevance and Enforcing Sparse Representations with a Scalable Spectral Neural Network Approachcited by 4
  4. 2023Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problemscited by 3