# Analyzing the Dynamics of WSBM-based Echo State Networks using InputDSA

arXiv: https://arxiv.org/abs/2610.15380 · HTML: https://mlsanity.com/paper/2610.15380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 11 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Learning Latent Block Structure in Weighted Networks](https://mlsanity.com/paper/1404.0431/) (2014)
- [Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis](https://mlsanity.com/paper/2306.10168/) (2023)
- [Adapting the Stochastic Block Model to Edge-Weighted Networks](https://mlsanity.com/paper/1305.5782/) (2013)
- [InputDSA: Demixing then Comparing Recurrent and Externally Driven Dynamics](https://mlsanity.com/paper/2510.25943/) (2025)
- [Generative Models for Network Neuroscience: Prospects and Promise](https://mlsanity.com/paper/1708.07958/) (2017)
- [Diversity of meso-scale architecture in human and non-human connectomes](https://mlsanity.com/paper/1702.02807/) (2017)
- [Evolving Reservoirs for Meta Reinforcement Learning](https://mlsanity.com/paper/2312.06695/) (2023)
- [Combined topological and spatial constraints are required to capture the structure of neural connectomes](https://mlsanity.com/paper/2405.06110/) (2024)
- [Evolutionary Optimization Reveals Structural Constraints on Reservoir Architecture for Spatiotemporal Chaos](https://mlsanity.com/paper/2606.22765/) (2026)

## Abstract (arXiv)

Bridging the structural gap between biological brains and artificial neural networks presents a pathway to altered computational dynamics. This paper introduces a Reservoir Computing framework that replaces random networks with biologically realistic modularity by applying the Weighted Stochastic Block Model (WSBM) to Echo State Networks (ESNs). This topological parameterization constructs reservoirs reflecting latent functional sub-circuits. Furthermore, the integration of Input Dynamical Similarity Analysis (InputDSA) provides a mechanism to isolate and compare how structural priors modulate intrinsic recurrent dynamics versus external inputs. By evaluating these architectures, we establish that structural diversity does not necessarily predicts behavioral diversity across the selected network subset. Furthermore, our demixed analysis confirms Anna Karenina principle of dynamics, demonstrating that environmental constraints enforce dynamical convergence in successful agents, while failing networks degenerate into idiosyncratic trajectories.