Research map / Time series / Causal and generative time series
Causality Preserving Chaotic Transformation and Classification using Neurochaos Learning
Harikrishnan N B, Aditi Kathpalia, Nithin Nagaraj
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ChaosNet instead of five layer DNN for cause-effect classification | ChaosNet · Coupled skew tent maps, eta 0.6-0.7 | macro F1-score | Improved |
| Use ChaosNet instead of five layer DNN for cause-effect classification | ChaosNet · Coupled skew tent maps, eta up to 0.5 | macro F1-score: 1.0 -> 1.0 | No clear effect |
| Increase coupling beyond 0.6 until synchronization | Cause-effect classification · Coupled skew tent maps | macro F1-score | Hurt |
| Use ChaosNet instead of DNN when testing on shifted skew tent parameters (Case I, b1=0.6, b2=0.4) | ChaosNet · Transfer Case I | macro F1-score | Improved |
| Use ChaosNet instead of DNN when testing on shifted skew tent parameters (Case II, b1=0.1, b2=0.3) | ChaosNet · Transfer Case II | macro F1-score | Improved |
| Transfer from skew tent maps to logistic maps (Case III) with ChaosNet versus DNN | ChaosNet · Transfer Case III | macro F1-score | Mixed |
| Use ChaosNet instead of DNN on coupled AR processes | ChaosNet · Coupled AR processes | macro F1-score: 0.656 | Improved |
| Use ChaosFEX firing time features instead of DNN features for Granger causality preservation | ChaosNet · Coupled AR processes | Granger causality preservation | Improved |
| Use ChaosFEX firing time instead of raw data for CCC on prey-predator data | ChaosNet · Prey-predator | CCC Predator->Prey: 0.1160 -> 0.0484 | Mixed |
Closest papers by meaning
- Hybrid$^2$ Neural ODE Causal Modeling and an Application to Glycemic Response (ICML 2024 · similarity 0.84)
- Generating Hypotheses of Dynamic Causal Graphs in Neuroscience: Leveraging Generative Factor Models of Observed Time Series (ICML 2025 · similarity 0.84)
- UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems (NeurIPS 2025 · similarity 0.83)
- Identifying Neural Dynamics Using Interventional State Space Models (ICML 2025 · similarity 0.83)
- Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data (NeurIPS 2025 · similarity 0.83)
- Multi-Granularity Causal Structure Learning (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
