#dynamical-systems News & Analysis

4 articles tagged with #dynamical-systems. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · Apr 207/10

🧠

EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs

Researchers introduce EVIL, an LLM-guided evolutionary approach that discovers interpretable Python algorithms for zero-shot inference on time series and event sequences without traditional neural network training. The evolved algorithms match or exceed deep learning performance while remaining transparent and significantly faster, demonstrating a novel paradigm for dynamical systems inference.

AIBullisharXiv – CS AI · Mar 167/10

🧠

Learnable Koopman-Enhanced Transformer-Based Time Series Forecasting with Spectral Control

Researchers propose a new family of learnable Koopman operators that combine linear dynamical systems theory with deep learning for time series forecasting. The approach integrates with existing transformer architectures like Patchtst and Autoformer, offering improved stability and interpretability in predictive models.

AINeutralarXiv – CS AI · Mar 37/104

🧠

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity

Researchers have identified the mathematical mechanisms behind 'loss of plasticity' (LoP), explaining why deep learning models struggle to continue learning in changing environments. The study reveals that properties promoting generalization in static settings actually hinder continual learning by creating parameter space traps.

AINeutralarXiv – CS AI · Apr 146/10

🧠

Detecting Invariant Manifolds in ReLU-Based RNNs

Researchers have developed a novel algorithm for detecting invariant manifolds in ReLU-based recurrent neural networks (RNNs), enabling analysis of dynamical system behavior through topological and geometrical properties. The method identifies basin boundaries, multistability, and chaotic dynamics, with applications to scientific computing and explainable AI.