Entity · paper

From Classification to Regression: Using a Fruitfly to Solve Equations

paperactiveprovisionalfrom-classification-to-regression-using-a-fruitfly-to-solve-equations-d57003e4·1 events·first seen 2d ago

Aliases: From Classification to Regression: Using a Fruitfly to Solve Equations

More like this (12)

logistic regression probes Neural Classification Trees FFR: Forward-Forward Learning for Regression Graph Classification TF-IDF + Logistic Regression Grasshopper Problem (IMO 2009 P6)Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling behavior trees with learning-enabled components When to Align, When to Predict: A Phase Diagram for Multimodal Learning Class-Incremental Learning Arithmetic Pedagogy for Language Models Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0

Recent events (1)

4arXiv · cs.LG·2d ago·source ↗

Fruitfly-inspired classification-to-regression framework for nonlinear dynamical systems

A new arXiv preprint proposes a regression framework inspired by the fruitfly olfactory system, replacing global surrogate models with a finite library of local patterns and using similarity-weighted reconstruction for prediction. The method is applied to nonlinear dynamical systems, data-driven regression, and physics-informed learning. An offline-online workflow separates pattern extraction from inference, offering explicit control over accuracy-storage-compute tradeoffs.

Evaluation and Benchmarking From Classification to Regression: Using a Fruitfly to Solve Equations