Research map / Probabilistic and scientific modeling / Dynamical systems
Memory by accident: a theory of learning as a byproduct of network stabilization
Basile Confavreux, Will Dorrell, Nishil Patel, Andrew M Saxe
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a theory in which memory arises as a byproduct of neural network stabilization, rather than from learning rules explicitly optimized for a memory function.
Problem
Biologically plausible learning rules for memory in neural networks are typically derived by optimizing directly for a desired memory function, which can yield complex, finely tuned rules.
Approach
Memory emerges as a side effect of network stabilization dynamics, so learning is a byproduct of stabilizing the network rather than a directly optimized objective.
Closest papers by meaning
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.91)
- Dynamical phases of short-term memory mechanisms in RNNs (ICML 2025 · similarity 0.88)
- Discovering plasticity rules that organize and maintain neural circuits (NeurIPS 2024 · similarity 0.88)
- Model Based Inference of Synaptic Plasticity Rules (NeurIPS 2024 · similarity 0.88)
- Predictive Attractor Models (NeurIPS 2024 · similarity 0.88)
- Feedback control guides credit assignment in recurrent neural networks (NeurIPS 2024 · similarity 0.88)
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.
