Input-Driven Dynamics for Robust Memory Retrieval in Hopfield Networks
This work addresses a gap in understanding memory retrieval dynamics in neural networks, offering insights for computational neuroscience and AI memory systems, though it is incremental in extending existing Hopfield frameworks.
The paper tackles the underexplored role of external inputs in Hopfield networks by proposing a novel dynamical system where inputs directly influence synapses and shape the energy landscape, enabling correct classification of highly mixed inputs and demonstrating improved robustness to noise compared to classic models.
The Hopfield model provides a mathematically idealized yet insightful framework for understanding the mechanisms of memory storage and retrieval in the human brain. This model has inspired four decades of extensive research on learning and retrieval dynamics, capacity estimates, and sequential transitions among memories. Notably, the role and impact of external inputs has been largely underexplored, from their effects on neural dynamics to how they facilitate effective memory retrieval. To bridge this gap, we propose a novel dynamical system framework in which the external input directly influences the neural synapses and shapes the energy landscape of the Hopfield model. This plasticity-based mechanism provides a clear energetic interpretation of the memory retrieval process and proves effective at correctly classifying highly mixed inputs. Furthermore, we integrate this model within the framework of modern Hopfield architectures, using this connection to elucidate how current and past information are combined during the retrieval process. Finally, we embed both the classic and the new model in an environment disrupted by noise and compare their robustness during memory retrieval.