In-memory phononic learning toward cognitive mechanical intelligence

Abstract

Modern autonomous systems are driving the critical need for next-generation adaptive materials and structures with embodied intelligence, i.e., the embodiment of memory, perception, learning, and decision-making within the mechanical domain. A fundamental challenge is the seamless and efficient integration of memory with information processing in a physically interpretable way that enables cognitive learning and decision-making under uncertainty. Prevailing paradigms, from intricate logic cascades to black-box morphological computing or physical neural networks, are seriously limited by trade-offs among efficiency, scalability, interpretability, transparency, and reliance on additional electronics. Here, we introduce in-memory phononic learning, a paradigm-shifting framework that unifies nonvolatile mechanical memory with wave-based perception within a phononic metastructure. Our system encodes spatial information into stable structural states as mechanical memory that directly programs its elastic wave-propagation landscape. This memory/wave-dynamics coupling enables effective sensory perception, decomposing complex patterns into informative geometric features through frequency-selective wave localization. Learning is created by optimizing input waveforms to selectively probe these features for memory-pattern classification, with decisions inferred directly from the output wave energy, thereby completing the entire information loop mechanically through an efficient and physically transparent mechanism without hidden architectures or electronics. This work transcends the paradigm of 'materials that compute' to cognitive matter capable of interpreting dynamic environments, paving the way for future intelligent structural-material systems with low power consumption, more direct interaction with surroundings, and enhanced cybersecurity and resilience in harsh conditions.