Nature Communications · 2024 · 28 citations · 42 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNanotechnologyDeep LearningNeural ModelingNeural NetworksDynamic RangeFew-shot LearningInternal DynamicsMultilayer NetworksNeuromorphic DevicesNeuromorphic HardwareNeuron DynamicsReservoir Computing
Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach's efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.
42
Oscillation and Chaos in Physiological Control Systems
Michael C. Mackey, Leon Glass · Science · 1977 · 4.1K citations
Neuromorphic computing with nanoscale spintronic oscillators
Jacob Torrejón, Flavio Abreu Araujo, Sumito Tsunegi et al. · Nature · 2017 · 1.3K citations · Full text
An Overview on Edge Computing Research
Keyan Cao, Yefan Liu, Gongjie Meng et al. · IEEE Access · 2020 · 1.2K citations · Full text