The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key challenge, however, is to understand which learning rules are best suited for specific tasks and how the relevant hyperparameters can be fine-tuned. In this work, we introduce a conceptual framework in which the learning process is integrated into the network itself. This allows us to cast meta-learning as a mathematical optimization problem. We employ DeepHyper, a scalable, asynchronous model-based search, to simultaneously optimize the choice of meta-learning rules and their hyperparameters. We demonstrate our approach with two different datasets, MNIST and FashionMNIST, using a network architecture inspired by the learning center of the insect brain. Our results show that optimal learning rules can be dataset-dependent even within similar tasks. This dependency demonstrates the importance of introducing versatility and flexibility in the learning algorithms. It also illuminates experimental findings in insect neuroscience that have shown a heterogeneity of learning rules within the insect mushroom body.
A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures
Systems Lab, Zernike Institute for Advanced Materials, University of Groningen, Netherlands(格罗宁根大学系统实验室,泽尼克先进材料研究所);Materials Center, University of Groningen, Netherlands(格罗宁根大学材料中心);School of Engineering, University of Cádiz, Puerto Real, Cádiz, Spain(卡迪斯大学工程学院);Institute of Neuroinformatics, University of Zurich(苏黎世大学神经信息研究所);ETH Zurich, Zurich, Switzerland(苏黎世联邦理工学院)
Exploring Structural Nonlinearity in Binary Polariton-Based Neuromorphic Architectures
St. Petersburg State University(圣彼得堡国立大学);Stoletov Vladimir State University(斯托列托夫弗拉基米尔国立大学);Moscow Institute of Physics and Technology(莫斯科物理技术学院);Westlake University(西湖大学)
A High Energy-Efficiency Multi-core Neuromorphic Architecture for Deep SNN Training
PengCheng Laboratory(鹏城实验室);School of Computer Science, Peking University(北京大学计算机学院);School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University(北京大学深圳研究生院电子与计算机工程学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Southern University of Science and Technology(南方科技大学)
Neuromorphic Satellite Intelligence: A Formal Framework for Event-Driven Architectures, Spike-Based Algorithms, and Quantitative Energy-Accuracy Trade-offs
Energy-Efficient Neuromorphic Computing for Edge AI: A Framework with Adaptive Spiking Neural Networks and Hardware-Aware Optimization
Department of Applied Mathematics and Computer Science (DTU Compute)(应用数学与计算机科学系(DTU计算));Department of Engineering(工程系);Department of Computer Engineering(计算机工程系);Department of Mathematics(数学系);Department of Computer Systems(计算机系统系)
NeuroNAS: Enhancing Efficiency of Neuromorphic In-Memory Computing for Intelligent Mobile Agents through Hardware-Aware Spiking Neural Architecture Search