paper-with-me

Papers

Neuronal diversity can improve machine learning for physics and beyond

2022-04-09 · Anshul Choudhary, Anil Radhakrishnan, John F. Lindner, Sudeshna Sinha, William L. Ditto

Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the layers of artificial neural networks. Here we construct neural networks from neurons that learn their own activation functions, quickly diversify, and subsequently outperform their homogeneous counterparts on image classification and nonlinear regression tasks. Sub-networks instantiate the neurons, which meta-learn especially efficient sets of nonlinear responses. Examples include conventional neural networks classifying digits and forecasting a van der Pol oscillator and physics-informed Hamiltonian neural networks learning H\'enon-Heiles stellar orbits and the swing of a video recorded pendulum clock. Such \textit{learned diversity} provides examples of dynamical systems selecting diversity over uniformity and elucidates the role of diversity in natural and artificial systems.

📄 PDF Abstract BibTeX arXiv:2204.04348

Code (1)

NonlinearArtificialIntelligenceLab/jaxDiversity 공식 구현 jax

Tasks

Diversityimage-classificationImage ClassificationMeta-Learningregression

Similar Papers 제목 키워드 기반

Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks

2023-01-23 · Feng-Lei Fan, Yingxin Li, Hanchuan Peng, Tieyong Zeng 외

Throughout history, the development of artificial intelligence, particularly artificial neural networks, has been open to and constantly inspired by the increasingly deepened understanding of the brain, such as the inspi…

Diversity

A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning

2023-07-27 · Heng Zhang, Danilo Vasconcellos Vargas

Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple str…

Diversity improves performance in excitable networks

2015-07-19

As few real systems comprise indistinguishable units, diversity is a hallmark of nature. Diversity among interacting units shapes properties of collective behavior such as synchronization and information transmission. Ho…

Diversity

Robust Computation with Intrinsic Heterogeneity

2024-12-06 · Arash Golmohammadi, Christian Tetzlaff

Intrinsic within-type neuronal heterogeneity is a ubiquitous feature of biological systems, with well-documented computational advantages. Recent works in machine learning have incorporated such diversities by optimizing…

Constructing a bridge between functioning of oscillatory neuronal networks and quantum-like cognition along with quantum-inspired computation and AI

2025-05-27 · Andrei Khrennikov, Atsushi Iriki, Irina Basieva

Quantum-like (QL) modeling, one of the outcomes of the quantum information revolution, extends quantum theory methods beyond physics to decision theory and cognitive psychology. While effective in explaining paradoxes in…

Decision Making