paper-with-me

Papers

Reducing hyperparameter dependence by external timescale tailoring

2023-07-17 · Lina C. Jaurigue, Kathy Lüdge

Task specific hyperparameter tuning in reservoir computing is an open issue, and is of particular relevance for hardware implemented reservoirs. We investigate the influence of directly including externally controllable task specific timescales on the performance and hyperparameter sensitivity of reservoir computing approaches. We show that the need for hyperparameter optimisation can be reduced if timescales of the reservoir are tailored to the specific task. Our results are mainly relevant for temporal tasks requiring memory of past inputs, for example chaotic timeseries prediciton. We consider various methods of including task specific timescales in the reservoir computing approach and demonstrate the universality of our message by looking at both time-multiplexed and spatially multiplexed reservoir computing.

📄 PDF Abstract BibTeX arXiv:2307.08603

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How to set AdamW's weight decay as you scale model and dataset size

2024-05-22 · Xi Wang, Laurence Aitchison

The scaling of the optimal AdamW weight decay hyperparameter with model and dataset size is critical as we seek to build larger models, but is poorly understood. We show that weights learned by AdamW can be understood as…

Self-induced stochastic resonance: A physics-informed machine learning approach

2025-10-26 · Divyesh Savaliya, Marius E. Yamakou arxiv

Self-induced stochastic resonance (SISR) is the emergence of coherent oscillations in slow-fast excitable systems driven solely by noise, without external periodic forcing or proximity to a bifurcation. This work present…

Critical neuronal models with relaxed timescales separation

2018-07-17

Power laws in nature are considered to be signatures of complexity. The theory of self-organized criticality (SOC) was proposed to explain their origins. A longstanding principle of SOC is the \emph{separation of timesca…

A two-step sequential approach for hyperparameter selection in finite context models

2026-03-20 · José Contente, Ana Martins, Armando J. Pinho, Sónia Gouveia arxiv

Finite-context models (FCMs) are widely used for compressing symbolic sequences such as DNA, where predictive performance depends critically on the context length k and smoothing parameter α. In practice, these hyperpara…

Mapping distinct timescales of functional interactions among brain networks

2017-12-01 · NeurIPS 2017 12 · Mali Sundaresan, Arshed Nabeel, Devarajan Sridharan

Brain processes occur at various timescales, ranging from milliseconds (neurons) to minutes and hours (behavior). Characterizing functional coupling among brain regions at these diverse timescales is key to understanding…

Functional ConnectivityRobust classification