paper-with-me

홈 › Papers

Actionable forecasting as a determinant of function in noisy biological systems

2024-04-11 · Jose M. G. Vilar, Leonor Saiz

Continuous adaptation to variable environments is crucial for the survival of living organisms. Here, we analyze how adaptation, forecasting, and resource mobilization towards a target state, termed actionability, interact to determine biological function. We develop a general theory and show that it is possible for organisms to continuously track their optimal state in a dynamic environment by adapting towards an actionable target that incorporates just current information on the optimal state and its rate of change. If the environmental information is precise and readily actionable, it is possible to implement perfect tracking without anticipatory mechanisms, irrespective of the adaptation rate. In contrast, predictive functions, like those of circadian rhythms, are beneficial if sensing the environment is slow or unreliable, as they allow better adaptation with fewer resources. To explore potential actionable forecasting mechanisms, we develop a general approach that implements the adaptation dynamics with forecasting through a dynamics-informed neural network.

📄 PDF Abstract BibTeX arXiv:2404.07895

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Aortic Pressure Forecasting with Deep Sequence Learning

2020-05-12 · Eliza Huang, Rui Wang, Uma Chandrasekaran, Rose Yu

Mean aortic pressure (MAP) is a major determinant of perfusion in all organs systems. The ability to forecast MAP would enhance the ability of physicians to estimate prognosis of the patient and assist in early detection…

PrognosisTime SeriesTime Series Analysis

iDNA-ABF: multi-scale deep biological language learning model for the interpretable prediction of DNA methylations

2022-10-17 · Genome Biology 2022 10 · Junru Jin, Yingying Yu, Ruheng Wang, Xin Zeng 외

In this study, we propose iDNA-ABF, a multi-scale deep biological language learning model that enables the interpretable prediction of DNA methylations based on genomic sequences only. Benchmarking comparisons show that …

BenchmarkingText Classification

AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data

2023-10-31 · Santosh Palaskar, Vijay Ekambaram, Arindam Jati, Neelamadhav Gantayat 외

The efficiency of business processes relies on business key performance indicators (Biz-KPIs), that can be negatively impacted by IT failures. Business and IT Observability (BizITObs) data fuses both Biz-KPIs and IT even…

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting

POCO: Scalable Neural Forecasting through Population Conditioning

2025-06-17 · Yu Duan, Hamza Tahir Chaudhry, Misha B. Ahrens, Christopher D Harvey 외

Predicting future neural activity is a core challenge in modeling brain dynamics, with applications ranging from scientific investigation to closed-loop neurotechnology. While recent models of population activity emphasi…

Robust Determinantal Generative Classifier for Noisy Labels and Adversarial Attacks

2019-05-01 · ICLR 2019 5 · Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee 외

Large-scale datasets may contain significant proportions of noisy (incorrect) class labels, and it is well-known that modern deep neural networks poorly generalize from such noisy training datasets. In this paper, we …