通过潜态动态网络学习时空过程的内在动态
Francesco Regazzoni1, Stefano Pagani2, Matteo Salvador2,3
1MOX, Department of Mathematics, Politecnico di Milano, Milan, Italy. francesco.regazzoni@polimi.it.
Nature communications
|February 28, 2024
概括
潜在动力学网络使用深度学习预测复杂系统的演变. 这种新的方法有效地揭示了空间时间系统中准确,数据驱动的预测的内在动态.
科学领域:
- 计算科学 计算科学
- 机器学习 机器学习
- 物理 物理学 物理
背景情况:
- 预测时空动态至关重要,但与传统方法计算密集.
- 数据驱动的深度学习为建模复杂系统演变提供了替代方案.
研究的目的:
- 介绍潜伏动力网络 (LDN) 架构.
- 能够准确地预测潜在的非马科维系统在低维空间中的系统演变.
主要方法:
- 开发了一种新的深度学习架构,即隐性动态网络 (LDN).
- LDNs自动发现低维的分流体,并同时学习系统动态.
- 该方法避免了自动编码器训练和高维空间操作.
主要成果:
- LDNs实现了卓越的准确性,正常化误差比最先进的方法小5倍.
- 需要的可训练参数要少得多 (比10倍少).
- 这种方法在高度非线性问题上表现出色,并且可以在没有固定的网格的情况下进行时间推算预测.
结论:
- 隐性动态网络为建模时空动态提供了一个轻量级,高效和准确的解决方案.
- 这种架构推进了科学预测和模拟的数据驱动方法.
相关概念视频
Linear time-invariant Systems
258
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
258
Spontaneity
23.9K
A spontaneous process is one that occurs naturally under certain conditions. A nonspontaneous process, on the other hand, will not take place unless it is “driven” by the continual input of energy from an external source. Processes have a natural tendency to occur in one direction under a given set of conditions. Water will naturally flow downhill (spontaneous process), but uphill flow (nonspontaneous process) requires outside intervention such as the use of a pump. Iron exposed to...
23.9K
Entropy Change in Reversible Processes
2.5K
In the Carnot engine, which achieves the maximum efficiency between two reservoirs of fixed temperatures, the total change in entropy is zero. The observation can be generalized by considering any reversible cyclic process consisting of many Carnot cycles. Thus, it can be stated that the total entropy change of any ideal reversible cycle is zero.
The statement can be further generalized to prove that entropy is a state function. Take a cyclic process between any two points on a p-V diagram.
The statement can be further generalized to prove that entropy is a state function. Take a cyclic process between any two points on a p-V diagram.
2.5K
State Space Representation
207
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
Consider an RLC circuit, a...
207
The Second Law of Thermodynamics
5.3K
In the quest to identify a property that may reliably predict the spontaneity of a process, a promising candidate has been identified: entropy. Scientists refer to the measure of randomness or disorder within a system as entropy. High entropy means high disorder and low energy. To better understand entropy, think of a student’s bedroom. If no energy or work were put into it, the room would quickly become messy. It would exist in a very disordered state, one of high entropy. Energy must be...
5.3K
Purposive Learning
119
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
119


