G2BFNN:一般化地质基础函数神经网络
Yang Zhao1, Jiayi Xu2, Jihong Pei2
1College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China.
概括
我们介绍了一个通用的地质基础函数神经网络 (G2BFNN) 来从多元体上的数据中提取空间分布特征. 与现有方法相比,这种新的方法提高了数据表示和识别性能.
科学领域:
- 机器学习 机器学习
- 数据科学数据科学数据科学
- 计算几何学的计算几何学
背景情况:
- 现实世界的数据通常位于高维空间内的低维多元体上.
- 有效的特征表示需要准确地捕捉这些变体上的内在数据特征.
- 现有的方法很难从复杂的多重结构中提取强大的空间分布特征.
研究的目的:
- 提出一种新的神经网络架构,即通用地测基函数神经网络 (G2BFNN),用于在多元体上增强特征提取.
- 通过学习多重结构,开发一个通用的地测距离度量 (G2DM).
- 为了引入一个特定的实现,基于投影的歧视性本地保存G2BFNN (DLPP-G2BFNN),以改善数据表示.
主要方法:
- 拟议的G2BFNN架构使用了由已学习的G2DM.定义的概括地质基础函数 (G2BF).
- DLPP-G2BFNN包括一个多元结构学习模块 (MSLM) 和一个网络映射模块 (NMM).
- MSLM采用监督的相邻图来学习多重结构,保留局部几何形状并增强特征的可区分性.
主要成果:
- 该DLPP-G2BFNN有效地提取空间分布特征,反映内在的多元体特征.
- 实验结果显示,与基于欧几里德距离的方法相比,识别性能优越.
- 拟议的网络实现了较高的识别率与较少的核心比现有方法.
结论:
- G2BFNN架构为多重数据分析提供了通用和可扩展的方法.
- 与传统方法相比,DLPP-G2BFNN在揭示基本空间结构方面表现出卓越的能力.
- 拟议的方法为多重学习中的特征表示和识别提供了一个强大的工具.
相关概念视频
01:25Neural Circuits
1.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.1K
01:25Network Function of a Circuit
269
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
269
01:21State Space to Transfer Function
179
The conversion of state-space representation to a transfer function is a fundamental process in system analysis. It provides a method for transitioning from a time-domain description to a frequency-domain representation, which is crucial for simplifying the analysis and design of control systems.
The transformation process begins with the state-space representation, characterized by the state equation and the output equation. These equations are typically represented as:
The transformation process begins with the state-space representation, characterized by the state equation and the output equation. These equations are typically represented as:
179
01:26Gauss's Law: Spherical Symmetry
7.4K
A charge distribution has spherical symmetry if the density of charge depends only on the distance from a point in space and not on the direction. In other words, if the system is rotated, it doesn't look different. For instance, if a sphere of radius R is uniformly charged with charge density ρ0, then the distribution has spherical symmetry. On the other hand, if a sphere of radius R is charged so that the top half of the sphere has a uniform charge density ρ1 and the bottom half...
7.4K
01:15Geometric Mean
3.4K
The mean is a measure of the central tendency of a data set. In some data sets, the data is inherently multiplicative, and the arithmetic mean is not useful. For example, the human population multiplies with time, and so does the credit amount of financial investment, as the interest compounds over successive time intervals.
In cases of multiplicative data, the geometric mean is used for statistical analysis. First, the product of all the elements is taken. Then, if there are n elements in the...
In cases of multiplicative data, the geometric mean is used for statistical analysis. First, the product of all the elements is taken. Then, if there are n elements in the...
3.4K