GT-CAM:用于GCN的基于游戏理论的类激活地图
概括
本研究介绍了基于图形理论的类激活映射 (GT-CAM),用于使用图形卷积网络 (GCN) 进行可解释的基于骨架的行为识别. 通过考虑节点相互作用,GT-CAM提高了解释性,超过了现有的方法.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 图形卷积网络 (GCN) 在基于骨架的行为识别方面表现出色,但缺乏透明度.
- 对于GCNs,现有的类激活图 (CAM) 方法经常忽略关键节点相互作用.
- 可解释性对于推动深度学习模型开发和信任至关重要.
研究的目的:
- 为GCNs在行为识别中开发一种新的可解释的人工智能方法.
- 通过结合节点交互来解决现有的CAM算法的局限性.
- 提供对GCN决策过程的更全面的理解.
主要方法:
- 拟议的基于图形理论的类激活映射 (GT-CAM) 集成Shapley值和梯度权重.
- 开发了一种计算节点联盟的Shapley值的方法,以降低计算成本.
- 引入了一种使用双边和合作游戏理论的理性评估方法.
- 实现了基于蒙特卡洛的有效计算联盟理性系数.
主要成果:
- GT-CAM生成激活地图,突出显示关键节点,并揭示节点或子图之间的合作动态.
- 拟议的基于联盟的Shapley值计算显著降低了计算负担.
- 理性评估方法确保了强大而有意义的联盟分区.
- 实验结果显示GT-CAM在可视化和定量分析方面超过了现有的解释方法.
结论:
- 在基于骨架的行为识别中,GT-CAM为GCN的解释性提供了显著的进步.
- 游戏理论方法有效地捕捉了节点相互作用,导致了更有洞察力的解释.
- GT-CAM为GCN可解释性提供了一个计算效率高且数量优越的替代方案.
更多相关视频
09:34Applications of Spatio-temporal Mapping and Particle Analysis Techniques to Quantify Intracellular Ca2+ Signaling In Situ
Published on: January 7, 2019
9.3K
13:40Combining Computer Game-Based Behavioural Experiments With High-Density EEG and Infrared Gaze Tracking
Published on: December 16, 2010
16.7K
相关概念视频
Vector Algebra: Graphical Method
12.1K
Vectors can be multiplied by scalars, added to other vectors, or subtracted from other vectors. The vector sum of two (or more) vectors is called the resultant vector or, for short, the resultant.
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
12.1K
Propagation of Action Potentials
5.6K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
5.6K
Network Function of a Circuit
280
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.
280
Neural 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
Deactivation Processes: Jablonski Diagram
638
Luminescence, the emission of light by a substance that has absorbed energy, is a process that involves the interaction of molecules with light. The energy-level diagram, or Jablonski diagram, is a graphical representation of these interactions, illustrating the various states and transitions a molecule can undergo. In a typical Jablonski diagram, the lowest horizontal line represents the ground-state energy of the molecule, which is usually a singlet state. This state represents the energies...
638
State Space to Transfer Function
197
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:
197
