通过高阶光谱聚类进行过器修剪
概括
本研究引入了一种新的过器修剪方法,用于使用高阶光谱集群的卷积神经网络 (CNN). 它有效地去除多余的过器,在不影响性能的情况下实现显著的模型压缩.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 卷积神经网络 (CNN) 通常含有显著的冗余性,导致模型大小.
- 现有的过器修剪方法主要依赖于距离指标,无法捕捉复杂的相关性,不适合高维特征.
- 这种限制阻碍了深度学习模型的有效压缩.
研究的目的:
- 为CNN开发一种先进的过器修剪策略,以解决基于距离的方法的局限性.
- 通过更有效地识别和删除多余的过器来提高模型压缩的准确性和效率.
- 为了实现显著的模型尺寸缩小,性能最小或没有损失.
主要方法:
- 提出了一种基于高阶光谱聚类的新型修剪策略.
- 使用超图结构来建模过器之间的复杂相关性.
- 采用超图结构学习来提取高阶信息,用于过器集群和冗余识别.
主要成果:
- 拟议的方法在各种CNN模型和数据集中,与最先进的技术相比,显示出更高的性能.
- 在ImageNet上为ResNet50实现了57.1%的浮点运算 (FLOP) 减少,而没有任何精度下降.
- 代表了无损修剪的突破,具有高压缩比.
结论:
- 高阶光谱聚类提供了一种更有效的方法来识别和删除CNN中的冗余过器.
- 提出的基于超图的方法可以实现显著的模型压缩,同时保持准确性.
- 这项工作为深度学习模型中无损修剪设定了新的基准.
相关概念视频
Cluster Sampling Method
11.6K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
11.6K
Quantifying and Rejecting Outliers: The Grubbs Test
1.4K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
1.4K
Trimmed Mean
2.8K
While measuring the mean of a data set, care needs to be taken when associating the mean to its central tendency. The same goes for the arithmetic mean, the geometric mean, or the harmonic mean. This is because the presence of a single outlier data value can significantly affect the mean. That is, the mean is sensitive to fluctuations in the data set.
Although certain measures of central tendency are not sensitive to outliers, there are alternative versions of the mean that get around the...
Although certain measures of central tendency are not sensitive to outliers, there are alternative versions of the mean that get around the...
2.8K
Extraction: Partition and Distribution Coefficients
1.7K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
For extracting a solute from an aqueous phase into an...
1.7K
¹H NMR: Interpreting Distorted and Overlapping Signals
989
Spin systems where the difference in chemical shifts of the coupled nuclei is greater than ten times J are called first-order spin systems. These nuclei are weakly coupled, and their chemical shifts and coupling constant can generally be estimated from the well-separated signals in the spectrum.
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
989
Survival Tree
50
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
50


