用于手写数字分类的双阶段特征生成器
M Altinay Gunler Pirim1, Hakan Tora2, Kasim Oztoprak3
1Vakifbank, 06200 Ankara, Turkey.
Sensors (Basel, Switzerland)
|October 28, 2023
概括
用于手写数字分类的新功能生成框架使用主要组件分析 (PCA) 和部分训练的神经网络 (PTNN) 实现了高精度. 这种新的方法甚至在有限的培训数据的情况下也表现出色.
科学领域:
- 计算机科学 计算机科学
- 机器学习 机器学习
- 模式识别 模式识别
背景情况:
- 手写数字的分类是识别模式的一个基本任务.
- 现有的方法通常需要大型数据集和复杂的功能工程.
研究的目的:
- 提出一个新的,双阶段级级特征生成器框架,用于增强手写数字分类.
- 评估框架在基准数据集上的表现,并与最先进的技术进行比较.
主要方法:
- 该框架采用两阶段的方法:主要组件分析 (PCA) 用于初始特征提取,其次是部分训练的神经网络 (PTNN) 用于精细的特征生成.
- 使用最小距离分类器 (MDC) 和支持矢量机 (SVM) 分类器测试特征.
- 性能是根据MNIST和USPS手写数字数据集进行评估的.
主要成果:
- 拟议的框架在MNIST上达到99.9815%的高精度,在USPS上达到99.9863%.
- 功能生成器显著优于现有的最先进的方法.
- 该框架表现出强大的性能,即使训练数据大小大幅减少.
结论:
- 新的两阶段特征生成器框架为手写数字分类提供了一种优越的方法.
- 该方法是高效和有效的,在最小的数据中实现近乎完美的准确性.
- 这种框架对于需要精确数字识别的应用程序具有潜力,而且资源有限.
相关概念视频
01:22Force Classification
1.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.2K
01:30Classification of Signals
484
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
484