| Algorithm | Alphabet / Digits | Digits |
|---|---|---|
| SoftMax Logistic Regression | 0.6085106 | 0.7697 |
| Neural Network | 0.6993085 | 0.9823 |
| Nueral Network with Xavier Initialization | 0.8368085 | 0.988775 |
| Nueral Network with Dropout | 0.84957445 | 0.990575 |
| Convolutional Neural Network (CNN) | 0.89090425 | 0.996125 |
| Convolutional Neural Network with Ensemble | 0.89521277 | 0.997225 |
Groups of objects that are
- Internal tightness within group
- External separation between groups
A generalization of a method to find a linear combination of features that characterizes or separates two or more classes of objects or events. The resulting combination may be used as a linear classifier, or, more commonly, for dimensionality recution
The simplest and most commonly applied form of linear regression, which provides a solution to the problem of finding the best fitting straight line through a set of points.
A statistical model that in its basic form uses a logistic function to model a binary dependent variable, although many more complex extensions exist
- Determine the form of the low dimensional representation
- Define a criterion to measure the quality of approximation
- Training: Optimize on data set to minimize the criterion
- Testing: Project new datum on the low dimensional representation