Fourier Transform Approach to Machine Learning III: Fourier Classification
This addresses classification problems with high nonlinearity and overlapped classes for machine learning practitioners, offering a novel method that avoids typical issues like overfitting.
The authors tackled highly nonlinear multiclass classification by proposing a Fourier-based learning algorithm that uses smoothing and low-pass filtering to calculate class probability distributions, enabling probabilistic explanations and handling overlapped classes without kernel functions or feature engineering.
We propose a Fourier-based learning algorithm for highly nonlinear multiclass classification. The algorithm is based on a smoothing technique to calculate the probability distribution of all classes. To obtain the probability distribution, the density distribution of each class is smoothed by a low-pass filter separately. The advantage of the Fourier representation is capturing the nonlinearities of the data distribution without defining any kernel function. Furthermore, contrary to the support vector machines, it makes a probabilistic explanation for the classification possible. Moreover, it can treat overlapped classes as well. Comparing to the logistic regression, it does not require feature engineering. In general, its computational performance is also very well for large data sets and in contrast to other algorithms, the typical overfitting problem does not happen at all. The capability of the algorithm is demonstrated for multiclass classification with overlapped classes and very high nonlinearity of the class distributions.