A Perceptron-based Fine Approximation Technique for Linear Separation
This incremental improvement addresses efficiency issues in training perceptron classifiers for binary classification tasks, especially in scenarios with large or imbalanced data.
The paper tackles the problem of training perceptron-based binary classifiers on large or imbalanced datasets by proposing a novel online learning method that transforms the data to eliminate labels and bias, reducing it to a one-class classification problem. Empirical results indicate the method converges and is more efficient than the Perceptron algorithm, particularly when dataset size exceeds dimensionality.
This paper presents a novel online learning method that aims at finding a separator hyperplane between data points labelled as either positive or negative. Since weights and biases of artificial neurons can directly be related to hyperplanes in high-dimensional spaces, the technique is applicable to train perceptron-based binary classifiers in machine learning. In case of large or imbalanced data sets, use of analytical or gradient-based solutions can become prohibitive and impractical, where heuristics and approximation techniques are still applicable. The proposed method is based on the Perceptron algorithm, however, it tunes neuron weights in just the necessary extent during searching the separator hyperplane. Due to an appropriate transformation of the initial data set we need not to consider data labels, neither the bias term. respectively, reducing separability to a one-class classification problem. The presented method has proven converge; empirical results show that it can be more efficient than the Perceptron algorithm, especially, when the size of the data set exceeds data dimensionality.