201 citations · 244 across the 6 of their papers we have counts for
4 papers · 1 filter
A Geometrical Approach to Constructing Neural Networks for Perfect Training-set Classification
Akos Hajnal
This paper proposes a method for constructing a neural network that achieves perfect classification of all samples in a given training set, without taking regularization into accou…
An Iterative Geometric Approach to Optimizing Separating Hyperplanes
Akos Hajnal
Given a binary-labeled linearly separable dataset, and the objective is to compute the maximum-margin separating hyperplane, also known as the hard-margin Support Vector Machine (S…
On Linear Separability of the MNIST Handwritten Digits Dataset
Ákos Hajnal
The MNIST dataset containing thousands of handwritten digit images is still a fundamental benchmark for evaluating various pattern-recognition and image-classification models. Line…
A Perceptron-based Fine Approximation Technique for Linear Separation
Ákos Hajnal
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…