Classification with neural networks with quadratic decision functions
This work addresses classification problems where objects have compact, basic geometries, but it appears incremental as it applies an existing method to new data.
The paper investigated neural networks with quadratic decision functions for classification tasks, testing them on MNIST and subspecies datasets, and demonstrated implementation using TensorFlow and Keras.
Neural networks with quadratic decision functions have been introduced as alternatives to standard neural networks with affine linear ones. They are advantageous when the objects or classes to be identified are compact and of basic geometries like circles, ellipses etc. In this paper we investigate the use of such ansatz functions for classification. In particular we test and compare the algorithm on the MNIST dataset for classification of handwritten digits and for classification of subspecies. We also show, that the implementation can be based on the neural network structure in the software Tensorflow and Keras, respectively.