Local Approximations, Real Interpolation and Machine Learning

07/15/2022
by   Eric Setterqvist, et al.
0

We suggest a novel classification algorithm that is based on local approximations and explain its connections with Artificial Neural Networks (ANNs) and Nearest Neighbour classifiers. We illustrate it on the datasets MNIST and EMNIST of images of handwritten digits. We use the dataset MNIST to find parameters of our algorithm and apply it with these parameters to the challenging EMNIST dataset. It is demonstrated that the algorithm misclassifies 0.42 predictions by humans and shallow artificial neural networks (ANNs with few hidden layers) that both have more than 1.3

READ FULL TEXT

page 5

page 6

research
04/27/2022

An Improved Nearest Neighbour Classifier

A windowed version of the Nearest Neighbour (WNN) classifier for images ...
research
09/01/2016

Defeating Image Obfuscation with Deep Learning

We demonstrate that modern image recognition methods based on artificial...
research
01/28/2022

DELAUNAY: a dataset of abstract art for psychophysical and machine learning research

Image datasets are commonly used in psychophysical experiments and in ma...
research
12/12/2016

Neurogenesis Deep Learning

Neural machine learning methods, such as deep neural networks (DNN), hav...
research
07/03/2020

MASKS: A Multi-Artificial Neural Networks System's verification approach

Artificial Neural networks are one of the most widely applied approaches...
research
11/03/2022

Exploring explicit coarse-grained structure in artificial neural networks

We propose to employ the hierarchical coarse-grained structure in the ar...
research
09/18/2017

Combinational neural network using Gabor filters for the classification of handwritten digits

A classification algorithm that combines the components of k-nearest nei...

Please sign up or login with your details

Forgot password? Click here to reset