Can neural networks count digit frequency?
This work addresses a specific problem in machine learning for digit frequency analysis, with potential applications in computer vision, but it is incremental as it applies existing methods to a new task.
The study compared neural networks with classical machine learning models for counting digit frequencies in numbers, finding that neural networks significantly outperformed decision trees and random forests in both regression and classification metrics on 6-digit and 10-digit datasets.
In this research, we aim to compare the performance of different classical machine learning models and neural networks in identifying the frequency of occurrence of each digit in a given number. It has various applications in machine learning and computer vision, e.g. for obtaining the frequency of a target object in a visual scene. We considered this problem as a hybrid of classification and regression tasks. We carefully create our own datasets to observe systematic differences between different methods. We evaluate each of the methods using different metrics across multiple datasets.The metrics of performance used were the root mean squared error and mean absolute error for regression evaluation, and accuracy for classification performance evaluation. We observe that decision trees and random forests overfit to the dataset, due to their inherent bias, and are not able to generalize well. We also observe that the neural networks significantly outperform the classical machine learning models in terms of both the regression and classification metrics for both the 6-digit and 10-digit number datasets. Dataset and code are available on github.