Wyniki wyszukiwania - BazTech

1

Comparison of classical machine learning algorithms in the task of handwritten digits classification

Voloshchenko Oleksandr, Plechawska-Wójcik Małgorzata

Journal of Computer Sciences Institute

|

2021

|

Vol. 21

279–286

EN

The purpose of this paper is to compare classical machine learning algorithms for handwritten number classification. The following algorithms were chosen for comparison: Logistic Regression, SVM, Decision Tree, Random Forest and k-NN. MNIST handwritten digit database is used in the task of training and testing the above algorithms. The dataset consists of 70,000 images of numbers from 0 to 9. The algorithms are compared considering such criteria as the learn-ing speed, prediction construction speed, host machine load, and classification accuracy. Each algorithm went through the training and testing phases 100 times, with the desired metrics retained at each iteration. The results were averaged to reach the reliable outcomes.

PL

Celem niniejszej pracy jest porównanie klasycznych algorytmów uczenia maszynowego do klasyfikacji liczb pisanych odręcznie. Do porównania wybrano następujące algorytmy: Logistic Regression, SVM, Decision Tree, Random Forest oraz k-NN. Do szkolenia i testowania powyższych algorytmów wykorzystano zbiór danych MNIST. Zbiór danych składa się z 70 000 obrazów cyfr od 0 do 9. Algorytmy porównywane są z uwzględnieniem takich kryteriów jak szyb-kość uczenia, szybkość budowania predykcji, obciążenie maszyny głównej oraz dokładność klasyfikacji. Każdy algo-rytm przeszedł przez fazy szkolenia i testowania 100 razy, z zachowaniem pożądanych metryk przy każdej iteracji. Wyniki zostały uśrednione w celu uzyskania wiarygodnych rezultatów.

2

Image Inpainting with Gradient Attention

Sadowski Michał, Grzegorczyk Aleksandra

Schedae Informaticae

|

2018

|

Vol. 27

81--91

EN

We present a novel modification of context encoder loss function, which results in more accurate and plausible inpainting. For this purpose, we introduce gradient attention loss component of loss function, to suppress the common problem of inconsistency in shapes and edges between the inpainted region and its context. To this end, the mean absolute error is computed not only for the input and output images, but also for their derivatives. Therefore, model concentrates on areas with larger gradient, which are crucial for accurate reconstruction. The positive effects on inpainting results are observed both for fully-connected and fully-convolutional models tested on MNIST and CelebA datasets.

3

Convergence Analysis of An Improved Extreme Learning Machine Based on Gradient Descent Method

Yusong L., Zhixun S., Bingjie Y., Xiaoling G., Zhaoyang S.

Journal of Applied Computer Science Methods

|

2016

|

Vol. 8 No. 1

5--15

EN

Extreme learning machine (ELM) is an efficient algorithm, but it requires more hidden nodes than the BP algorithms to reach the matched performance. Recently, an efficient learning algorithm, the upper-layer-solution-unaware algorithm (USUA), is proposed for the single-hidden layer feed-forward neural network. It needs less number of hidden nodes and testing time than ELM. In this paper, we mainly give the theoretical analysis for USUA. Theoretical results show that the error function monotonously decreases in the training procedure, the gradient of the error function with respect to weights tends to zero (the weak convergence), and the weight sequence goes to a fixed point (the strong convergence) when the iterations approach positive infinity. An illustrated simulation has been implemented on the MNIST database of handwritten digits which effectively verifies the theoretical results.