Analyzing the Efficacy of Base Algorithms: Application of Machine Learning Models in Classification Tasks

The article presents a comprehensive examination and comparison of several machine learning algorithms, such as Artificial Neural Network, K-Nearest Neighbor, Support Vector Machines, Decision Tree, and Random Forests, with a specific focus on the significance of neural networks in classification tasks. This study employs three distinct datasets: (1) the "Titanic" dataset is about the sinking of the British transatlantic liner, which resulted in the deaths of 1502 of the 2224 people who were on board. On April 15, 1912, the event occurred in the North Atlantic Ocean; (2) the "MNIST" dataset, which consists of 70,000 grayscale images (28×28 pixels) of handwritten digits; (3) and the "Fashion-MNIST" dataset, which showcases images of 10 fashion item classes such as T-shirt/Top, Trouser, Pullover, Dress, Coat, Sandals, Shirt, Sneaker, Bag, Ankle boots which have been classified. The analysis evaluates the strengths and weaknesses of each algorithm based on the research outcomes. The results suggest that for certain classification tasks, the use of machine learning algorithms may be more appropriate, as the accuracy levels may remain relatively unchanged, and vary depending on the size of the dataset used with the features it includes in the classification tasks.