Publications Repository - Gdańsk University of Technology

Recently gathered image datasets and the new capabilities of high-performance computing systems have allowed developing new artificial neural network models and training algorithms. Using the new machine learning models, computer vision tasks can be accomplished based on the raw values of image pixels instead of specific features. The principle of operation of deep neural networks resembles more and more what we believe to be happening in the human visual cortex. In this paper, we build up an understanding of the most-successful recent model (a convolutional neural network) through the investigation of supervised machine learning methods such as K-Nearest Neighbors, linear classifiers, and fully connected neural networks. We provide examples and accuracy results based on our implementation aimed for the problem of hand pose recognition.

Authors

• dr inż. Paweł Rościszewski link open in new tab