Tomasz Szandala

According to our database, Tomasz Szandala authored at least 14 papers between 2015 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2025

Predicting Desire Paths: Agent-Based Simulation for Neighbourhood Route Planning.

Józef Bossowski, Tomasz Szandala, Jacek Mazurkiewicz

Comput. Environ. Urban Syst., 2025

ChatGPT vs human expertise in the context of IT recruitment.

Tomasz Szandala

Expert Syst. Appl., 2025

2024

Discriminating feature ratio: Introducing metric for uncovering vulnerabilities in deep convolutional neural networks.

Tomasz Szandala, Henryk Maciejewski

Knowl. Based Syst., 2024

Enhancing SEO in Single-Page Web Applications in Contrast With Multi-Page Applications.

Karolina Kowalczyk, Tomasz Szandala

IEEE Access, 2024

2023

Unlocking the black box of CNNs: Visualising the decision-making process with PRISM.

Tomasz Szandala

Inf. Sci., 2023

2022

PRISM: Principal Image Sections Mapping.

Tomasz Szandala, Henryk Maciejewski

Proceedings of the Computational Science - ICCS 2022, 2022

2021

TorchPRISM: Principal Image Sections Mapping, a novel method for Convolutional Neural Network features visualization.

Tomasz Szandala

CoRR, 2021

Enhancing Deep Neural Network Saliency Visualizations With Gradual Extrapolation.

Tomasz Szandala

IEEE Access, 2021

Automated Method for Evaluating Neural Network's Attention Focus.

Tomasz Szandala, Henryk Maciejewski

Proceedings of the Computational Science - ICCS 2021, 2021

2020

Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks.

Tomasz Szandala

CoRR, 2020

Convolutional Neural Network for Blur Images Detection as an Alternative for Laplacian Method.

Tomasz Szandala

Proceedings of the 2020 IEEE Symposium Series on Computational Intelligence, 2020

2019

Benchmarking Comparison of Swish vs. Other Activation Functions on CIFAR-10 Imageset.

Tomasz Szandala

Proceedings of the Engineering in Dependability of Computer Systems and Networks, 2019

2015

Classification Based on Lingual Variables Using Expert Matrix Obtained with Genetic Algorithm.

Tomasz Szandala

Proceedings of the 6th Annual International Conference on Biologically Inspired Cognitive Architectures, 2015

Comparison of Different Learning Algorithms for Pattern Recognition with Hopfield's Neural Network.

Tomasz Szandala

Proceedings of the 6th Annual International Conference on Biologically Inspired Cognitive Architectures, 2015