Lennart Brocki

According to our database, Lennart Brocki authored at least 13 papers between 2019 and 2024.

Collaborative distances:

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

2024

False Sense of Security in Explainable Artificial Intelligence (XAI).

Neo Christopher Chung, Hongkyou Chung, Hearim Lee, Hongbeom Chung, Lennart Brocki, George C. Dyer

CoRR, 2024

2023

Feature perturbation augmentation for reliable evaluation of importance estimators in neural networks.

Lennart Brocki, Neo Christopher Chung

Pattern Recognit. Lett., December, 2023

Class-Discriminative Attention Maps for Vision Transformers.

Lennart Brocki, Neo Christopher Chung

CoRR, 2023

Challenges of Large Language Models for Mental Health Counseling.

Neo Christopher Chung, George C. Dyer, Lennart Brocki

CoRR, 2023

Integration of Radiomics and Tumor Biomarkers in Interpretable Machine Learning Models.

Lennart Brocki, Neo Christopher Chung

CoRR, 2023

Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators.

Lennart Brocki, Neo Christopher Chung

CoRR, 2023

Fidelity of Interpretability Methods and Perturbation Artifacts in Neural Networks.

Lennart Brocki, Neo Christopher Chung

Proceedings of the First Tiny Papers Track at ICLR 2023, 2023

Deep Learning Mental Health Dialogue System.

Lennart Brocki, George C. Dyer, Anna Gladka, Neo Christopher Chung

Proceedings of the IEEE International Conference on Big Data and Smart Computing, 2023

2022

Evaluation of Interpretability Methods and Perturbation Artifacts in Deep Neural Networks.

Lennart Brocki, Neo Christopher Chung

CoRR, 2022

Evaluation of Importance Estimators in Deep Learning Classifiers for Computed Tomography.

Lennart Brocki, Wistan Marchadour, Jonas Maison, Bogdan Badic, Panagiotis G. Papadimitroulas, Mathieu Hatt, Franck Vermet, Neo Christopher Chung

Proceedings of the Explainable and Transparent AI and Multi-Agent Systems, 2022

2021

Input Bias in Rectified Gradients and Modified Saliency Maps.

Lennart Brocki, Neo Christopher Chung

Proceedings of the IEEE International Conference on Big Data and Smart Computing, 2021

2020

Removing Brightness Bias in Rectified Gradients.

Lennart Brocki, Neo Christopher Chung

CoRR, 2020

2019

Concept Saliency Maps to Visualize Relevant Features in Deep Generative Models.

Lennart Brocki, Neo Christopher Chung

Proceedings of the 18th IEEE International Conference On Machine Learning And Applications, 2019