Search Results for author:
Found 11 papers, 3 papers with code
False Sense of Security in Explainable Artificial Intelligence (XAI)
"Explainability" has multiple meanings which are often used interchangeably, and there are an even greater number of XAI methods - none of which presents a clear edge.
Class-Discriminative Attention Maps for Vision Transformers
We introduce class-discriminative attention maps (CDAM), a novel post-hoc explanation method that is highly sensitive to the target class.
Challenges of Large Language Models for Mental Health Counseling
The global mental health crisis is looming with a rapid increase in mental disorders, limited resources, and the social stigma of seeking treatment.
Integration of Radiomics and Tumor Biomarkers in Interpretable Machine Learning Models
Therefore, we study and propose the integration of expert-derived radiomics and DNN-predicted biomarkers in interpretable classifiers which we call ConRad, for computerized tomography (CT) scans of lung cancer.
Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks
However, the change in the prediction outcome may stem from perturbation artifacts, since perturbed samples in the test dataset are out of distribution (OOD) compared to the training dataset and can therefore potentially disturb the model in an unexpected manner.
Deep Learning Mental Health Dialogue System
The system consists of a core generative model and post-processing algorithms.
Evaluation of importance estimators in deep learning classifiers for Computed Tomography
Interestingly, there was a critical discrepancy between model-centric (fidelity) and human-centric (ROC and DSC) evaluation.
Fidelity of Interpretability Methods and Perturbation Artifacts in Neural Networks
Despite excellent performance of deep neural networks (DNNs) in image classification, detection, and prediction, characterizing how DNNs make a given decision remains an open problem, resulting in a number of interpretability methods.
Human in the Loop for Machine Creativity
Overall, these HITL approaches will increase interaction between human and AI, and thus help the future AI systems to better understand our own creative and emotional processes.
Input Bias in Rectified Gradients and Modified Saliency Maps
In particular, gradients of classes or concepts with respect to the input features (e. g., pixels in images) are often used as importance scores or estimators, which are visualized in saliency maps.
Concept Saliency Maps to Visualize Relevant Features in Deep Generative Models
Evaluating, explaining, and visualizing high-level concepts in generative models, such as variational autoencoders (VAEs), is challenging in part due to a lack of known prediction classes that are required to generate saliency maps in supervised learning.
