Search Results for author:
Found 16 papers, 4 papers with code
Efficient Representation of the Activation Space in Deep Neural Networks
The representations of the activation space of deep neural networks (DNNs) are widely utilized for tasks like natural language processing, anomaly detection and speech recognition.
Weakly Supervised Detection of Hallucinations in LLM Activations
We introduce a weakly supervised auditing technique using a subset scanning approach to detect anomalous patterns in LLM activations from pre-trained models.
Revisiting Skin Tone Fairness in Dermatological Lesion Classification
Addressing fairness in lesion classification from dermatological images is crucial due to variations in how skin diseases manifest across skin tones.
FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare
This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare.
Domain-agnostic and Multi-level Evaluation of Generative Models
To this end, we propose a framework for Multi-level Performance Evaluation of Generative mOdels (MPEGO), which could be employed across different domains.
Model-free feature selection to facilitate automatic discovery of divergent subgroups in tabular data
Existing feature selection techniques for tabular data often involve fitting a particular model in order to select important features.
Towards Creativity Characterization of Generative Models via Group-based Subset Scanning
We propose group-based subset scanning to identify, quantify, and characterize creative processes by detecting a subset of anomalous node-activations in the hidden layers of the generative models.
Pattern Detection in the Activation Space for Identifying Synthesized Content
Generative Adversarial Networks (GANs) have recently achieved unprecedented success in photo-realistic image synthesis from low-dimensional random noise.
Out-of-Distribution Detection in Dermatology using Input Perturbation and Subset Scanning
Current skin disease models could make incorrect inferences for test samples from different hardware devices and clinical settings or unknown disease samples, which are out-of-distribution (OOD) from the training samples.
Towards creativity characterization of generative models via group-based subset scanning
We propose group-based subset scanning to quantify, detect, and characterize creative processes by detecting a subset of anomalous node-activations in the hidden layers of generative models.
Prediction of neonatal mortality in Sub-Saharan African countries using data-level linkage of multiple surveys
Existing datasets available to address crucial problems, such as child mortality and family planning discontinuation in developing countries, are not ample for data-driven approaches.
Identifying Audio Adversarial Examples via Anomalous Pattern Detection
Audio processing models based on deep neural networks are susceptible to adversarial attacks even when the adversarial audio waveform is 99. 9% similar to a benign sample.
Deep Mining: Detecting Anomalous Patterns in Neural Network Activations with Subset Scanning
This work introduces ``Subset Scanning methods from the anomalous pattern detection domain to the task of detecting anomalous inputs to neural networks.
Analyzing Bias in Sensitive Personal Information Used to Train Financial Models
Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models.
Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
We find that the majority of the data in the the two datasets have ITA values between 34. 5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets.
Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models
With the intention to create an enhanced visual explanation in terms of visual sharpness, object localization and explaining multiple occurrences of objects in a single image, we present Smooth Grad-CAM++ \footnote{Simple demo: http://35. 238. 22. 135:5000/}, a technique that combines methods from two other recent techniques---SMOOTHGRAD and Grad-CAM++.
