More Like this

1. Equi-explanation Maps: Concise and Informative Global Summary Explanations

   https://doi.org/10.1145/3531146.3533112  

   Chowdhury, Tanya; Rahimi, Razieh; Allan, James (June 2022, Proceedings of the 2022 ACM FAccT* Conference)

   We propose equi-explanation maps to study the variation in model logic across the input space. These global model-agnostic structures partition the hyper-space of explanation features into regions of similar model logic. Equi-explanation maps act as a concise summary of instance explanations and can provide laymen an at-a-glance understanding of the basis on which the classifier makes its decisions. We thus propose the task of generating $$\epsilon$$-equi-explanation maps, a partitioning of the input space into subspaces such that the standard deviation of explanation vectors in a subspace do not exceed $$\epsilon$$. We adapt existing local and subspace explainability techniques like LIME and MUSE to generate equi-explanation maps on two binary classification datasets using four classification models and evaluate the quality of their partitioning. We find that these techniques produce a sub-optimal number of subspaces (making the maps harder to interpret) and have a considerable run time. We then propose E-map, a new divide-and-conquer based algorithm to produce $$\epsilon$$-equi-explanation maps. E-map is able to decrease the number of subspaces (and hence increase interpretability) and running time as compared to the previous systems for a fixed value of $$\epsilon$$. Finally, given a classifier decision boundary, we try to determine what would be an optimal value for the parameter $$\epsilon$$. We believe good explanation representation methods can increase the trustworthiness and understanding of machine learning models for critical real world tasks. 

   more » « less
2. Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace

   https://doi.org/10.1109/WACV57701.2024.00481  

   Hong, Jinyung; Park, Keun Hee; Pavlic, Theodore P (January 2024, IEEE)

   Many interpretable AI approaches have been proposed to provide plausible explanations for a model’s decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less attention. A recently proposed shared global workspace theory showed that networks of distributed modules can benefit from sharing information with a bottle-necked memory because the communication constraints encourage specialization, compositionality, and synchronization among the modules. Inspired by this, we propose Concept-Centric Transformers, a simple yet effective configuration of the shared global workspace for interpretability, consisting of: i) an object-centric-based memory module for extracting semantic concepts from input features, ii) a cross-attention mechanism between the learned concept and input embeddings, and iii) standard classification and explanation losses to allow human analysts to directly assess an explanation for the model’s classification reasoning. We test our approach against other existing concept-based methods on classification tasks for various datasets, including CIFAR100, CUB-200-2011, and ImageNet, and we show that our model achieves better classification accuracy than all baselines across all problems but also generates more consistent concept-based explanations of classification output. 

   more » « less
3. TLSL e AF: automatic leaf angle estimates from single‐scan terrestrial laser scanning

   https://doi.org/10.1111/nph.17548  

   Stovall, Atticus E. L.; Masters, Benjamin; Fatoyinbo, Lola; Yang, Xi (July 2021, New Phytologist)

   Summary Leaf angle distribution (LAD) in forest canopies affects estimates of leaf area, light interception, and global‐scale photosynthesis, but is often simplified to a single theoretical value. Here, we present TLSLeAF (Terrestrial Laser Scanning Leaf Angle Function), an automated open‐source method of deriving LADs from terrestrial laser scanning.TLSLeAF produces canopy‐scale leaf angle and LADs by relying on gridded laser scanning data. The approach increases processing speed, improves angle estimates, and requires minimal user input. Key features are automation, leaf–wood classification, beta parameter output, and implementation in R to increase accessibility for the ecology community.TLSLeAF precisely estimates leaf angle with minimal distance effects on angular estimates while rapidly producing LADs on a consumer‐grade machine. We challenge the popular spherical LAD assumption, showing sensitivity to ecosystem type in plant area index and foliage profile estimates that translate toc. 25% andc. 11% increases in canopy net photosynthesis (c. 25%) and solar‐induced chlorophyll fluorescence (c. 11%).TLSLeAF can now be applied to the vast catalog of laser scanning data already available from ecosystems around the globe. The ease of use will enable widespread adoption of the method outside of remote‐sensing experts, allowing greater accessibility for addressing ecological hypotheses and large‐scale ecosystem modeling efforts. 

   more » « less
4. An Uncertainty Estimation Framework for Risk Assessment in Deep Learning-based Atrial Fibrillation Classification

   Belen, James; Mousavi, Sajad; Shamsoshoara, Alireza; Afghah, Fatemeh (January 2020, IEEE Asilomar Conference on Signals, Systems, and Computers)

   null (Ed.)

   Atrial Fibrillation (AF) is among one of the most common types of heart arrhythmia afflicting more than 3 million people in the U.S. alone. AF is estimated to be the cause of death of 1 in 4 individuals. Recent advancements in Artificial Intelligence (AI) algorithms have led to the capability of reliably detecting AF from ECG signals. While these algorithms can accurately detect AF with high precision, the discrete and deterministic classifications mean that these networks are likely to erroneously classify the given ECG signal. This paper proposes a variational autoencoder classifier network that provides an uncertainty estimation of the network's output in addition to reliable classification accuracy. This framework can increase physicians' trust in using AI-based AF detection algorithms by providing them with a confidence score which reflects how uncertain the algorithm is about a case and recommending them to put more attention to the cases with a lower confidence score. The uncertainty is estimated by conducting multiple passes of the input through the network to build a distribution; the mean of the standard deviations is reported as the network's uncertainty. Our proposed network obtains 97.64% accuracy in addition to reporting the uncertainty. 

   more » « less
5. Reading Detection in Real-time

   Kelton, Conor; Wei, Zijun; Ahn, Seoyoung; Balasubramanian, Aruna; Das, Samir R; Samaras, Dimitris; Zelinsky, Gregory (June 2019, Symposium on Eye Tracking Research And Application)

   Observable reading behavior, the act of moving the eyes over lines of text, is highly stereotyped among the users of a language, and this has led to the development of reading detectors–methods that input windows of sequential fixations and output predictions of the fixation behavior during those windows being reading or skimming. The present study introduces a newmethod for reading detection using Region Ranking SVM (RRSVM). An SVM-based classifier learns the local oculomotor features that are important for real-time reading detection while it is optimizing for the global reading/skimming classification, making it unnecessary to hand-label local fixation windows for model training. This RRSVM reading detector was trained and evaluated using eye movement data collected in a laboratory context, where participants viewed modified web news articles and had to either read them carefully for comprehension or skim them quickly for the selection of keywords (separate groups). Ground truth labels were known at the global level (the instructed reading or skimming task), and obtained at the local level in a separate rating task. The RRSVM reading detector accurately predicted 82.5% of the global (article-level) reading/skimming behavior, with accuracy in predicting local window labels ranging from 72-95%, depending on how tuned the RRSVM was for local and global weights. With this RRSVM reading detector, a method now exists for near real-time reading detection without the need for hand-labeling of local fixation windows. With real-time reading detection capability comes the potential for applications ranging from education and training to intelligent interfaces that learn what a user is likely to know based on previous detection of their reading behavior. 

   more » « less