Virtual laboratories that enable novice scientists to construct, evaluate and revise models of complex systems heavily involve parameter estimation tasks. We seek to understand novice strategies for parameter estimati...
详细信息
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ...
详细信息
As AI technologies increasingly integrate into daily life, their deployment often overlooks the complexities of the communities they aim to serve. This gap is particularly acute for marginalized communities, where AI ...
详细信息
The integration of edge computing with deep neural networks (DNNs) is crucial for intelligent industrial cyber-physical systems. Typically, deploying DNNs on heterogeneous edge devices relies on methods like model com...
详细信息
Accurate weather forecasting is essential for sectors like agriculture, aviation, and disaster management. However, deep learning algorithms face challenges in prediction accuracy due to issues like vanishing gradient...
详细信息
ISBN:
(数字)9798331505264
ISBN:
(纸本)9798331505271
Accurate weather forecasting is essential for sectors like agriculture, aviation, and disaster management. However, deep learning algorithms face challenges in prediction accuracy due to issues like vanishing gradients, overfitting, and high computational demands. This research proposes a novel U-Net based architecture utilizing a Convolutional Neural Network (CNN) bottleneck layer to improve weather forecasting. Key features include a skip-connection mechanism, modified weight update rules, Gaussian-mutation operations, and the Adam optimizer for enhanced feature extraction and faster, more accurate predictions. The model was tested using precipitation data from Doppler Weather Radar (DWR) Chennai Radar and weather parameters from European Centre for Medium-Range Weather Forecasts (ECMWF). A dedicated GeoServer facilitates realtime data processing. Experimental results show the proposed algorithm achieves 97.5% accuracy, outperforming CNN and long short-term memory (LSTM) models by 5.84% and 2.41%, respectively.
Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obt...
详细信息
ISBN:
(纸本)9781450380966
Root cause analysis is a common data analysis task. While question-answering systems enable people to easily articulate a why question (e.g., why students in Massachusetts have high ACT Math scores on average) and obtain an answer, these systems often produce questionable causal claims. To investigate how such claims might mislead users, we conducted two crowdsourced experiments to study the impact of showing different information on user perceptions of a question-answering system. We found that in a system that occasionally provided unreasonable responses, showing a scatterplot increased the plausibility of unreasonable causal claims. Also, simply warning participants that correlation is not causation seemed to lead participants to accept reasonable causal claims more cautiously. We observed a strong tendency among participants to associate correlation with causation. Yet, the warning appeared to reduce the tendency. Grounded in the findings, we propose ways to reduce the illusion of causality when using question-answering systems.
How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and ...
ISBN:
(纸本)9798331314385
How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.
An important task in NLP applications such as sentence simplification is the ability to take a long, complex sentence and split it into shorter sentences, rephrasing as necessary. We introduce a novel dataset and a ne...
Identifying predictive covariates, which forecast individual treatment effectiveness, is crucial for decision-making across different disciplines such as personalized medicine. These covariates, referred to as biomark...
详细信息
暂无评论