An official website of the United States government
Convolutional Neural Network (CNN) uses convolutional layers to explore spatial/temporal adjacency to construct new feature representations. So, CNN is commonly used for data with strong temporal/spatial correlations, but cannot be directly applied to generic learning tasks. In this paper, we propose to enable CNN for learning from generic data to improve classification accuracy. To take the full advantage of CNN’s feature learning power, we propose to convert each instance of the original dataset into a synthetic matrix/image format. To maximize the correlation in the constructed matrix/image, we use 0/1 optimization to reorder features and ensure that the ones with strong correlations are adjacent to each other. By using a feature reordering matrix, we are able to create a synthetic image to represent each instance. Because the constructed synthetic image preserves the original feature values and correlation, CNN can be applied to learn effective features for classification. Experiments and comparisons, on 22 benchmark datasets, demonstrate clear performance gain of applying CNN to generic datasets, compared to conventional machine learning methods. Furthermore, our method consistently outperforms approaches which directly apply CNN to generic datasets in naive ways. This research allows deep learning to be broadly applied to generic datasets.
more »
« less
TOM Toolkit Swift Module
A TOM Toolkit plugin module designed to enable users to submit requests for Target-Of-Opportunity observations to the Neil Gehrel's Swift Space Telescope.
more »
« less
- Award ID(s):
- 2209852
- PAR ID:
- 10536015
- Publisher / Repository:
- Zenodo
- Date Published:
- Edition / Version:
- 0.2.2
- Format(s):
- Medium: X
- Right(s):
- Creative Commons Attribution 4.0 International
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Unhelkar, Vaibhav (Ed.)The need to train new workers effectively and upskill the existing workforce is a challenge faced by almost every industry across the globe. The healthcare industry, in particular, is confronting a crisis. The World Health Organization (WHO) projects a shortage of 10 million healthcare workers by 2030. However, according to the Future of Jobs Report by the World Economic Forum, only half of the workers have access to training and learning opportunities. To sustain a resilient workforce and to protect the health of the world’s population, my thesis looks at using AI and robots to accelerate human learners’ acquisition of workforce skills. Specifically, I develop novel Explainable AI (XAI) algorithms to automate training to enable workers to collaborate with autonomous robots - a trend that is fast-growing. I also use statistical models to model human learner cognitive processes to create Human-Robot Interaction (HRI) systems to generate effective instructions tailored to individual learners. In addition to driving technical advances, my research is having a positive societal impact. I collaborate with Houston Methodist Hospital to create a first-of-its-kind robotic tutor for clinical nursing education to reduce healthcare-associated infections.more » « less
-
Mitigating damages due to a cyber attack in industrial plants relies upon timely triage of early physical process symptoms. This aims to connect process symptoms to a potential control host intrusion. Unfortunately, due to the semantic gap between host and process behavior, operators must manually and painstakingly iterate between diverse control host and process forensic logs. This slows down their response, is error-prone, and may lead to further damage. We present PhyLink, a post-mortem technique to automatically connect process symptoms to control host intrusion, allowing operators to respond to confirmed attacks and stop damages. PhyLink uses physical evidence (e.g., device symptom location) to guide a symbolic binary exploration of the control host execution context (from memory snapshots). Learning from past control host attacks, PhyLink develops a generic approach to not only link host intrusion vectors to process symptoms, but ranks them by their likelihood to cause damages. This helps operators prioritize their response (e.g., which symptoms to respond to). Using 1219 real-world control host snapshots, we evaluated PhyLink against past attacks, and adaptive attacks to evade PhyLink. We show that PhyLink is robust in triaging control host-originated process attacks.more » « less
-
The ability to exert self-control varies within and across taxa. Some species can exert self-control for several seconds whereas others, such as large-brained vertebrates, can tolerate delays of up to several minutes. Advanced self-control has been linked to better performance in cognitive tasks and has been hypothesized to evolve in response to specific socio-ecological pressures. These pressures are difficult to uncouple because previously studied species face similar socio-ecological challenges. Here, we investigate self-control and learning performance in cuttlefish, an invertebrate that is thought to have evolved under partially different pressures to previously studied vertebrates. To test self-control, cuttlefish were presented with a delay maintenance task, which measures an individual's ability to forgo immediate gratification and sustain a delay for a better but delayed reward. Cuttlefish maintained delay durations for up to 50–130 s. To test learning performance, we used a reversal-learning task, whereby cuttlefish were required to learn to associate the reward with one of two stimuli and then subsequently learn to associate the reward with the alternative stimulus. Cuttlefish that delayed gratification for longer had better learning performance. Our results demonstrate that cuttlefish can tolerate delays to obtain food of higher quality comparable to that of some large-brained vertebrates.more » « less
-
The dataset includes the measurements of individual subduction zones defined in the convergence-parallel, trench-perpendicular, and spreading-parallel direction. </p> </p> Table S3. Location of each trench, arc, and back-arc defined in a direction parallel to the convergence, and the corresponding distance from the trench to the arc (D_TA), subarc slab depth (H), and from the trench to the back-arc spreading center (D_TB). The slab dip is measured at 50km (Dip50), 100km (Dip100), and 200km (Dip200) and averaged from 0 to 50 km (Dip050), 0 to 100km (Dip0100), 0 to 200km (Dip0200), and 50 to 200km (Dip50200). </p> Table S4. Location of each trench, arc, and back-arc defined in a direction perpendicular to the trench, and the corresponding distance from the trench to the arc (D_TA), subarc slab depth (H), and from the trench to the back-arc spreading center (D_TB). The slab dip is measured at 50km (Dip50), 100km (Dip100), and 200km (Dip200) and averaged from 0 to 50 km (Dip050), 0 to 100km (Dip0100), 0 to 200km (Dip0200), and 50 to 200km (Dip50200). </p> Table S5. Location of each trench, arc, and back-arc defined in a direction parallel to the spreading direction, and the corresponding distance from the trench to the arc (D_TA), subarc slab depth (H), and from the trench to the back-arc spreading center (D_TB). The slab dip is measured at 50km (Dip50), 100km (Dip100), and 200km (Dip200) and averaged from 0 to 50 km (Dip050), 0 to 100km (Dip0100), 0 to 200km (Dip0200), and 50 to 200km (Dip50200). </p> </p>more » « less
