检索结果-内蒙古大学图书馆

Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kao, Po-Yu Yang, Ya-Chu Chiang, Wei-Yin Hsiao, Jen-Yueh Cao, Yudong Aliper, Alex Ren, Feng Aspuru-Guzik, Alán Zhavoronkov, Alex Hsieh, Min-Hsiu Lin, Yen-Chu Insilico Medicine Taiwan Ltd. Taipei Taiwan Research Institute Taipei Taiwan Zapata Computing Inc. BostonMA United States Insilico Medicine AI Limited Masdar City Abu Dhabi United Arab Emirates Insilico Medicine Shanghai Ltd. Shanghai China Department of Chemistry University of Toronto Toronto Canada Department of Computer Science University of Toronto Toronto Canada Vector Institute for Artificial Intelligence Toronto Canada Canadian Institute for Advanced Research Toronto Canada Insilico Medicine Hong Kong Ltd. Hong Kong Department of Pharmacy National Yang Ming Chiao Tung University Taipei Taiwan

De novo drug design with desired biological activities is crucial for developing novel therapeutics for patients. The drug development process is time and resource-consuming, and it has a low probability of success. Recent advances in machine learning and deep learning technology have reduced the time and cost of the discovery process and therefore, improved pharmaceutical research and development. In this paper, we explore the combination of two rapidly-developing fields with lead candidate discovery in the drug development process. First, Artificial intelligence has already been demonstrated to successfully accelerate conventional drug design approaches. Second, quantum computing has demonstrated promising potential in different applications, such as quantum chemistry, combinatorial optimizations, and machine learning. This manuscript explores hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. We substituted each element of GAN with a variational quantum circuit (VQC) and demonstrated the quantum advantages in the small drug discovery. Utilizing a VQC in the noise generator of a GAN to generate small molecules achieves better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart. Moreover, we demonstrate the potential of a VQC with only tens of learnable parameters in the generator of GAN to generate small molecules. We also demonstrate the quantum advantage of a VQC in the discriminator of GAN. In this hybrid model, the number of learnable parameters is significantly less than the classical ones, and it can still generate valid molecules. The hybrid model with only tens of training parameters in the quantum discriminator outperforms the MLP-based one in terms of both generated molecule properties and the achieved KL divergence. © 2022, CC BY-NC-ND.

关键词： Generative adversarial networks

Buzzer Detection to Maintain Information Neutrality in 2019 Indonesia Presidential Election 8

学校读者我要写书评

暂无评论

Buzzer Detection to Maintain Information Neutrality in 2019 ...

8th IIAI International Congress on advanced Applied Informatics, IIAI-AAI 2019

作者： Panatra, Adrian Julianto Chandra, Felisitus Bryan Darmawan, Wiliam Warnars, Harco Leslie Hendric Spits Utomo, Wiranto Herry Matsuo, Tokuro Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Faculty of Computing President University Jawa Barat17550 Indonesia Graduate School of Industrial Technology Advanced Institute of Industrial Technology Tokyo Japan

ISBN: (纸本)9781728126272

This paper proposed a method which detects a political buzzer in social media, specifically Instagram. With Indonesia undergoing 2019 presidential election, a detection of buzzers that causes much trouble in maintaining information neutrality is seen as a needed. One of the many reasons is because those buzzers spread false news making the information gained by the use of social media to be not neutral and deliberately offends or attack those that they are not in favor of. Those buzzers share a similar characteristic, tendency, or even possess the same pattern. Grouping, classification, and detection method are used to counter this problem. This research gives a slight overview of what is happening in social media and a theory of how to deal with those problems. The argument is expected to help to identify buzzer in real life, thus helps in maintaining information neutrality along with the social media in Indonesia. © 2019 IEEE.

关键词： Social networking (online)

Topic specificity: A descriptive metric for algorithm selection and finding the right number of topics

学校读者我要写书评

暂无评论

Natural Language Processing Journal

Natural Language Processing Journal 2024年 8卷

作者： Emil Rijcken Kalliopi Zervanou Pablo Mosteiro Floortje Scheepers Marco Spruit Uzay Kaymak Jheronimus Academy of Data Science Eindhoven University of Technology ’s Hertogenbosch The Netherlands Department of Information and Computing Sciences Utrecht University Utrecht The Netherlands Department of Methodology and Statistics Utrecht University Utrecht The Netherlands Psychiatry University Medical Center Utrecht Utrecht The Netherlands Leiden Institute of Advanced Computer Science Leiden The Netherlands Public Health & Primary Care Leiden University Medical Center Leiden The Netherlands

Topic modeling is a prevalent task for discovering the latent structure of a corpus, identifying a set of topics that represent the underlying themes of the documents. Despite its popularity, issues with its evaluation metric, the coherence score, result in two common challenges: algorithm selection and determining the number of topics . To address these two issues, we propose the topic specificity metric, which captures the relative frequency of topic words in the corpus and is used as a proxy for the specificity of a word. In this work, we formulate the metric firstly. Secondly, we demonstrate that algorithms train topics at different specificity levels. This insight can be used to address algorithm selection as it allows users to distinguish and select algorithms with the desired specificity level. Lastly, we show a strictly positive monotonic correlation between the topic specificity and the number of topics for LDA, FLSA-W, NMF and LSI. This correlation can be used to address the selection of the number of topics, as it allows users to adjust the number of topics to their desired level. Moreover, our descriptive metric provides a new perspective to characterize topic models, allowing them to be understood better.

关键词： Topic modeling Metric Algorithm selection

LOCUS: A multi-robot loss-tolerant algorithm for surveying volcanic plumes

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ericksen, John Aggarwal, Abhinav Fricke, G. Matthew Moses, Melanie E. Department of Computer Science Center for Advanced Research Computing United States Department of Biology University of New Mexico AlbuquerqueNM United States Santa Fe Institute Santa FeNM United States

Measurement of volcanic CO2 flux by a drone swarm poses special challenges. Drones must be able to follow gas concentration gradients while tolerating frequent drone loss. We present the LoCUSalgorithm as a solution to this problem and prove its robustness. LoCUS relies on swarm coordination and self-healing to solve the task. As a point of contrast we also implement the MoBSalgorithm, derived from previously published work, which allows drones to solve the task independently. We compare the effectiveness of these algorithms using drone simulations, and find that LoCUS provides a reliable and efficient solution to the volcano survey problem. Further, the novel data-structures and algorithms underpinning LoCUS have application in other areas of fault-tolerant algorithm research. Copyright © 2020, The Authors. All rights reserved.

关键词： Fault tolerance

A composite measurement scheme for efficient quantum observable estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zi-Jian Nakaji, Kouhei Choi, Matthew Aspuru-Guzik, Alán Department of Computer Science University of Toronto TorontoONM5S 2E4 Canada Vector Institute for Artificial Intelligence TorontoONM5S 1M1 Canada Department of Chemistry University of Toronto TorontoONM5G 1Z8 Canada 1-1-1 Umezono Ibaraki Tsukuba305-8568 Japan Quantum Computing Center Keio University 3-14-1 Hiyoshi Kohoku-ku Kanagawa Yokohama223-8522 Japan Department of Materials Science & Engineering University of Toronto TorontoONM5S 3E4 Canada Department of Chemical Engineering & Applied Chemistry University of Toronto TorontoONM5S 3E5 Canada Canadian Institute for Advanced Research TorontoONM5G 1Z8 Canada

Estimation of the expectation value of observables is a key subroutine in quantum computing and is also the bottleneck of the performance of many near-term quantum algorithms. Many works have been proposed to reduce the number of measurements needed for this task and they provide different measurement schemes for generating the measurements to perform. In this paper, we propose a new approach, composite measurement scheme, which composes multiple measurement schemes by distributing shots to them with a trainable ratio. As an example of our method, we study the case where only Pauli measurements are allowed and propose Composite-LBCS (C-LBCS), a composite measurement scheme made by composing locally-biased classical shadows. We numerically demonstrate C-LBCS on molecular systems up to CO2 (30 qubits) and show that C-LBCS outperforms the previous state-of-the-art methods despite its simplicity. We also show that C-LBCS can be efficiently optimized by stochastic gradient descent and is trainable even when the observable contains a large number of terms. We believe our method opens up a reliable way toward efficient observable estimation on large quantum systems. © 2023, CC BY-NC-SA.

关键词： Stochastic systems

Symmetries, graph properties, and quantum speedups

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ben-David, Shalev Childs, Andrew M. Gilyén, András Kretschmer, William Podder, Supartha Wang, Daochen Cheriton School of Computer Science University of Waterloo Canada Department of Computer Science Institute for Advanced Computer Studies University of Maryland United States Joint Center for Quantum Information and Computer Science University of Maryland United States Institute for Quantum Information and Matter California Institute of Technology United States Simons Institute for the Theory of Computing University of California Berkeley United States Department of Computer Science University of Texas Austin United States Department of Mathematics and Statistics University of Ottawa Canada Department of Mathematics University of Maryland United States

Aaronson and Ambainis (2009) and Chailloux (2018) showed that fully symmetric (partial) functions do not admit exponential quantum query speedups. This raises a natural question: how symmetric must a function be before it cannot exhibit a large quantum speedup? In this work, we prove that hypergraph symmetries in the adjacency matrix model allow at most a polynomial separation between randomized and quantum query complexities. We also show that, remarkably, permutation groups constructed out of these symmetries are essentially the only permutation groups that prevent super-polynomial quantum speedups. We prove this by fully characterizing the primitive permutation groups that allow super-polynomial quantum speedups. In contrast, in the adjacency list model for bounded-degree graphs-where graph symmetry is manifested differently-we exhibit a property testing problem that shows an exponential quantum speedup. These results resolve open questions posed by Ambainis, Childs, and Liu (2010) and Montanaro and de Wolf (2013). Copyright © 2020, The Authors. All rights reserved.

关键词： Group theory

Multitask Deep Learning for Accurate Risk Stratification and Prediction of Next Steps for Coronary Ct Angiography Patients

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Lu, Juan Bennamoun, Mohammed Stewart, Jonathon Eshraghian, Jason K. Liu, Yanbin Chow, Benjamin Sanfilippo, Frank M. Dwivedi, Girish Medical School The University of Western Australia 35 Stirling Highway NedlandsWA6009 Australia School of Computer Science The University of Western Australia 35 Stirling Highway NedlandsWA6009 Australia Harry Perkins Institute of Medical Research 5 Robin Warren Dr MurdochWA6150 Australia Department of Electrical and Computer Engineering University of California 1156 High Street Santa CruzCA95064 United States School of Computing Australian National University Australian Capital Territory Canberra2601 Australia Division of Cardiology Departments of Medicine University of Ottawa Heart Institute 40 Ruskin Street OttawaONK1Y 4W7 Canada School of Population and Global Health The University of Western Australia 35 Stirling Highway NedlandsWA6009 Australia Department of Advanced Clinical and Translational Cardiovascular Imaging

Diagnostic investigation has an important role in risk stratification and clinical decision making of patients with suspected and documented coronary artery disease (CAD). However, the majority of existing tools are primarily focused on the selection of gatekeeper tests, whereas only a handful of systems contain information regarding the downstream testing or treatment. We propose a multi-task deep learning model to support risk stratification and down-stream test selection for patients undergoing coronary computed tomography angiography (CCTA). The analysis included 14,021 patients who underwent CCTA between 2006 and 2017. Our novel multitask deep learning framework (TabPerceiver) extends the state-of-the-art Perceiver model to deal with real-world patient information and their CCTA report data. Despite significant progress using deep learning models for tabular data, they rarely outperform gradient boosting decision trees (GBDT). Our multi-task TabPerceiver model achieved an area under the receiver operating characteristic curve (AUC) of 0.752 (low), 0.629 (medium), and 0.765 (high) in CAD risk stratification, and 0.730 in predicting downstream tests, which has outperformed the benchmark GBDT (low: 0.733, medium: 0.610, high: 0.719, downstream test: 0.741).To the best of our knowledge, our multi-task TabPerceiver model is the first cross-attention based deep learning model processing tabular data, it accurately estimates the patients’ risk of CAD and provides recommended downstream tests based on prior CCTA information. In clinical practice, the utilization of such an approach could bring a paradigm shift in risk stratification and downstream management. Our study also shows that neural networks appear to benefit more readily from multi-task learning than tree-based models. This could offset the shortcomings of using single-task deep learning approach when working with tabular data. © 2023, The Authors. All rights reserved.

关键词： Decision trees

International AI Safety Report

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Bengio, Yoshua Mindermann, Sören Privitera, Daniel Besiroglu, Tamay Bommasani, Rishi Casper, Stephen Choi, Yejin Fox, Philip Garfinkel, Ben Goldfarb, Danielle Heidari, Hoda Ho, Anson Kapoor, Sayash Khalatbari, Leila Longpre, Shayne Manning, Sam Mavroudis, Vasilios Mazeika, Mantas Michael, Julian Newman, Jessica Ng, Kwan Yee Okolo, Chinasa T. Raji, Deborah Sastry, Girish Seger, Elizabeth Skeadas, Theodora South, Tobin Strubell, Emma Tramèr, Florian Velasco, Lucia Wheeler, Nicole Acemoglu, Daron Adekanmbi, Olubayo Dalrymple, David Dietterich, Thomas G. Felten, Edward W. Fung, Pascale Gourinchas, Pierre-Olivier Heintz, Fredrik Hinton, Geoffrey Jennings, Nick Krause, Andreas Leavy, Susan Liang, Percy Ludermir, Teresa Marda, Vidushi Margetts, Helen McDermid, John Munga, Jane Narayanan, Arvind Nelson, Alondra Neppel, Clara Oh, Alice Ramchurn, Gopal Russell, Stuart Schaake, Marietje Schölkopf, Bernhard Song, Dawn Soto, Alvaro Tiedrich, Lee Varoquaux, Gaël Yao, Andrew Zhang, Ya-Qin Université de Montréal Mila - Quebec AI Institute Canada Epoch AI United States KIRA Center Mila Quebec AI Institute Canada Stanford University United States Massachusetts Institute of Technology United States University of Oxford United Kingdom Carnegie Mellon University United States Princeton University United States Hong Kong University of Science and Technology Hong Kong Centre for the Governance of AI United Kingdom The Alan Turing Institute United Kingdom University of Illinois at Urbana-Champaign United States New York University United States University of California Berkeley United States Concordia AI China Brookings Institution United States Demos United Kingdom Humane Intelligence ETH Zurich Switzerland Maastricht University Netherlands University of Birmingham United Kingdom Advanced Research Invention Agency United Kingdom Oregon State University United States Research Department International Monetary Fund United States Linköping University Sweden University of Toronto Canada University of Loughborough United Kingdom University College Dublin Ireland Federal University of Pernambuco Brazil AI Collaborative University of York United Kingdom Carnegie Endowment for International Peace United States Institute for Advanced Study KAIST School of Computing Korea Republic of ELLIS Institute Tübingen Germany Pontificia Universidad Católica de Chile Chile Duke University United States Inria France Institute for Interdisciplinary Information Sciences Tsinghua University China Tsinghua University China

The first International AI Safety Report comprehensively synthesizes thecurrent evidence on the capabilities, risks, and safety of advanced AI *** report was mandated by the nations attending the AI Safety Summit inBletchley, UK. Thirty nations, the UN, the OECD, and the EU each nominated arepresentative to the report\'s Expert Advisory Panel. A total of 100 AI expertscontributed, representing diverse perspectives and disciplines. Led by thereport\'s Chair, these independent experts collectively had full discretion overthe report\'s content. © 2025, CC BY.

关键词： Safety engineering

Gate-Tunable Multi-Band van der Waals Photodetector and Polarization Sensor

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shen, Daozhi Yang, HeeBong Patel, Tarun Rhodes, Daniel A. Timusk, Thomas Zhou, Y. Norman Kim, Na Young Tsen, Adam W. School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China Institute for Quantum Computing University of Waterloo WaterlooONN2L 3G1 Canada Department of Chemistry University of Waterloo WaterlooONN2L 3G1 Canada Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Physics and Astronomy University of Waterloo WaterlooONN2L 3G1 Canada Department of Materials Science and Engineering University of Wisconsin-Madison WI United States Department of Physics and Astronomy McMaster University HamiltonONL8S 4M1 Canada Centre for Advanced Materials Joining Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Waterloo Institute for Nanotechnology University of Waterloo WaterlooONN2L 3G1 Canada

A single photodetector with tunable detection wavelengths and polarization sensitivity can potentially be harnessed for diverse optical applications ranging from imaging and sensing to telecommunications. Such a device will require the combination of multiple material systems with different structures, bandgaps, and photoelectrical responses, which is extremely difficult to engineer using traditional epitaxial films. Here, we develop a multi-functional and high-performance photosensor using all van der Waals materials. The device features a gate-tunable spectral response that is switchable between near-infrared/visible and short-/mid-wave infrared, as well as broadband operation, at room temperature. The linear polarization sensitivity in the telecommunications O-band can also be directly modulated between horizontal, vertical, and nonpolarizing modes. These effects originate from the balance of photocurrent generation in two of the active layers that can be manipulated by an electric field. The photodetector features high detectivity (>109 cmHz1/2W-1) together with fast operation speed (~ 1 MHz) and can be further exploited for dual visible and infrared imaging. Copyright © 2024, The Authors. All rights reserved.

关键词： Photodetectors