检索结果-内蒙古大学图书馆

ABIDES: Towards High-Fidelity Multi-Agent Market Simulation 20

学校读者我要写书评

暂无评论

ABIDES: Towards High-Fidelity Multi-Agent Market Simulation

2020 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, SIGSIM-PADS 2020

作者： Byrd, David Hybinette, Maria Balch, Tucker Hybinette School of Interactive Computing Georgia Institute of Technology Atlanta United States Department of Computer Science University of Georgia Athens United States J.P. Morgan AI Research New York United States

ISBN: (纸本)9781450375924

We introduce ABIDES, an open source Agent-Based interactive Discrete Event Simulation environment. ABIDES is designed from the ground up to support agent-based research in market applications. While proprietary simulations are available within trading firms, there are no broadly available high-fidelity market simulation environments. ABIDES enables the simulation of tens of thousands of trading agents interacting with an exchange agent to facilitate transactions. It supports configurable pairwise noisy network latency between each individual agent as well as the exchange. Our simulator's message-based design is modeled after NASDAQ's published equity trading protocols ITCH and OUCH. We introduce the design of the simulator and illustrate its use and configuration with sample code, validating the environment with example trading scenarios. The utility of ABIDES for financial research is illustrated through experiments to develop a market impact model. The core of ABIDES is a general-purpose discrete event simulation, and we demonstrate its breadth of application with a non-finance work-in-progress simulating secure multiparty federated learning. We close with discussion of additional experimental problems it can be, or is being, used to explore, such as the development of machine learning trading algorithms. We hope that the availability of such a platform will facilitate research in this important area. © 2020 Association for computing Machinery.

关键词： Discrete event simulation

Learning to look inside: Augmenting token-based encoders with character-level information

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Pinter, Yuval Dredze, Mark Stent, Amanda Eisenstein, Jacob School of Interactive Computing Georgia Institute of Technology AtlantaGA United States Bloomberg Department of Computer Science Johns Hopkins University Bloomberg New YorkNY United States Google Research

Commonly-used transformer language models depend on a tokenization schema which sets an unchangeable subword vocabulary prior to pre-training, destined to be applied to all downstream tasks regardless of domain shift, novel word formations, or other sources of vocabulary mismatch. Recent work has shown that "token-free" models can be trained directly on characters or bytes, but training these models from scratch requires substantial computational resources, and this implies discarding the many domain-specific models that were trained on tokens. In this paper, we present XRAYEMB, a method for retrofitting existing token-based models with character-level information. XRAYEMB is composed of a character-level "encoder" that computes vector representations of character sequences, and a generative component that decodes from the internal representation to a character sequence. We show that incorporating XRAYEMB's learned vectors into sequences of pre-trained token embeddings helps performance on both autoregressive and masked pre-trained transformer architectures and on both sequence-level and sequence tagging tasks, particularly on nonstandard English text. © 2021, CC BY-SA.

关键词： Signal encoding

Reframing Human-AI Collaboration for Generating Free-Text Explanations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wiegreffe, Sarah Hessel, Jack Swayamdipta, Swabha Riedl, Mark Choi, Yejin School of Interactive Computing Georgia Institute of Technology United States Allen Institute for Artificial Intelligence United States Paul G. Allen School of Computer Science and Engineering University of Washington United States

Large language models are increasingly capable of generating fluent-appearing text with relatively little task-specific supervision. But can these models accurately explain classification decisions? We consider the task of generating free-text explanations using human-written examples in a few-shot manner. We find that (1) authoring higher quality prompts results in higher quality generations;and (2) surprisingly, in a head-to-head comparison, crowdworkers often prefer explanations generated by GPT-3 to crowdsourced explanations in existing datasets. Our human studies also show, however, that while models often produce factual, grammatical, and sufficient explanations, they have room to improve along axes such as providing novel information and supporting the label. We create a pipeline that combines GPT-3 with a supervised filter that incorporates binary acceptability judgments from humans in the loop. Despite the intrinsic subjectivity of acceptability judgments, we demonstrate that acceptability is partially correlated with various fine-grained attributes of explanations. Our approach is able to consistently filter GPT-3-generated explanations deemed acceptable by humans. Copyright © 2021, The Authors. All rights reserved.

关键词：

Confidence intervals uncovered: Are we ready for real-world medical imaging AI?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Christodoulou, Evangelia Reinke, Annika Houhou, Rola Kalinowski, Piotr Erkan, Selen Sudre, Carole H. Burgos, Ninon Boutaj, Sofiène Loizillon, Sophie Solal, Maëlys Rieke, Nicola Cheplygina, Veronika Antonelli, Michela Mayer, Leon D. Tizabi, Minu D. Jorge Cardoso, M. Simpson, Amber Jäger, Paul F. Kopp-Schneider, Annette Varoquaux, Gaël Colliot, Olivier Maier-Hein, Lena Heidelberg Div. Intelligent Medical Systems Germany AI Health Innovation Cluster Germany NCT Heidelberg a partnership between DKFZ Heidelberg University Hospital Germany DKFZ Heidelberg Helmholtz Imaging Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Germany DKFZ Heidelberg Interactive Machine Learning Group Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London United Kingdom Sorbonne Université Institut du Cerveau - Paris Brain Institute - ICM CNRS Inria Inserm AP-HP Hôpital de la Pitié-Salpêtrière France NVIDIA Germany Department of Computer Science IT University of Copenhagen Denmark Centre for Medical Image Computing University College London United Kingdom School of Computing Queen’s University Canada Department of Biomedical and Molecular Sciences Queen’s University Canada Division of Biostatistics DKFZ Germany Parietal project team INRIA Saclay-Île de France France Faculty of Mathematics and Computer Science Heidelberg University Germany Medical Faculty Heidelberg University Germany

Medical imaging is spearheading the AI transformation of healthcare. Performance reporting is key to determine which methods should be translated into clinical practice. Frequently, broad conclusions are simply derived from mean performance values. In this paper, we argue that this common practice is often a misleading simplification as it ignores performance variability. Our contribution is threefold. (1) Analyzing all MICCAI segmentation papers (n = 221) published in 2023, we first observe that more than 50% of papers do not assess performance variability at all. Moreover, only one (0.5%) paper reported confidence intervals (CIs) for model performance. (2) To address the reporting bottleneck, we show that the unreported standard deviation (SD) in segmentation papers can be approximated by a second-order polynomial function of the mean Dice similarity coefficient (DSC). Based on external validation data from 56 previous MICCAI challenges, we demonstrate that this approximation can accurately reconstruct the CI of a method using information provided in publications. (3) Finally, we reconstructed 95% CIs around the mean DSC of MICCAI 2023 segmentation papers. The median CI width was 0.03 which is three times larger than the median performance gap between the first and second ranked method. For more than 60% of papers, the mean performance of the second-ranked method was within the CI of the first-ranked method. We conclude that current publications typically do not provide sufficient evidence to support which models could potentially be translated into clinical practice. © 2024, CC BY.

关键词： Medical imaging

Efficient and scalable masked word prediction using concept formation

学校读者我要写书评

暂无评论

Cognitive Systems Research 2025年 92卷

作者： Xin Lian Zekun Wang Christopher J. MacLellan Department of Computer Science McCormick School of Engineering and Applied Science Northwestern University 2233 Tech Dr 3rd Floor Evanston 60208 IL United States School of Interactive Computing College of Computing Georgia Institute of Technology 85 5th St NW Atlanta 30332 GA United States

This paper introduces Cobweb/4L, a novel approach for efficient language model learning that supports masked word prediction. The approach builds on Cobweb, an incremental system that learns a hierarchy of probabilistic concepts. Each concept stores the frequencies of words that appear in instances tagged with the concept label. The system utilizes an attribute-value representation to encode words and their context into instances. Cobweb/4L uses an information-theoretic variant of category utility as well as a new performance mechanism that leverages multiple concepts to generate predictions. We demonstrate that its new performance mechanism substantially outperforms prior Cobweb performance mechanisms that use only a single node to generate predictions. Further, we demonstrate that Cobweb/4L outperforms transformer-based language models in a low-data setting by learning more rapidly and achieving better final performance. Lastly, we show that Cobweb/4L, which is hyperparameter-free, is robust across varying scales of training data and does not require any manual tuning. This is in contrast to Word2Vec, which performs best with a varying number of hidden nodes that depend on the total amount of training data; this means its hyperparameters must be manually tuned for different amounts of training data. We conclude by discussing future directions for Cobweb/4L.

关键词： Concept learning Masked language modeling

RelJoin: Relative-cost-based Selection of Distributed Join Methods for Query Plan Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liang, Feng Lau, Francis C.M. Cui, Heming Li, Yupeng Lin, Bing Li, Chengming Hu, Xiping Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing Shenzhen MSU-BIT University Shenzhen China School of Medical Technology Beijing Institute of Technology Beijing China Department of Computer Science The University of Hong Kong Hong Kong Department of Interactive Media Hong Kong Baptist University Hong Kong College of Physics and Energy Fujian Normal University Fuzhou China Key Laboratory of Quantum Manipulation and New Energy Materials Fuzhou China School of Computer Science Peking University Bejing China

Selecting appropriate distributed join methods for logical join operations in a query plan is crucial for the performance of data-intensive scalable computing (DISC). Different network communication patterns in the data exchange phase generate varying network communication workloads and significantly affect the distributed join performance. However, most cost-based query optimizers focus on the local computing cost and do not precisely model the network communication cost. We propose a cost model for various distributed join methods to optimize join queries in DISC platforms. Our method precisely measures the network and local computing workloads in different execution phases, using information on the size and cardinality statistics of datasets and cluster join parallelism. Our cost model reveals the importance of the relative size of the joining datasets. We implement an efficient distributed join selection strategy, known as RelJoin in SparkSQL, which is an industry-prevalent distributed data processing framework. RelJoin uses runtime adaptive statistics for accurate cost estimation and selects optimal distributed join methods for logical joins to optimize the physical query plan. The evaluation results on the TPC-DS benchmark show that RelJoin performs best in 62 of the 97 queries and can reduce the average query time by 21% compared with other strategies. © 2023, CC BY-NC-ND.

关键词： Electronic data interchange

ForceNet: A graph neural network for large-scale quantum calculations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Weihua Shuaibi, Muhammed Das, Abhishek Goyal, Siddharth Sriram, Anuroop Leskovec, Jure Parikh, Devi Zitnick, C. Lawrence Department of Computer Science Stanford University United States Department of Chemical Engineering Carnegie Mellon University United States Facebook AI Research United States School of Interactive Computing Georgia Institute of Technology United States

With massive amounts of atomic simulation data available, there is a huge opportunity to develop fast and accurate machine learning models to approximate expensive physics-based calculations. The key quantity to estimate is atomic forces, where the state-of-the-art Graph Neural Networks (GNNs) explicitly enforce basic physical constraints such as rotation-covariance. However, to strictly satisfy the physical constraints, existing models have to make tradeoffs between computational efficiency and model expressiveness. Here we explore an alternative approach. By not imposing explicit physical constraints, we can flexibly design expressive models while maintaining their computational efficiency. Physical constraints are implicitly imposed by training the models using physics-based data augmentation. To evaluate the approach, we carefully design a scalable and expressive GNN model, ForceNet, and apply it to OC20 (Chanussot et al., 2020), an unprecedentedly-large dataset of quantum physics calculations. Our proposed ForceNet is able to predict atomic forces more accurately than state-of-the-art physics-based GNNs while being faster both in training and inference. Overall, our promising and counter-intuitive results open up an exciting avenue for future research. © 2021, CC BY.

关键词： Computational efficiency

Controllable text simplification with explicit paraphrasing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Maddela, Mounica Alva-Manchego, Fernando Xu, Wei School of Interactive Computing Georgia Institute of Technology United States Department of Computer Science University of Sheffield United Kingdom

Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained end-to-end to perform all these operations simultaneously. However, such systems limit themselves to mostly deleting words and cannot easily adapt to the requirements of different target audiences. In this paper, we propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles. We introduce a new data augmentation method to improve the paraphrasing capability of our model. Through automatic and manual evaluations, we show that our proposed model establishes a new state-of-the art for the task, paraphrasing more often than the existing systems, and can control the degree of each simplification operation applied to the input texts.1 © 2020, CC0.

关键词： Computational linguistics

RecycleNet: Latent Feature Recycling Leads to Iterative Decision Refinement

学校读者我要写书评

暂无评论

RecycleNet: Latent Feature Recycling Leads to Iterative Deci...

IEEE Workshop on Applications of computer Vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：