Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence最新文献_第7页

Solving Math Word Problems concerning Systems of Equations with GPT-3 用GPT-3求解方程组数学应用题

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26896

M. Zong, Bhaskar Krishnamachari

{"title":"Solving Math Word Problems concerning Systems of Equations with GPT-3","authors":"M. Zong, Bhaskar Krishnamachari","doi":"10.1609/aaai.v37i13.26896","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26896","url":null,"abstract":"Researchers have been interested in developing AI tools to help students learn various mathematical subjects. One challenging set of tasks for school students is learning to solve math word problems. We explore how recent advances in natural language processing, specifically the rise of powerful transformer based models, can be applied to help math learners with such problems. Concretely, we evaluate the use of GPT-3, a 1.75B parameter transformer model recently released by OpenAI, for three related challenges pertaining to math word problems corresponding to systems of two linear equations. The three challenges are classifying word problems, extracting equations from word problems, and generating word problems. For the first challenge, we define a set of problem classes and find that GPT-3 has generally very high accuracy in classifying word problems (80%-100%), for all but one of these classes. For the second challenge, we find the accuracy for extracting equations improves with number of examples provided to the model, ranging from an accuracy of 31% for zero-shot learning to about 69% using 3-shot learning, which is further improved to a high value of 80% with fine-tuning. For the third challenge, we find that GPT-3 is able to generate problems with accuracy ranging from 33% to 93%, depending on the problem type.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"2 1","pages":"15972-15979"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78654967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Separate but Equal: Equality in Belief Propagation for Single Cycle Graphs 分离但相等:单循环图的信念传播中的相等性

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i4.25506

Erel Cohen, Omer Lev, R. Zivan

引用次数: 2

Learning Better Representations Using Auxiliary Knowledge 使用辅助知识学习更好的表征

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26927

Saed Rezayi

引用次数: 0

Learning Temporal-Ordered Representation for Spike Streams Based on Discrete Wavelet Transforms 基于离散小波变换的尖峰流时间有序表示学习

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i1.25085

Jiyuan Zhang, Shanshan Jia, Zhaofei Yu, Tiejun Huang

{"title":"Learning Temporal-Ordered Representation for Spike Streams Based on Discrete Wavelet Transforms","authors":"Jiyuan Zhang, Shanshan Jia, Zhaofei Yu, Tiejun Huang","doi":"10.1609/aaai.v37i1.25085","DOIUrl":"https://doi.org/10.1609/aaai.v37i1.25085","url":null,"abstract":"Spike camera, a new type of neuromorphic visual sensor that imitates the sampling mechanism of the primate fovea, can capture photons and output 40000 Hz binary spike streams. Benefiting from the asynchronous sampling mechanism, the spike camera can record fast-moving objects and clear images can be recovered from the spike stream at any specified timestamps without motion blurring. Despite these, due to the dense time sequence information of the discrete spike stream, it is not easy to directly apply the existing algorithms of traditional cameras to the spike camera. Therefore, it is necessary and interesting to explore a universally effective representation of dense spike streams to better fit various network architectures. In this paper, we propose to mine temporal-robust features of spikes in time-frequency space with wavelet transforms. We present a novel Wavelet-Guided Spike Enhancing (WGSE) paradigm consisting of three consecutive steps: multi-level wavelet transform, CNN-based learnable module, and inverse wavelet transform. With the assistance of WGSE, the new streaming representation of spikes can be learned. We demonstrate the effectiveness of WGSE on two downstream tasks, achieving state-of-the-art performance on the image reconstruction task and getting considerable performance on semantic segmentation. Furthermore, We build a new spike-based synthesized dataset for semantic segmentation. Code and Datasets are available at https://github.com/Leozhangjiyuan/WGSE-SpikeCamera.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"3 1","pages":"137-147"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76182204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Autonomous Agents: An Advanced Course on AI Integration and Deployment 自主代理:人工智能集成与部署高级课程

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26881

Stephanie Rosenthal, R. Simmons

引用次数: 0

Robust Training for AC-OPF (Student Abstract) AC-OPF的鲁棒训练(学生摘要)

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26941

Fuat C. Beylunioglu, M. Pirnia, P. R. Duimering, Vijay Ganesh

引用次数: 0

DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness DeFL:通过关键学习周期感知防御联邦学习中的模型中毒攻击

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i9.26271

Gang Yan, Hao Wang, Xu Yuan, Jian Li

{"title":"DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness","authors":"Gang Yan, Hao Wang, Xu Yuan, Jian Li","doi":"10.1609/aaai.v37i9.26271","DOIUrl":"https://doi.org/10.1609/aaai.v37i9.26271","url":null,"abstract":"Federated learning (FL) is known to be susceptible to model poisoning attacks in which malicious clients hamper the accuracy of the global model by sending manipulated model updates to the central server during the FL training process. Existing defenses mainly focus on Byzantine-robust FL aggregations, and largely ignore the impact of the underlying deep neural network (DNN) that is used to FL training. Inspired by recent findings on critical learning periods (CLP) in DNNs, where small gradient errors have irrecoverable impact on the final model accuracy, we propose a new defense, called a CLP-aware defense against poisoning of FL (DeFL). The key idea of DeFL is to measure fine-grained differences between DNN model updates via an easy-to-compute federated gradient norm vector (FGNV) metric. Using FGNV, DeFL simultaneously detects malicious clients and identifies CLP, which in turn is leveraged to guide the adaptive removal of detected malicious clients from aggregation. As a result, DeFL not only mitigates model poisoning attacks on the global model but also is robust to detection errors. Our extensive experiments on three benchmark datasets demonstrate that DeFL produces significant performance gain over conventional defenses against state-of-the-art model poisoning attacks.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"14 1","pages":"10711-10719"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87129730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

On Undisputed Sets in Abstract Argumentation 论抽象论证中的不可争集

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i5.25805

Matthias Thimm

引用次数: 1

Identifying and Eliminating Majority Illusion in Social Networks 识别和消除社交网络中的多数错觉

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i4.25634

Umberto Grandi, Lawqueen Kanesh, Grzegorz Lisowski, M. Ramanujan, P. Turrini

引用次数: 0

Privacy Attacks on Schedule-Driven Data 对计划驱动数据的隐私攻击

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i10.26412

Stephan A. Fahrenkrog-Petersen, Arik Senderovich, Alexandra Tichauer, Ali Kaan Tutak, J. Christopher Beck, M. Weidlich

{"title":"Privacy Attacks on Schedule-Driven Data","authors":"Stephan A. Fahrenkrog-Petersen, Arik Senderovich, Alexandra Tichauer, Ali Kaan Tutak, J. Christopher Beck, M. Weidlich","doi":"10.1609/aaai.v37i10.26412","DOIUrl":"https://doi.org/10.1609/aaai.v37i10.26412","url":null,"abstract":"Schedules define how resources process jobs in diverse domains, reaching from healthcare to transportation, and, therefore, denote a valuable starting point for analysis of the underlying system. However, publishing a schedule may disclose private information on the considered jobs. In this paper, we provide a first threat model for published schedules, thereby defining a completely new class of data privacy problems. We then propose distance-based measures to assess the privacy loss incurred by a published schedule, and show their theoretical properties for an uninformed adversary, which can be used as a benchmark for informed attacks. We show how an informed attack on a published schedule can be phrased as an inverse scheduling problem. We instantiate this idea by formulating the inverse of a well-studied single-machine scheduling problem, namely minimizing the total weighted completion times. An empirical evaluation for synthetic scheduling problems shows the effectiveness of informed privacy attacks and compares the results to theoretical bounds on uninformed attacks.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"115 1","pages":"11972-11979"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86171558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0