Recurrent neural networks have achieved remarkable success at generating sequences with complex structures, thanks to advances that include richer embeddings of input and cures for vanishing gradients. Trained only on sequences from a known grammar, though, they can still struggle to learn rules and constraints of the grammar. Neural Attribute Machines (NAMs) are equipped with a logical machine that represents the underlying grammar, which is used to teach the constraints to the neural machine by (i) augmenting the input sequence, and (ii) optimizing a custom loss function. Unlike traditional RNNs, NAMs are exposed to the grammar, as well as samples from the language of the grammar. During generation, NAMs make significantly fewer violations of the constraints of the underlying grammar than RNNs trained only on samples from the language of the grammar.
Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines
AI Enablement(AI赋能部门);Huawei Türkiye R&D Center(华为土耳其研发中心)
A Taxonomy of Information Attributes for Test Case Prioritisation: Applicability, Machine Learning
Universidad de Córdoba(科尔多瓦大学);Instituto Andaluz Interuniversitario de Data Science and Computational Intelligence (DaSCI)(安达卢西亚校际数据科学与计算智能研究所);Chalmers University of Technology(查尔姆斯理工大学)
A Novel Machine Learning Approach to Data Inconsistency with respect to a Fuzzy Relation
Ghent University(根特大学);University of Catania(卡塔尼亚大学);University of Portsmouth(朴茨茅斯大学);Poznań University of Technology(波兹南理工大学);Polish Academy of Sciences(波兰科学院)
Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding
State Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);Department of Computer Science and Engineering, University of Texas at Arlington(德克萨斯大学阿灵顿分校计算机科学与工程系)
Bio-inspired Machine Learning: programmed death and replication
Budker Institute of Nuclear Physics(布德克尔核物理研究所);Novosibirsk State University(新西伯利亚国立大学);National Center for Biotechnology Information(美国国家生物技术信息中心);Duluth Institute for Advanced Study(德卢斯高等研究院)
Towards Visual Explainable Active Learning for Zero-Shot Classification
Tianjin University(天津大学);Tianjin cultural heritage conservation and inheritance engineering technology center(天津文化遗产保护与传承工程技术中心);Key Research Center for Surface Monitoring and Analysis of Relics, State Administration of Cultural Heritage, China(国家文物局文物表面监测与分析重点科研基地)
On Interpretability and Similarity in Concept-Based Machine Learning
Bern University of Applied Sciences(伯尔尼应用科学大学);National Research University Higher School of Economics(国立研究型大学高等经济学院);St. Petersburg Department of Steklov Mathematical Institute of Russian Academy of Sciences(俄罗斯科学院斯捷克洛夫数学研究所圣彼得堡分所)