paper-with-me

Papers

A Semantic Loss Function for Deep Learning with Symbolic Knowledge

2017-11-29 · ICML 2018 7 · Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang, Guy Van Den Broeck

This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An experimental evaluation shows that it effectively guides the learner to achieve (near-)state-of-the-art results on semi-supervised multi-class classification. Moreover, it significantly increases the ability of the neural network to predict structured objects, such as rankings and paths. These discrete concepts are tremendously difficult to learn, and benefit from a tight integration of deep learning and symbolic reasoning methods.

📄 PDF Abstract BibTeX arXiv:1711.11157

Code (1)

UCLA-StarAI/Semantic-Loss 공식 구현 tf

Tasks

Deep LearningGeneral ClassificationMulti-class Classification

Similar Papers 제목 키워드 기반

Neuro-Symbolic Approaches for Context-Aware Human Activity Recognition

2023-06-08 · Luca Arrotta, Gabriele Civitarese, Claudio Bettini

Deep Learning models are a standard solution for sensor-based Human Activity Recognition (HAR), but their deployment is often limited by labeled data scarcity and models' opacity. Neuro-Symbolic AI (NeSy) provides an int…

Activity RecognitionHuman Activity Recognition

Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

2020-11-21 · Karan Sikka, Jihua Huang, Andrew Silberfarb, Prateeth Nayak 외

We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that re…

Common Sense ReasoningZero-Shot Learning

Semantic Loss Application to Entity Relation Recognition

2020-06-07 · Venkata Sasank Pagolu

Usually, entity relation recognition systems either use a pipe-lined model that treats the entity tagging and relation identification as separate tasks or a joint model that simultaneously identifies the relation and ent…

Feature EngineeringNatural Language UnderstandingRelationRelation Extraction

T-Norms Driven Loss Functions for Machine Learning

2019-07-26 · Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Maggini 외

Neural-symbolic approaches have recently gained popularity to inject prior knowledge into a learner without requiring it to induce this knowledge from data. These approaches can potentially learn competitive solutions wi…

BIG-bench Machine LearningGeneral Knowledge

Semantic Loss Functions for Neuro-Symbolic Structured Prediction

2024-05-12 · Kareem Ahmed, Stefano Teso, Paolo Morettin, Luca Di Liello 외

Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the independence of the outputs. These outputs…

PredictionStructured Prediction