Neural-Symbolic Integration for Interactive Learning and Conceptual Grounding
Neural-Symbolic Integration for Interactive Learning and Conceptual Grounding
复制标题
用于交互式学习和概念基础的神经符号整合
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
A. Garcez
中科院分区：
文献类型：
--
作者：
Benedikt Wagner;A. Garcez
我们提出了神经符号集成的抽象概念解释和交互式学习。神经符号集成和解释允许用户和领域专家了解大型神经模型的数据驱动决策过程。使用符号逻辑语言查询模型。然后，与用户的交互使用可以被提取到模型架构中的基于逻辑的约束来确认或拒绝神经模型的修订。该方法使用逻辑张量网络框架以及概念激活向量进行说明，并应用于卷积神经网络。
We propose neural-symbolic integration for abstract concept explanation and interactive learning. Neural-symbolic integration and explanation allow users and domain-experts to learn about the data-driven decision making process of large neural models. The models are queried using a symbolic logic language. Interaction with the user then confirms or rejects a revision of the neural model using logic-based constraints that can be distilled into the model architecture. The approach is illustrated using the Logic Tensor Network framework alongside Concept Activation Vectors and applied to a Convolutional Neural Network.