Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks

03/16/2020
by   Karan Sikka, et al.
10

We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data. We provide formal semantics that demonstrate that our knowledge representation captures all of first order logic and that finite sampling from infinite domains converges to correct truth values. DASL's representation improves on prior neural-symbolic work by avoiding vanishing gradients, allowing deeper logical structure, and enabling richer interactions between the knowledge and learning components. We illustrate DASL through a toy problem in which we add structure to an image classification problem and demonstrate that knowledge of that structure reduces data requirements by a factor of 1000. We then evaluate DASL on a visual relationship detection task and demonstrate that the addition of commonsense knowledge improves performance by 10.7% in a data scarce setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/06/2019

Semantic Interpretation of Deep Neural Networks Based on Continuous Logic

Combining deep neural networks with the concepts of continuous logic is ...
research
06/23/2020

Logical Neural Networks

We propose a novel framework seamlessly providing key properties of both...
research
06/14/2016

Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge

We propose Logic Tensor Networks: a uniform framework for integrating au...
research
04/11/2016

Symbolic Knowledge Extraction using Łukasiewicz Logics

This work describes a methodology that combines logic-based systems and ...
research
05/24/2017

Logic Tensor Networks for Semantic Image Interpretation

Semantic Image Interpretation (SII) is the task of extracting structured...
research
07/06/2022

Extending Logical Neural Networks using First-Order Theories

Logical Neural Networks (LNNs) are a type of architecture which combine ...
research
06/17/2019

Neural Theorem Provers Do Not Learn Rules Without Exploration

Neural symbolic processing aims to combine the generalization of logical...

Please sign up or login with your details

Forgot password? Click here to reset