Search
 
loader loading subjects...
cover
Chapter 5. Boolean Connectives and Deep Learning: Three Interpretations
Miguel-Angel Mendez-Lucero, Vaishak Belle
100 - 113
10.3233/FAIA230137
Research Article
Frontiers in Artificial Intelligence and Applications
Volume 369: Compendium of Neurosymbolic Artificial Intelligence
Abstract

In this paper, we motivate three approaches for integrating symbolic logic systems and deep learning methods. First, we consider whether the hidden layers of neural networks can be used to represent and reason about Boolean functions via so-called Tractable Circuits. Second, we discuss a method for encoding domain knowledge into the training and outputs of neural networks via so-called MultiplexNets. Finally, we show how we can instantiate deep learning architectures that perform exact function learning, via so-called Signal Perceptrons.

$35.00 / €27.50 / £22.00
Add PDF to cart