Logical Neural Networks Pt 2/4: Logic and Inference

preview_player
Показать описание
The Neuro Symbolic Channel provides the tutorials, courses, and research results on one of the most exciting areas in artificial intelligence and machine learning. With content originally from the AI course taught at Arizona State University, this channel brings you the latest at the intersection of symbolic methods (e.g., logic programming) and deep learning. Learn about the latest algorithms, Python packages, and progress toward larger goals such as artificial general intelligence (AGI).

In this video:
In this video, we continue our discussion on Logical Neural Networks (Riegel et al., 2020) commonly referred to as LNN's. Here we describe the weighted, real-valued logic that underlies the framework as well as the inference process (the upward-downward algorithm).

Original paper of Riegel et al.:

LNN GitHub site:

Key words:
Neuro symbolic reasoning
Artificial intelligence
Machine learning
Logic programming
Рекомендации по теме