Neural Markov Prolog
This tool assists researchers and developers in designing and communicating neural network structures, but it is incremental as it builds on existing concepts like Markov logic and Prolog.
The authors tackled the challenge of understanding and designing neural network architectures by proposing Neural Markov Prolog (NMP), a language that bridges first-order logic and neural networks, enabling easy generation and presentation of architectures for various data types.
The recent rapid advance of AI has been driven largely by innovations in neural network architectures. A concomitant concern is how to understand these resulting systems. In this paper, we propose a tool to assist in both the design of further innovative architectures and the simple yet precise communication of their structure. We propose the language Neural Markov Prolog (NMP), based on both Markov logic and Prolog, as a means to both bridge first order logic and neural network design and to allow for the easy generation and presentation of architectures for images, text, relational databases, or other target data types or their mixtures.