Robin Manhaeve - DeepProbLog: Neural Probabilistic Logic Programming

These past few years, deep learning has been successfully applied to many fields in AI. However, in doing this, we have also encountered some of its limitations. One of these limitations is that the reasoning power of neural networks is still limited. Integrating deep learning and logic-based reasoning methods could alleviate this issue. There are, however, many ways to approach this integration. In this talk, we will discuss several of these approaches. Furthermore, we will focus on probabilistic logic programming and why it is well suited to solve this. Finally, we will also discuss our own implementation, DeepProbLog, in detail.

Bio: Robin Manhaeve is a PhD student at the DTAI research group under the supervision of Professor Luc De Raedt. His main research focus is on the integration of Deep Learning and Probabilistic Logic Programming. He's currently being supported by the FWO as an SB PhD fellow.

*Sponsors*
Man AHL: At Man AHL, we mix machine learning, computer science and engineering with terabytes of data to invest billions of dollars every day.

https://evolution.ai/ : Machines that Read - Intelligent data extraction from corporate and financial documents.

Видео Robin Manhaeve - DeepProbLog: Neural Probabilistic Logic Programming канала London Machine Learning Meetup