Differentiable logic programming in Python for elegant encoding and extending of GNNs towards more complex deep relational models — In the previous articles, we discussed the problem of relational machine learning, how it can be naturally expressed in relational logic, and why it cannot be fully addressed with standard feature vector-based models, such as classic neural networks. Then we reviewed the paradigm of neural-symbolic integration aimed at combining logic…

A closer look into the history of combining symbolic AI with deep learning — For almost a decade now, deep learning has been the moving force behind most of the progress, success, and hype surrounding the AI landscape. It has taken over the field so rapidly that many people commonly confuse the domains as being equivalent now. Artificial Intelligence ⊃ Machine Learning ⊃ Deep…

A dive into fundamentals of learning representations beyond feature vectors — From AI to ML All intelligent life forms instinctively model their surrounding environment in order to actively navigate through it with their actions. In Artificial Intelligence (AI) research, we then try to understand and automate this interesting ability of living systems with machine learning (ML) at the core. Generally speaking, deriving mathematical models of…