Contemporary neural networks still fall short of human-level generalization, which extends
far beyond our direct experiences. In this paper, we argue that the underlying cause for this …

In the history of the quest for human-level artificial intelligence, a number of rival paradigms
have vied for supremacy. Symbolic artificial intelligence was dominant for much of the 20th …

A key aspect of human intelligence is the ability to infer abstract rules directly from high-
dimensional sensory data, and to do so given only a limited amount of training experience …

Compositional generalization, the ability of an agent to generalize to unseen combinations
of latent factors, is easy for humans but hard for deep neural networks. A line of research in …

Despite significant progress in the development of neural-symbolic frameworks, the question
of how to integrate a neural and a symbolic system in a compositional manner remains …

The seemingly infinite diversity of the natural world arises from a relatively small set of
coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give …

Existing Collaborative Filtering (CF) methods are mostly designed based on the idea of
matching, ie, by learning user and item embeddings from data using shallow or deep …

Leveraging the compositional nature of our world to expedite learning and facilitate
generalization is a hallmark of human perception. In machine learning, on the other hand …

A central challenge for cognitive science is to explain how abstract concepts are acquired
from limited experience. This has often been framed in terms of a dichotomy between …

Current advances in Artificial Intelligence and machine learning in general, and deep
learning in particular have reached unprecedented impact not only across research …