Despite the recent successes of deep neural networks in various fields such as image and speech recognition, natural language processing, and reinforcement learning, we still face big challenges in bringing the power of numeric optimization to symbolic reasoning. Researchers have proposed different avenues such as neural machine translation for proof synthesis, vectorization of symbols and expr...

Bilateral regions of the intraparietal sulcus (IPS) appear to be functionally selective for both rudimentary non-symbolic number tasks and higher-level symbolic number tasks in adults and older children. Furthermore, the ability to mentally represent and manipulate approximate non-symbolic numerical quantities is present from birth. These factors leave open whether the specialization of the IPS...

We propose a new cognitive robot control architecture in which the cognitive layer can be programmed by means of the agent programming language Goal. The architecture exploits the support that agent-oriented programming offers for creating cognitive robotic agents, including symbolic knowledge representation, deliberation via modular, high-level action selection, and support for multiple, decla...

The problem of language acquistion was originally studied by psychologists, but now it is an important problem in Artificial Intelligence as well. Rumelhart and McClelland (from now on referred to as R&M) have claimed that simulating the internal workings of the brain (i.e. using a connectionist method) best models language acquistion. This problem is important for several reasons. It has many ...

THIS section of the paper describes a general method, which applies the techniques of modern symbolic logic, for giving a semantical interpretation to those entities of natural language systems that function in a structural capacity. Such entities do not perform the task of denoting the individuals, properties and relations of those individuals a language talks about; they are linguistic device...

In this article we first review evidence for the approximate number system (ANS), an evolutionarily ancient and developmentally conservative cognitive mechanism for representing number without language. We then critically review five different lines of support for the proposal that symbolic representations of number build upon the ANS, and discuss potential causes of conflicting findings in the...