Category-based Inductive Learning in Shared NeMuS

One of the main objectives of cognitive science is to use abstraction to create models that represent accurately the cognitive processes that constitute learning, such as categorisation. Relational knowledge is important in this task, since through the reasoning processes of induction and analogy over relations that the mind ”creates” categories (it later estabilishes causal relations between them by using induction and abduction), and analogies exemplify crucial properties of relational processing, like structure-consistent mapping[2]. Given the complexity of the task, no model today has accomplished it completely. The associacionist/connectionist approach represents those processes through associations between different informations. That is done by using artificial neural networks. However, it faces a great obstacle: the idea (called propositional fixation) that neural networks could not represent relational knowledge. A recent attempt to tackle the symbolic extraction from artificial neural networks was proposed in [1] The cognitive agent Amao uses a shared Neural Multi-Space (Shared NeMuS) of coded first-order expressions to model the various aspects of logical formulae as separate spaces, with importance vectors of different sizes. Amao [4] uses inverse unification as the generalization mechanism for learning from a set of logically connected expressions of the Herbrand Base (HB). Here we present an experiment to use such learning mechanism to model a simple version of train set from Michalski’s train problem[3].