Potential-based shaping was designed as a way of introducing background knowledge into model-free reinforcement-learning algorithms. By identifying states that are likely to have ...
Abstract. This paper examines the generalization capability in learning multiple temporal patterns by the recurrent neural network with parametric bias (RNNPB). Our simulation expe...
We recapitulate regular one-shot learning from membership and equivalence queries, positive and negative finite data. We present a meta-algorithm that generalizes over as many sett...
Finding multiple occurrences of themes and patterns in music can be hampered due to polyphonic textures. This is caused by the complexity of music that weaves multiple independent...
Abstract. An object recognition process in general is designed as a domain specific, highly specialized task. As the complexity of such a process tends to be rather inestimable, m...