Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtaine...
Virtual labs enable field specific experiments and open them for collaborative and distributed usage. In order to realize comprehensive laboratory set-ups providing a scientifi...
We present a trainable sequential-inference technique for processes with large state and observation spaces and relational structure. Our method assumes "reliable observation...
A number of natural models for learning in the limit is introduced to deal with the situation when a learner is required to provide a grammar covering the input even if only a par...
Observation activity, on instrumented collective learning situations, enables participants to appropriate themselves corresponding systems in their own practice. In this paper, we...