Adaptive sequence chunkers

Schmidhuber's hierarchical chunker systems [23,24] can in principle bridge arbitrary time lags, but only if there is local predictability across the subsequences causing the time lags (see also [17]). For instance, in his postdoctoral thesis [24], Schmidhuber uses hierarchical recurrent networks with self-organizing time scales to rapidly solve certain grammar learning tasks involving minimal time lags in excess of 1000 steps. The performance of chunker systems, however, deteriorates as the noise level increases and the input sequences become less compressible.