> Generating random patterns that sound jazz-ish is interesting, but until multiple generators can react to what the other is doing in real time (or to a human participant), it isn't exactly jazz.
For an arbitrarily complex network, it could internally develop independent generators that react to each other.
However, the likelihood of common optimization strategies used for training RNNs (back-propagation through time, foveation/attention, etc.) developing a network like this is probably quite small.
It would be possible for a network designer to come up with a structure (as Hochreiter did with LSTMs) that lends itself to this sort of structure but then you're baking in assumptions about how humans accomplish a task (which comes with trade-offs).
For an arbitrarily complex network, it could internally develop independent generators that react to each other.
However, the likelihood of common optimization strategies used for training RNNs (back-propagation through time, foveation/attention, etc.) developing a network like this is probably quite small.
It would be possible for a network designer to come up with a structure (as Hochreiter did with LSTMs) that lends itself to this sort of structure but then you're baking in assumptions about how humans accomplish a task (which comes with trade-offs).