Take a look at this 'KQRP vs kbp' chess puzzle or problem (whichever you wish to call it) composed by a computer using the 'Digital Synaptic Neural Substrate' computational creativity approach which does not use any kind of deep learning. After years of development, Chesthetica is able to use the technology to express original creative thought in this domain. Note that it also never had millions of IBM or Google dollars behind it. Depending on the type and complexity of the problem desired, a single instance of Chesthetica running on a desktop computer can probably generate anywhere between one and ten problems per hour.
