Alternative AI

I have an ambitious project where a musician can play a few chords , then the algorithm completes the whole song together with a music video for it. i will train my system on the billboard charts throughout the years and the artist has the option of stipulating which year he wants the song to sound like its from. First i create a tree that starts whith the whole song at the top node then branches of on and on till it reaches the bit stage. During training different songs will have different trees, but i will back propagate to the bit level an expected value of say 5. The back propagation will cause the tree to be set up in a particular way. So all songs in the training set will then be represented by a "type" of tree, though the trees will still be unique. Then during operation if you play a few chords the algorithm will set up that part of the tree for the song while at this stage the rest of it is random. finally we forward propagate through this partially random tree and g

I have written a paper on a new type of network for NLP but i have lingering questions on how efficient and effective it is....this is a link to it on my blog... http://alternativeai.blogspot.com/2018/05/abstract-submited.html So the following is a more formal framing of efficiency and effectiveness in this network that i would appreciate input on. i have a type of network...it has one output node connected to all 4 hidden layer nodes, which are connected to the 12 input layer nodes the following  way.Each  is connected to exactly 9 nodes and the set of all sets of 3 nodes not being used by each node in the hidden layer consist of disjoint sets....this just means that we cant have any 2 nodes connected to the exact same nine nodes...or in general , we cant have any two nodes share missing nodes between them...... if this is clear so far there is another condition....the inputs of these input nodes is a number and each node in the hidden layer simply sums all the numbers from the input