Memory facilitation using directed acyclic graphs

One or more tangible device-readable media with device-executable instructions that, when executed by a computing system, direct the computing system to perform steps comprising:

• at a machine learning system:
• accessing a plurality of training examples;
• storing a graph of connected nodes at a memory of the machine learning system the nodes having split function parameters specifying tests for determining flow of elements through the graph;
• and
• adding, using a processor, new nodes to the graph in a manner which selects between possible connection patterns between nodes of the graph, and possible split function parameter values, by applying a training objective to elements of the training examples reaching nodes of the graph according to the split function parameters;
• wherein adding new nodes to the graph comprises selecting between possible connection patterns only between the new nodes and a single parent layer of nodes of the graph.

A machine learning system comprising:

• an input arranged to access a plurality of training examples;
• a memory storing a graph of connected nodes, the nodes having split function parameters specifying tests for determining flow of elements through the graph;
• and
• a training logic arranged to add new nodes to the graph in a manner which selects between possible connection patterns between nodes of the graph, and possible split function parameter values, by applying a training objective to elements of the training images reaching nodes of the graph according to the split function parameters.