Artificial Intelligence By Example

Training the CRLMM

In previous chapters, the CRLMM program CNN_STRATEGY_MODEL.py was trained to identify Γ (gamma concept) in outputs on the conveyor belt of a food processing factory. The end of the previous chapter brought Γ up to a higher abstraction level.

As long as a member of γ (gamma) of the Γ dataset is in an undetermined state, its generalization encompasses ambivalent but similar concepts. Up to this chapter, these are the concepts Γ has learned (conceptual representation learning). 

Γ = { a gap, no gap, a load, no load, not enough load, enough load, too much load, a space on a lane for a car, a distance between a high load of products and missing products on a conveyor belt, weights on sewing stations...n}

The next step in the ...