It is an empirical observation that Software Engineering and Knowledge Engineering seem to converge to a single discipline which may be suitably called Software-Knowledge. However, mere empirical observations are not satisfactory. These should be justified by plausible arguments. There are three convergence aspects, semantic, algebraic and topological, and this paper focuses on the algebraic aspect. Linear algebra is the basis for Linear Software Models, a rigorous theory of software systems composition from subsystems , recently developed. Linear algebra, with added non-linearity, is also the basis for Deep Learning, a successful Artificial Intelligence domain. This work suggests and analyzes Deep Software Learning, i.e. Deep Learning specific to Software development problems. We then conjecture on deep reasons for Software-Knowledge convergence.