Learning dynamics of deep linear networks with multiple pathways

Jianghong Shi, Eric Todd SheaBrown, Michael A Buice

Keywords: deep networks, linear networks, dynamical systems, theory, parallel pathways

TL;DR: We show in the large width, large depth limit that deep linear networks will concentrate features of the training set (defined by singular values) in separate pathways.

Abstract: Not only have deep networks become standard in machine learning, they are increasingly of interest in neuroscience as models of cortical computation that capture relationships between structural and functional properties. In addition they are a useful target of theoretical research into the properties of network computation. Deep networks typically have a serial or approximately serial organization across layers, and this is often mirrored in models that purport to represent computation in mammalian brains. There are, however, multiple examples of parallel pathways in mammalian brains. In some cases, such as the mouse, the entire visual system appears arranged in a largely parallel, rather than serial fashion. While these pathways may be formed by differing cost functions that drive different computations, here we present a new mathematical analysis of learning dynamics in networks that have parallel computational pathways driven by the same cost function. We use the approximation of deep linear networks with large hidden layer sizes to show that, as the depth of the parallel pathways increases, different features of the training set (defined by the singular values of the input-output correlation) will typically concentrate in one of the pathways. This result is derived analytically and demonstrated with numerical simulation. Thus, rather than sharing stimulus and task features across multiple pathways, parallel network architectures learn to produce sharply diversified representations with specialized and specific pathways, a mechanism which may hold important consequences for codes in both biological and artificial systems.