Topographic Representation for Quantum Machine Learning. (arXiv:1810.06992v3 [cs.LG] UPDATED)

This paper proposes a brain-inspired approach to quantum machine learning
with the goal of circumventing many of the complications of other approaches.
The fact that quantum processes are unitary presents both opportunities and
challenges. A principal opportunity is that a large number of computations can
be carried out in parallel in linear superposition, that is, quantum
parallelism. The challenge is that the process is linear, and most approaches
to machine learning depend significantly on nonlinear processes. Fortunately,
the situation is not hopeless, for we know that nonlinear processes can be
embedded in unitary processes, as is familiar from the circuit model of quantum
computation. This paper explores an approach to the quantum implementation of
machine learning involving nonlinear functions operating on information
represented topographically (by computational maps), as common in neural
cortex.

Article web page: