Resonator Networks, 2: Factorization Performance and Capacity Compared to Optimization-Based Methods.

Journal: Neural computation
Published Date:

Abstract

We develop theoretical foundations of resonator networks, a new type of recurrent neural network introduced in Frady, Kent, Olshausen, and Sommer (2020), a companion article in this issue, to solve a high-dimensional vector factorization problem arising in Vector Symbolic Architectures. Given a composite vector formed by the Hadamard product between a discrete set of high-dimensional vectors, a resonator network can efficiently decompose the composite into these factors. We compare the performance of resonator networks against optimization-based methods, including Alternating Least Squares and several gradient-based algorithms, showing that resonator networks are superior in several important ways. This advantage is achieved by leveraging a combination of nonlinear dynamics and searching in superposition, by which estimates of the correct solution are formed from a weighted superposition of all possible solutions. While the alternative methods also search in superposition, the dynamics of resonator networks allow them to strike a more effective balance between exploring the solution space and exploiting local information to drive the network toward probable solutions. Resonator networks are not guaranteed to converge, but within a particular regime they almost always do. In exchange for relaxing the guarantee of global convergence, resonator networks are dramatically more effective at finding factorizations than all alternative approaches considered.

Authors

  • Spencer J Kent
    Redwood Center for Theoretical Neuroscience and Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94720, U.S.A. spencer.kent@berkeley.edu.
  • E Paxon Frady
    Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA 94720, U.S.A. epaxon@berkeley.edu.
  • Friedrich T Sommer
    Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA 94720, U.S.A. fsommer@berkeley.edu.
  • Bruno A Olshausen
    Redwood Center for Theoretical Neuroscience, Helen Wills Neuroscience Institute, and School of Optometry, University of California, Berkeley, Berkeley, CA 94720, U.S.A. baolshausen@berkeley.edu.