Sampling binary sparse coding QUBO models using a spiking neuromorphic processor

by   Kyle Henke, et al.

We consider the problem of computing a sparse binary representation of an image. To be precise, given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an L_2 loss on the reconstruction error, and an L_0 (or, equivalently, an L_1) loss on the binary vector enforcing sparsity. This yields a so-called Quadratic Unconstrained Binary Optimization (QUBO) problem, whose solution is generally NP-hard to find. The contribution of this work is twofold. First, the method of unsupervised and unnormalized dictionary feature learning for a desired sparsity level to best match the data is presented. Second, the binary sparse coding problem is then solved on the Loihi 1 neuromorphic chip by the use of stochastic networks of neurons to traverse the non-convex energy landscape. The solutions are benchmarked against the classical heuristic simulated annealing. We demonstrate neuromorphic computing is suitable for sampling low energy solutions of binary sparse coding QUBO models, and although Loihi 1 is capable of sampling very sparse solutions of the QUBO models, there needs to be improvement in the implementation in order to be competitive with simulated annealing.


page 2

page 5


Computing optimal discrete readout weights in reservoir computing is NP-hard

We show NP-hardness of a generalized quadratic programming problem, whic...

Quantum Sparse Coding

The ultimate goal of any sparse coding method is to accurately recover f...

Implementing and Benchmarking the Locally Competitive Algorithm on the Loihi 2 Neuromorphic Processor

Neuromorphic processors have garnered considerable interest in recent ye...

Lossy compression of statistical data using quantum annealer

We present a new lossy compression algorithm for statistical floating-po...

Improving energy efficiency and classification accuracy of neuromorphic chips by learning binary synaptic crossbars

Deep Neural Networks (DNN) have achieved human level performance in many...

Image classification using quantum inference on the D-Wave 2X

We use a quantum annealing D-Wave 2X computer to obtain solutions to NP-...

Prediction and compression of lattice QCD data using machine learning algorithms on quantum annealer

We present regression and compression algorithms for lattice QCD data ut...

Please sign up or login with your details

Forgot password? Click here to reset