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

09/04/2018
by   Fatemeh Hadaeghi, et al.
0

We show NP-hardness of a generalized quadratic programming problem, which we called Unconstrained N-ary Quadratic Programming (UNQP). This problem has recently become practically relevant in the context of novel memristor-based neuromorphic microchip designs, where solving the UNQP is a key operation for on-chip training of the neural network implemented on the chip. UNQP is the problem of finding a vector v∈ S^N which minimizes v^T Q v +v^T c , where S = {s_1, ..., s_n}⊂Z is a given set of eligible parameters for v, Q ∈Z^N × N is positive semi-definite, and c∈Z^N. In memristor-based neuromorphic hardware, S is physically given by a finite (and small) number of possible memristor states. The proof of NP-hardness is by reduction from the Unconstrained Binary Quadratic Programming problem, which is a special case of UNQP where S = {0, 1} and which is known to be NP-hard.

READ FULL TEXT
research
11/18/2019

Mapping NP-hard and NP-complete optimisation problems to Quadratic Unconstrained Binary Optimisation problems

We discuss several mappings from well-known NP-hard problems to Quadrati...
research
06/02/2023

Sampling binary sparse coding QUBO models using a spiking neuromorphic processor

We consider the problem of computing a sparse binary representation of a...
research
02/27/2018

Finding a root of constrained quadratic polynomial system is NP-hard

Here, we prove that finding a root of a quadratic polynomial system with...
research
02/23/2018

Graph Similarity and Approximate Isomorphism

The graph similarity problem, also known as approximate graph isomorphis...
research
11/24/2020

PeleNet: A Reservoir Computing Framework for Loihi

High-level frameworks for spiking neural networks are a key factor for f...
research
02/27/2018

Finding steady-state solutions for ODE systems of zero, first and homogeneous second-order chemical reactions is NP-hard

In the context of modeling of cell signaling pathways, a relevant step i...
research
11/26/2018

Canonical Duality Theory and Algorithm for Solving Bilevel Knapsack Problems with Applications

A novel canonical duality theory (CDT) is presented for solving general ...

Please sign up or login with your details

Forgot password? Click here to reset