Litcius/Paper detail

On the Stability of Analog ReLU Networks

Ibrahim M. Elfadel

2020IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems21 citationsDOI

Abstract

Rectified linear unit (ReLU) networks have become widely used in machine learning and automated inference using neural networks. Various forms of hardware accelerators based on ReLU networks have also been under development. In this brief, the stability problem in analog ReLU networks is addressed. Using the Lyapunov stability theory, it is shown that the origin of an unforced, analog ReLU dynamical system is globally asymptotically stable if the induced Euclidean norm of its connectivity matrix is less than one. An example is given to demonstrate that this upper bound is the best that can be achieved. In particular, the stability result holds for the case of a nonsymmetric connectivity matrix as may occur in some mathematical models of neurobiology.

Topics & Concepts

Stability (learning theory)Artificial neural networkComputer scienceCellular neural networkMatrix (chemical analysis)Stability theoryNorm (philosophy)Lyapunov stabilityEuclidean geometryUpper and lower boundsArtificial intelligenceMathematicsMachine learningNonlinear systemMathematical analysisPhysicsControl (management)Composite materialPolitical scienceGeometryMaterials scienceLawQuantum mechanicsNeural Networks Stability and SynchronizationAdvanced Memory and Neural Computingstochastic dynamics and bifurcation