Approximate Computing for ML
Georgios Zervakis, Hassaan Saadat, Hussam Amrouch, Andreas Gerstlauer, Sri Parameswaran, Jörg Henkel
Abstract
In this paper, we present our state-of-the-art approximate techniques that cover the main pillars of approximate computing research. Our analysis considers both static and reconfigurable approximation techniques as well as operation-specific approximate components (e.g., multipliers) and generalized approximate highlevel synthesis approaches. As our application target, we discuss the improvements that such techniques bring on machine learning and neural networks. In addition to the conventionally analyzed performance and energy gains, we also evaluate the improvements that approximate computing brings in the operating temperature.
Topics & Concepts
Computer scienceCover (algebra)Artificial neural networkApproximation algorithmState (computer science)Computational scienceComputer engineeringArtificial intelligenceAlgorithmEngineeringMechanical engineeringLow-power high-performance VLSI designParallel Computing and Optimization TechniquesFerroelectric and Negative Capacitance Devices