Litcius/Paper detail

Computational Complexity Reduction Techniques for Deep Neural Networks: A Survey

Md. Bipul Hossain, Na Gong, Mohamed Shaban

202313 citationsDOI

Abstract

Deep-learning (DL) has been extensively applied in multiple fields such as medicine, space, agriculture and industry. It has proven to be able to successfully extract unique and discriminative features of targets from structured or unstructured data and provide useful and precise predictions. However, the computational complexity of DL remains a burden for realizing such approaches on battery-powered resource-constrained mobile, wearable, and other Internet-of-Things (IoT) edge devices. In this paper, we present a survey of the significant approaches for reducing the complexity of DL models including pruning, quantization, knowledge distillation, multiplication reduction, resource efficient architectures, low rank approximation and network architecture search. Further, we discuss the limitations of these approaches and demonstrate potential solutions.

Topics & Concepts

Computer scienceComputational complexity theoryArtificial intelligenceReduction (mathematics)Computational resourcePruningDeep learningMachine learningArtificial neural networkWearable technologyEdge computingQuantization (signal processing)Wearable computerComputer engineeringEnhanced Data Rates for GSM EvolutionAlgorithmEmbedded systemMathematicsBiologyGeometryAgronomyAdvanced Neural Network ApplicationsMachine Learning and ELMNeural Networks and Applications