Home /Research /Techology trend of edge AI
LEARNING

Techology trend of edge AI

Yen-Lin Lee, Pei-Kuei Tsung, Max Wu

Year
2018
Citations
86

Abstract

Artificial intelligence (AI), defined as intelligence exhibited by machines, has many applications in today's society, including robotics, mobile devices, smart transportation, healthcare service, and more. Recently, lots of AI investment in both big companies and startups have launched. Besides cloud-based solution, AI on the edge devices (Edge AI) takes the advantages of rapid response with low latency, high privacy, more robustness, and better efficient use of network bandwidth. To enable Edge AI, new embedded system technologies are desired, including machine learning, neural network acceleration and reduction, and heterogeneous run-time mechanism. This paper introduces challenges and technologies trend of Edge AI. In addition, it illustrates edge AI solutions from MediaTek, including the dedicated AI processing unit (APU) and NeuroPilot technology, which provides superior Edge AI ability in a wide range of applications.

Keywords

Computer scienceEdge computingArtificial intelligenceApplications of artificial intelligenceCloud computingEnhanced Data Rates for GSM EvolutionEdge deviceRobustness (evolution)Artificial neural networkRobotics

Related papers

Browse all LEARNING papers