Deep Learning on Mobile Devices - A Review


Resource history | v1 (current) | created by janarez

Details

Deep Learning on Mobile Devices - A Review

| created by janarez | Edit resource "DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices"
Title
Deep Learning on Mobile Devices - A Review
Type
Paper
Created
2019-03-20
Description
While traditional computation paradigms rely on mobile sensing and cloud computing, deep learning implemented on mobile devices provides several advantages. These advantages include low communication bandwidth, small cloud computing resource cost, quick response time, and improved data privacy. In this paper, we discuss hardware architectures for mobile deep learning. We present Size, Weight, Area and Power considerations and their relation to algorithm optimizations, such as quantization, pruning, compression, and approximations that simplify computation while retaining performance accuracy. We cover existing systems and give a state-of-the-industry review of TensorFlow, MXNet, Mobile AI Compute Engine, and Paddle-mobile deep learning platform. We discuss resources for mobile deep learning practitioners. We present applications of various mobile sensing modalities to industries. We address the key deep learning challenges to overcome.
Link
http://arxiv.org/abs/1904.09274
Identifier
10.13140/RG.2.2.15012.12167

authors

This resource has no history of related authors.

resources

This resource has no history of related resources.