ADaPT: optimizing CNN inference on IoT and mobile devices using approximately separable 1-D kernels.
Partha MajiDaniel BatesAlex ChadwickRobert D. MullinsPublished in: IML (2017)
Keyphrases
- mobile devices
- mobile computing
- context aware
- mobile learning
- management system
- cellular neural networks
- kernel methods
- bayesian networks
- mobile phone
- inference process
- location aware
- probabilistic inference
- kernel function
- mobile environments
- smart phones
- embedded devices
- feature space
- support vector
- media rich
- tablet computers
- mobile users
- mobile applications
- learning activities
- multiple kernel learning
- belief networks
- positive definite
- cloud computing
- color images