Edit resource "DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices" Accepted
The requested resource couldn't be found.
Changes: 6
-
Update DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- Title
-
- Unchanged
- DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- At edit time
- DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- Type
-
- Unchanged
- Paper
- At edit time
- Paper
- Created
-
- Unchanged
- 2016-04
- At edit time
- 2016-04
- Description
-
- Unchanged
- In this work, we present the design and implementation of DeepX, a software accelerator for deep learning execution. DeepX significantly lowers the device resources (viz. memory, computation, energy) required by deep learning that currently act as a severe bottleneck to mobile adoption.
- At edit time
- In this work, we present the design and implementation of DeepX, a software accelerator for deep learning execution. DeepX significantly lowers the device resources (viz. memory, computation, energy) required by deep learning that currently act as a severe bottleneck to mobile adoption.
- Link
-
- Unchanged
- http://dx.doi.org/10.1109/ipsn.2016.7460664
- At edit time
- http://dx.doi.org/10.1109/ipsn.2016.7460664
- Identifier
-
- Unchanged
- ISBN: 9781509008025
- At edit time
- ISBN: 9781509008025
-
Add Deep Learning on Mobile Devices - A Review
- Title
-
- Unchanged
- Deep Learning on Mobile Devices - A Review
- Type
-
- Unchanged
- Paper
- Created
-
- Unchanged
- 2019-03-20
- Description
-
- Unchanged
- 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
-
- Unchanged
- http://arxiv.org/abs/1904.09274
- Identifier
-
- Unchanged
- 10.13140/RG.2.2.15012.12167
Resource | v1 | current (v1) -
Add Deep learning on mobile devices
- Title
-
- Unchanged
- Deep learning on mobile devices
- Description
-
- Unchanged
- 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.
- Link
-
- Unchanged
- https://arxiv.org/abs/1904.09274
Topic | v1 | current (v1) -
Update Deep learning relates to DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- Current
- relates to
- At edit time
- treated in
Topic to resource relation | v2 -
Add Deep learning on mobile devices treated in DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
- Current
- treated in
Topic to resource relation | v1 -
Add Deep learning on mobile devices treated in Deep Learning on Mobile Devices - A Review
- Current
- treated in
Topic to resource relation | v1