The Orlando Project: A 28 nm FD-SOI Low Memory Embedded Neural Network ASIC
2016
The recent success of neural networks in various computer vision tasks open the possibility to add visual intelligence to mobile and wearable devices; however, the stringent power requirements are unsuitable for networks run on embedded CPUs or GPUs. To address such challenges, STMicroelectronics developed the Orlando Project, a new and low power architecture for convolutional neural network acceleration suited for wearable devices. An important contribution to the energy usage is the storage and access to the neural network parameters. In this paper, we show that with adequate model compression schemes based on weight quantization and pruning, a whole AlexNet network can fit in the local memory of an embedded processor, thus avoiding additional system complexity and energy usage, with no or low impact on the accuracy of the network. Moreover, the compression methods work well across different tasks, e.g. image classification and object detection.
Keywords:
- Quantization (signal processing)
- Application-specific integrated circuit
- Parallel computing
- Convolutional neural network
- Artificial neural network
- Wearable technology
- Contextual image classification
- Computer science
- Object detection
- Hardware acceleration
- Computer vision
- Artificial intelligence
- Computer architecture
- Power Architecture
- Embedded system
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
30
References
2
Citations
NaN
KQI