Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge

Abstract

Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Object Detection. However, many other relevant applications of DL, especially at the edge, are based on time-series processing and require models with unique features, for which NAS is less explored. This work focuses in particular on Temporal Convolutional Networks (TCNs), a convolutional model for time-series processing that has recently emerged as a promising alternative to more complex recurrent architectures. We propose the first NAS tool that explicitly targets the optimization of the most peculiar architectural parameters of TCNs, namely dilation, receptive-field and number of features in each layer. The proposed approach searches for networks that offer good trade-offs between accuracy and number of parameters/operations, enabling an efficient deployment on embedded platforms. We test the proposed NAS on four real-world, edge-relevant tasks, involving audio and bio-signals. Results show that, starting from a single seed network, our method is capable of obtaining a rich collection of Pareto optimal architectures, among which we obtain models with the same accuracy as the seed, and 15.9-152x fewer parameters. Compared to three state-of-the-art NAS tools, ProxylessNAS, MorphNet and FBNetV2, our method explores a larger search space for TCNs (up to 10^12x) and obtains superior solutions, while requiring low GPU memory and search time. We deploy our NAS outputs on two distinct edge devices, the multicore GreenWaves Technology GAP8 IoT processor and the single-core STMicroelectronics STM32H7 microcontroller. With respect to the state-of-the-art hand-tuned models, we reduce latency and energy of up to 5.5x and 3.8x on the two targets respectively, without any accuracy loss.

arXiv commentAccepted for publication at the IEEE Transactions on Computers

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Neural Architecture Search with Reinforcement Learning
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Deep Neural Networks for Multiple Speaker Detection and Localization
• Benchmarking TinyML Systems: Challenges and Direction
• DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs
• Robust and Energy-efficient PPG-based Heart-Rate Monitoring
• TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
• Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
• Fine-Grained Stochastic Architecture Search

Cited by in corpus (8)

• Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
• Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays
• Flexible and Fully Quantized Ultra-Lightweight TinyissimoYOLO for Ultra-Low-Power Edge Systems
• Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes
• Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs
• Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time
• On-Device Neural Architecture Search
• Green-NAS: A Global-Scale Multi-Objective Neural Architecture Search for Robust and Efficient Edge-Native Weather Forecasting