ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks

by   Zachary Susskind, et al.

The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain, including pruning, quantization, compression, and binary neural networks (BNNs), but with the emergence of the "extreme edge", there is now a demand for even more efficient models. In order to meet the constraints of ultra-low-energy devices, we propose ULEEN, a model architecture based on weightless neural networks. Weightless neural networks (WNNs) are a class of neural model which use table lookups, not arithmetic, to perform computation. The elimination of energy-intensive arithmetic operations makes WNNs theoretically well suited for edge inference; however, they have historically suffered from poor accuracy and excessive memory usage. ULEEN incorporates algorithmic improvements and a novel training strategy inspired by BNNs to make significant strides in improving accuracy and reducing model size. We compare FPGA and ASIC implementations of an inference accelerator for ULEEN against edge-optimized DNN and BNN devices. On a Xilinx Zynq Z-7045 FPGA, we demonstrate classification on the MNIST dataset at 14.3 million inferences per second (13 million inferences/Joule) with 0.21 μs latency and 96.2 accuracy, while Xilinx FINN achieves 12.3 million inferences per second (1.69 million inferences/Joule) with 0.31 μs latency and 95.83 45nm ASIC, we achieve 5.1 million inferences/Joule and 38.5 million inferences/second at 98.46 achieves 9230 inferences/Joule and 19,100 inferences/second at 99.35 In our search for ever more efficient edge devices, ULEEN shows that WNNs are deserving of consideration.


page 4

page 7

page 9

page 10


3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration

The deep neural network (DNN) based AI applications on the edge require ...

Weightless Neural Networks for Efficient Edge Inference

Weightless Neural Networks (WNNs) are a class of machine learning model ...

DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications

Deep neural networks (DNN) have achieved remarkable success in computer ...

Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference

The need to execute Deep Neural Networks (DNNs) at low latency and low p...

Edge-Tailored Perception: Fast Inferencing in-the-Edge with Efficient Model Distribution

The rise of deep neural networks (DNNs) is inspiring new studies in myri...

Hyperdrive: A Systolically Scalable Binary-Weight CNN Inference Engine for mW IoT End-Nodes

Deep neural networks have achieved impressive results in computer vision...

TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimation

Intelligent edge vision tasks encounter the critical challenge of ensuri...

Please sign up or login with your details

Forgot password? Click here to reset