TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT
In this research, we propose a new low-precision framework, TENT, to leverage the benefits of a tapered fixed-point numerical format in TinyML models. We introduce a tapered fixed-point quantization algorithm that matches the numerical format's dynamic range and distribution to that of the deep neural network model's parameter distribution at each layer. An accelerator architecture for the tapered fixed-point with TENT framework is proposed. Results show that the accuracy on classification tasks improves up to ~31 % with an energy overhead of ~17-30 % as compared to fixed-point, for ConvNet and ResNet-18 models.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Quantization Mimic: Towards Very Tiny CNN for Object Detection
In this paper, we propose a simple and general framework for training very tiny CNNs for object detection. Due to limited representation ability, it is challenging to train very tiny networks for complicated tasks like d…
Objectobject-detectionObject DetectionQuantizationPositNN: Tapered Precision Deep Learning Inference for the Edge
The performance of neural networks, especially the currently popular form of deep neural networks, is often limited by the underlying hardware. Computations in deep neural networks are expensive, have large memory footpr…
Deep LearningTapered Language Models
Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack of identical layers in which parameters are allocated uniformly across depth. This is a default inherit…
Improving the Energy Efficiency and Robustness of tinyML Computer Vision using Log-Gradient Input Images
This paper studies the merits of applying log-gradient input images to convolutional neural networks (CNNs) for tinyML computer vision (CV). We show that log gradients enable: (i) aggressive 1.5-bit quantization of first…
Neural Architecture SearchQuantizationData-Free Network Quantization With Adversarial Knowledge Distillation
Network quantization is an essential procedure in deep learning for development of efficient fixed-point inference models on mobile or edge platforms. However, as datasets grow larger and privacy regulations become stric…
Knowledge DistillationModel CompressionQuantization