# TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT

arXiv: https://arxiv.org/abs/2104.02233 · HTML: https://mlsanity.com/paper/2104.02233/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Scaling Laws for Autoregressive Generative Modeling](https://mlsanity.com/paper/2010.14701/) (2020)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks](https://mlsanity.com/paper/1911.03852/) (2019)
- [CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs](https://mlsanity.com/paper/1801.06601/) (2018)
- [Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy](https://mlsanity.com/paper/1711.05852/) (2017)
- [Benchmarking TinyML Systems: Challenges and Direction](https://mlsanity.com/paper/2003.04821/) (2020)
- [DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning](https://mlsanity.com/paper/1810.05726/) (2018)
- [μNAS: Constrained Neural Architecture Search for Microcontrollers](https://mlsanity.com/paper/2010.14246/) (2020)
- [SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers](https://mlsanity.com/paper/1905.12107/) (2019)
- [Visual Wake Words Dataset](https://mlsanity.com/paper/1906.05721/) (2019)
- [Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference](https://mlsanity.com/paper/1809.04191/) (2018)
- [SCALE-Sim: Systolic CNN Accelerator Simulator](https://mlsanity.com/paper/1811.02883/) (2018)
- [Least squares binary quantization of neural networks](https://mlsanity.com/paper/2001.02786/) (2020)
- [Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers](https://mlsanity.com/paper/2008.05124/) (2020)
- [Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation](https://mlsanity.com/paper/2009.05647/) (2020)

## Built on by (most cited first, 4 of 4)

- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [From Tiny Machine Learning to Tiny Deep Learning: A Survey](https://mlsanity.com/paper/2506.18927/) (2025)

## Abstract (arXiv)

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.