# Ternary Neural Networks for Resource-Efficient AI Applications

arXiv: https://arxiv.org/abs/1609.00222 · HTML: https://mlsanity.com/paper/1609.00222/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2016.

## Built on by (most cited first, 30 of 33)

- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Sparse Random Networks for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2209.15328/) (2022)
- [LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup](https://mlsanity.com/paper/2302.03213/) (2023)
- [Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training](https://mlsanity.com/paper/2308.06689/) (2023)
- [FlexBlock: A Flexible DNN Training Accelerator with Multi-Mode Block Floating Point Support](https://mlsanity.com/paper/2203.06673/) (2022)
- [ULEEN: A Novel Architecture for Ultra Low-Energy Edge Neural Networks](https://mlsanity.com/paper/2304.10618/) (2023)
- [TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization](https://mlsanity.com/paper/2606.13054/) (2026)
- [Signing the Supermask: Keep, Hide, Invert](https://mlsanity.com/paper/2201.13361/) (2022)
- [A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challenges](https://mlsanity.com/paper/2205.03824/) (2022)
- [TerDiT: Ternary Diffusion Models with Transformers](https://mlsanity.com/paper/2405.14854/) (2024)
- [Static analysis of ReLU neural networks with tropical polyhedra](https://mlsanity.com/paper/2108.00893/) (2021)
- [Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks](https://mlsanity.com/paper/2206.05916/) (2022)
- [Stochastic Configuration Machines for Industrial Artificial Intelligence](https://mlsanity.com/paper/2308.13570/) (2023)
- [Fast matrix multiplication for binary and ternary CNNs on ARM CPU](https://mlsanity.com/paper/2205.09120/) (2022)
- [PT2-LLM: Post-Training Ternarization for Large Language Models](https://mlsanity.com/paper/2510.03267/) (2025)
- [TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge](https://mlsanity.com/paper/2510.21879/) (2025)
- [3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration](https://mlsanity.com/paper/2105.06250/) (2021)
- [Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge](https://mlsanity.com/paper/2307.02894/) (2023)
- [Full-Precision and Ternarised Neural Networks with Tunnel-Diode Activation Functions: Computing and Physics Perspectives](https://mlsanity.com/paper/2503.04978/) (2025)
- [Ternary Hashing](https://mlsanity.com/paper/2103.09173/) (2021)
- [TinyM2Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices](https://mlsanity.com/paper/2202.04303/) (2022)
- [Ternary Quantization: A Survey](https://mlsanity.com/paper/2303.01505/) (2023)
- [SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2404.19668/) (2024)
- [Matmul or No Matmul in the Era of 1-bit LLMs](https://mlsanity.com/paper/2408.11939/) (2024)
- [A Memory-Efficient Learning Framework for SymbolLevel Precoding with Quantized NN Weights](https://mlsanity.com/paper/2110.06542/) (2021)
- [A Fast Network Exploration Strategy to Profile Low Energy Consumption for Keyword Spotting](https://mlsanity.com/paper/2202.02361/) (2022)
- [Hardware-Robust In-RRAM-Computing for Object Detection](https://mlsanity.com/paper/2205.03996/) (2022)
- [Infrared Domain Adaptation with Zero-Shot Quantization](https://mlsanity.com/paper/2408.13925/) (2024)
- [Learning-Based Symbol Level Precoding: A Memory-Efficient Unsupervised Learning Approach](https://mlsanity.com/paper/2111.08110/) (2021)
- [AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks](https://mlsanity.com/paper/2304.03782/) (2023)

## Abstract (arXiv)

The computation and storage requirements for Deep Neural Networks (DNNs) are usually high. This issue limits their deployability on ubiquitous computing devices such as smart phones, wearables and autonomous drones. In this paper, we propose ternary neural networks (TNNs) in order to make deep learning more resource-efficient. We train these TNNs using a teacher-student approach based on a novel, layer-wise greedy methodology. Thanks to our two-stage training procedure, the teacher network is still able to use state-of-the-art methods such as dropout and batch normalization to increase accuracy and reduce training time. Using only ternary weights and activations, the student ternary network learns to mimic the behavior of its teacher network without using any multiplication. Unlike its -1,1 binary counterparts, a ternary neural network inherently prunes the smaller weights by setting them to zero during training. This makes them sparser and thus more energy-efficient. We design a purpose-built hardware architecture for TNNs and implement it on FPGA and ASIC. We evaluate TNNs on several benchmark datasets and demonstrate up to 3.1x better energy efficiency with respect to the state of the art while also improving accuracy.