# Full-Precision and Ternarised Neural Networks with Tunnel-Diode Activation Functions: Computing and Physics Perspectives

arXiv: https://arxiv.org/abs/2503.04978 · HTML: https://mlsanity.com/paper/2503.04978/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 84 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)
- [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Next Generation Reservoir Computing](https://mlsanity.com/paper/2106.07688/) (2021)
- [Ternary Neural Networks for Resource-Efficient AI Applications](https://mlsanity.com/paper/1609.00222/) (2016)
- [NICE: Noise Injection and Clamping Estimation for Neural Network Quantization](https://mlsanity.com/paper/1810.00162/) (2018)
- [Analogue and Physical Reservoir Computing Using Water Waves](https://mlsanity.com/paper/2306.09095/) (2023)
- [Controlling Chaos Using Edge Computing Hardware](https://mlsanity.com/paper/2406.12876/) (2024)
- [RTN: Reparameterized Ternary Network](https://mlsanity.com/paper/1912.02057/) (2019)
- [Classical and Quantum Physical Reservoir Computing for Onboard Artificial Intelligence Systems: A Perspective](https://mlsanity.com/paper/2407.04717/) (2024)
- [Quantum-Inspired Neural Network Model of Optical Illusions](https://mlsanity.com/paper/2312.03447/) (2023)
- [Reservoir Computing Using Measurement-Controlled Quantum Dynamics](https://mlsanity.com/paper/2403.01024/) (2024)
- [ON-OFF Neuromorphic ISING Machines using Fowler-Nordheim Annealers](https://mlsanity.com/paper/2406.05224/) (2024)
- [Quantum-tunnelling deep neural network for optical illusion recognition](https://mlsanity.com/paper/2407.11013/) (2024)
- [Physical Reservoir Computing Enabled by Solitary Waves and Biologically-Inspired Nonlinear Transformation of Input Data](https://mlsanity.com/paper/2402.03319/) (2024)
- [xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems](https://mlsanity.com/paper/2405.19065/) (2024)
- [Quantum-Cognitive Neural Networks: Assessing Confidence and Uncertainty with Human Decision-Making Simulations](https://mlsanity.com/paper/2412.08010/) (2024)
- [Mathematics of Neural Networks (Lecture Notes Graduate Course)](https://mlsanity.com/paper/2403.04807/) (2024)

## Built on by (most cited first, 3 of 3)

- [TunnElQNN: A Hybrid Quantum-classical Neural Network for Efficient Learning](https://mlsanity.com/paper/2505.00933/) (2025)
- [Transforming Traditional Neural Networks into Neuromorphic Quantum-Cognitive Models: A Tutorial with Applications](https://mlsanity.com/paper/2503.07681/) (2025)
- [Resonant-Tunnelling Diode Reservoir Computing System for Image Recognition](https://mlsanity.com/paper/2507.15158/) (2025)

## Abstract (arXiv)

The mathematical complexity and high dimensionality of neural networks slow both training and deployment, demanding heavy computational resources. This has driven the search for alternative architectures built from novel components, including new activation functions. Taking a different approach from state-of-the-art neural and neuromorphic computational systems, we employ the current-voltage characteristic of a tunnel diode as a quantum physics-based activation function for deep networks. This tunnel-diode activation function (TDAF) outperforms standard activations in deep architectures, delivering lower loss and higher accuracy in both training and evaluation. We also highlight its promise for implementation in electronic hardware aimed at neuromorphic, ternarised and energy efficient AI systems. Speaking broadly, our work lays a solid foundation for a new bridge between machine learning, semiconductor electronics and quantum physics -- bringing together quantum tunnelling, a phenomenon recognised in six Nobel Prizes (including the 2025 award), and contemporary AI research.