# Brain inspired neuronal silencing mechanism to enable reliable sequence identification

arXiv: https://arxiv.org/abs/2203.13028 · HTML: https://mlsanity.com/paper/2203.13028/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 41 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures](https://mlsanity.com/paper/1903.06379/) (2019)
- [Learning Features for Offline Handwritten Signature Verification using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1705.05787/) (2017)
- [Significant anisotropic neuronal refractory period plasticity](https://mlsanity.com/paper/2109.02041/) (2021)
- [evt_MNIST: A spike based version of traditional MNIST](https://mlsanity.com/paper/1604.06751/) (2016)
- [Putting a bug in ML: The moth olfactory network learns to read MNIST](https://mlsanity.com/paper/1802.05405/) (2018)
- [Neuronal Response Impedance Mechanism Implementing Cooperative Networks with Low Firing Rates and Microseconds Precision](https://mlsanity.com/paper/1411.5258/) (2014)
- [Fast Reversible Learning based on Neurons functioning as Anisotropic Multiplex Hubs](https://mlsanity.com/paper/1707.06501/) (2017)

## Built on by (most cited first, 2 of 2)

- [Efficient shallow learning as an alternative to deep learning](https://mlsanity.com/paper/2211.11106/) (2022)
- [Role of Delay in Brain Dynamics](https://mlsanity.com/paper/2410.11384/) (2024)

## Abstract (arXiv)

Real-time sequence identification is a core use-case of artificial neural networks (ANNs), ranging from recognizing temporal events to identifying verification codes. Existing methods apply recurrent neural networks, which suffer from training difficulties; however, performing this function without feedback loops remains a challenge. Here, we present an experimental neuronal long-term plasticity mechanism for high-precision feedforward sequence identification networks (ID-nets) without feedback loops, wherein input objects have a given order and timing. This mechanism temporarily silences neurons following their recent spiking activity. Therefore, transitory objects act on different dynamically created feedforward sub-networks. ID-nets are demonstrated to reliably identify 10 handwritten digit sequences, and are generalized to deep convolutional ANNs with continuous activation nodes trained on image sequences. Counterintuitively, their classification performance, even with a limited number of training examples, is high for sequences but low for individual objects. ID-nets are also implemented for writer-dependent recognition, and suggested as a cryptographic tool for encrypted authentication. The presented mechanism opens new horizons for advanced ANN algorithms.