# The mechanism underlying successful deep learning

arXiv: https://arxiv.org/abs/2305.18078 · HTML: https://mlsanity.com/paper/2305.18078/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Deep Learning in Neural Networks: An Overview](https://mlsanity.com/paper/1404.7828/) (2014)
- [Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent](https://mlsanity.com/paper/1607.01981/) (2016)
- [Enhancing the accuracies by performing pooling decisions adjacent to the output layer](https://mlsanity.com/paper/2303.05800/) (2023)

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

- [Towards a universal mechanism for successful deep learning](https://mlsanity.com/paper/2309.07537/) (2023)
- [Unified CNNs and transformers underlying learning mechanism reveals multi-head attention modus vivendi](https://mlsanity.com/paper/2501.12900/) (2025)
- [Low-latency vision transformers via large-scale multi-head attention](https://mlsanity.com/paper/2506.23832/) (2025)
- [Self-attention vector output similarities reveal how machines pay attention](https://mlsanity.com/paper/2512.21956/) (2025)

## Abstract (arXiv)

Deep architectures consist of tens or hundreds of convolutional layers (CLs) that terminate with a few fully connected (FC) layers and an output layer representing the possible labels of a complex classification task. According to the existing deep learning (DL) rationale, the first CL reveals localized features from the raw data, whereas the subsequent layers progressively extract higher-level features required for refined classification. This article presents an efficient three-phase procedure for quantifying the mechanism underlying successful DL. First, a deep architecture is trained to maximize the success rate (SR). Next, the weights of the first several CLs are fixed and only the concatenated new FC layer connected to the output is trained, resulting in SRs that progress with the layers. Finally, the trained FC weights are silenced, except for those emerging from a single filter, enabling the quantification of the functionality of this filter using a correlation matrix between input labels and averaged output fields, hence a well-defined set of quantifiable features is obtained. Each filter essentially selects a single output label independent of the input label, which seems to prevent high SRs; however, it counterintuitively identifies a small subset of possible output labels. This feature is an essential part of the underlying DL mechanism and is progressively sharpened with layers, resulting in enhanced signal-to-noise ratios and SRs. Quantitatively, this mechanism is exemplified by the VGG-16, VGG-6, and AVGG-16. The proposed mechanism underlying DL provides an accurate tool for identifying each filter's quality and is expected to direct additional procedures to improve the SR, computational complexity, and latency of DL.