# Selective Embedding for Deep Learning

arXiv: https://arxiv.org/abs/2507.13399 · HTML: https://mlsanity.com/paper/2507.13399/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 60 references that are in the map.
- First posted on arXiv 16 Jul 2025.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Subdomain Adaptation Network for Image Classification](https://mlsanity.com/paper/2106.09388/) (2021)
- [Intelligent fault diagnosis of worm gearbox based on adaptive CNN using amended gorilla troop optimization with quantum gate mutation strategy](https://mlsanity.com/paper/2403.13036/) (2024)
- [Towards a Universal Vibration Analysis Dataset: A Framework for Transfer Learning in Predictive Maintenance and Structural Health Monitoring](https://mlsanity.com/paper/2504.11581/) (2025)

## Built on by (most cited first, 1 of 1)

- [Industrial Steel Slag Flow Data Loading Method for Deep Learning Applications](https://mlsanity.com/paper/2509.00034/) (2025)

## Abstract (arXiv)

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and performance often deteriorates under nonstationary conditions and across dissimilar domains, especially when using time-domain data. Conventional single-channel or parallel multi-source data loading strategies either limit generalization or increase computational costs. This study introduces selective embedding, a novel data loading strategy, which alternates short segments of data from multiple sources within a single input channel. Drawing inspiration from cognitive psychology, selective embedding mimics human-like information processing to reduce model overfitting, enhance generalization, and improve computational efficiency. Validation is conducted using six time-domain datasets, demonstrating that the proposed method consistently achieves high classification accuracy across various deep learning architectures while significantly reducing training times. The approach proves particularly effective for complex systems with multiple data sources, offering a scalable and resource-efficient solution for real-world applications in healthcare, heavy machinery, marine, railway, and agriculture, where robustness and adaptability are critical.