# Attentional Neural Network: Feature Selection Using Cognitive Feedback

arXiv: https://arxiv.org/abs/1411.5140 · HTML: https://mlsanity.com/paper/1411.5140/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2014.

## Built on by (most cited first, 8 of 8)

- [Sequential Attention for Feature Selection](https://mlsanity.com/paper/2209.14881/) (2022)
- [Neural Attention Models in Deep Learning: Survey and Taxonomy](https://mlsanity.com/paper/2112.05909/) (2021)
- [Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition](https://mlsanity.com/paper/2110.04954/) (2021)
- [SAND: One-Shot Feature Selection with Additive Noise Distortion](https://mlsanity.com/paper/2505.03923/) (2025)
- [The Origin of Self-Attention: Pairwise Affinity Matrices in Feature Selection and the Emergence of Self-Attention](https://mlsanity.com/paper/2507.14560/) (2025)
- [Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects](https://mlsanity.com/paper/2109.03391/) (2021)
- [Redundancy-optimized Multi-head Attention Networks for Multi-View Multi-Label Feature Selection](https://mlsanity.com/paper/2511.12462/) (2025)
- [Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting](https://mlsanity.com/paper/2607.21200/) (2026)

## Abstract (arXiv)

Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or difficult segmentation problems. Our system is modular and extensible. It is also easy to train and cheap to run, and yet can accommodate complex behaviors. We obtain classification accuracy better than or competitive with state of art results on the MNIST variation dataset, and successfully disentangle overlaid digits with high success rates. We view such a general purpose framework as an essential foundation for a larger system emulating the cognitive abilities of the whole brain.