# Feature Imitating Networks

arXiv: https://arxiv.org/abs/2110.04831 · HTML: https://mlsanity.com/paper/2110.04831/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 10 Oct 2021.

## Builds on (most cited first, 5 of 5)

- [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)
- [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020)
- [Towards Alzheimer's Disease Classification through Transfer Learning](https://mlsanity.com/paper/1711.11117/) (2017)
- [Artifact Detection and Correction in EEG data: A Review](https://mlsanity.com/paper/2106.13081/) (2021)

## Built on by (most cited first, 6 of 6)

- [MambaNet: A Hybrid Neural Network for Predicting the NBA Playoffs](https://mlsanity.com/paper/2210.17060/) (2022)
- [Feature Imitating Networks Enhance The Performance, Reliability And Speed Of Deep Learning On Biomedical Image Processing Tasks](https://mlsanity.com/paper/2306.14572/) (2023)
- [The Broad Impact of Feature Imitation: Neural Enhancements Across Financial, Speech, and Physiological Domains](https://mlsanity.com/paper/2309.12279/) (2023)
- [Different Algorithms (Might) Uncover Different Patterns: A Brain-Age Prediction Case Study](https://mlsanity.com/paper/2402.09464/) (2024)
- [An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals](https://mlsanity.com/paper/2405.19356/) (2024)
- [ECG-SleepNet: Deep Learning-Based Comprehensive Sleep Stage Classification Using ECG Signals](https://mlsanity.com/paper/2412.01929/) (2024)

## Abstract (arXiv)

In this paper, we introduce a novel approach to neural learning: the Feature-Imitating-Network (FIN). A FIN is a neural network with weights that are initialized to reliably approximate one or more closed-form statistical features, such as Shannon's entropy. In this paper, we demonstrate that FINs (and FIN ensembles) provide best-in-class performance for a variety of downstream signal processing and inference tasks, while using less data and requiring less fine-tuning compared to other networks of similar (or even greater) representational power. We conclude that FINs can help bridge the gap between domain experts and machine learning practitioners by enabling researchers to harness insights from feature-engineering to enhance the performance of contemporary representation learning approaches.