# Understanding Convolutional Neural Networks with A Mathematical Model

arXiv: https://arxiv.org/abs/1609.04112 · HTML: https://mlsanity.com/paper/1609.04112/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2016.

## Built on by (most cited first, 30 of 33)

- [DefakeHop: A Light-Weight High-Performance Deepfake Detector](https://mlsanity.com/paper/2103.06929/) (2021)
- [Green Learning: Introduction, Examples and Outlook](https://mlsanity.com/paper/2210.00965/) (2022)
- [VoxelHop: Successive Subspace Learning for ALS Disease Classification Using Structural MRI](https://mlsanity.com/paper/2101.05131/) (2021)
- [AnomalyHop: An SSL-based Image Anomaly Localization Method](https://mlsanity.com/paper/2105.03797/) (2021)
- [Successive Subspace Learning: An Overview](https://mlsanity.com/paper/2103.00121/) (2021)
- [E-PixelHop: An Enhanced PixelHop Method for Object Classification](https://mlsanity.com/paper/2107.02966/) (2021)
- [TGHop: An Explainable, Efficient and Lightweight Method for Texture Generation](https://mlsanity.com/paper/2107.04020/) (2021)
- [Segmentation of Cardiac Structures via Successive Subspace Learning with Saab Transform from Cine MRI](https://mlsanity.com/paper/2107.10718/) (2021)
- [GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds](https://mlsanity.com/paper/2109.11835/) (2021)
- [Convolutional Neural Networks Demystified: A Matched Filtering Perspective Based Tutorial](https://mlsanity.com/paper/2108.11663/) (2021)
- [DefakeHop++: An Enhanced Lightweight Deepfake Detector](https://mlsanity.com/paper/2205.00211/) (2022)
- [PAGER: Progressive Attribute-Guided Extendable Robust Image Generation](https://mlsanity.com/paper/2206.00162/) (2022)
- [Bridging Gap between Image Pixels and Semantics via Supervision: A Survey](https://mlsanity.com/paper/2107.13757/) (2021)
- [A data filling methodology for time series based on CNN and (Bi)LSTM neural networks](https://mlsanity.com/paper/2204.09994/) (2022)
- [Subspace Learning Machine (SLM): Methodology and Performance](https://mlsanity.com/paper/2205.05296/) (2022)
- [GENHOP: An Image Generation Method Based on Successive Subspace Learning](https://mlsanity.com/paper/2210.03689/) (2022)
- [Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach](https://mlsanity.com/paper/2108.10751/) (2021)
- [Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking](https://mlsanity.com/paper/2206.09061/) (2022)
- [Enhancing Edge Intelligence with Highly Discriminant LNT Features](https://mlsanity.com/paper/2312.14968/) (2023)
- [Demystifying the Effect of Receptive Field Size in U-Net Models for Medical Image Segmentation](https://mlsanity.com/paper/2406.16701/) (2024)
- [Trends and Challenges in Authorship Analysis: A Review of ML, DL, and LLM Approaches](https://mlsanity.com/paper/2505.15422/) (2025)
- [Statistical Attention Localization (SAL): Methodology and Application to Object Classification](https://mlsanity.com/paper/2208.01823/) (2022)
- [VS-CAM: Vertex Semantic Class Activation Mapping to Interpret Vision Graph Neural Network](https://mlsanity.com/paper/2209.09104/) (2022)
- [Green Steganalyzer: A Green Learning Approach to Image Steganalysis](https://mlsanity.com/paper/2306.04008/) (2023)
- [HyperBank: A Differentiable Bank of Classical Priors for Few-Shot Spheroid Microscopy Segmentation](https://mlsanity.com/paper/2607.10684/) (2026)
- [Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI](https://mlsanity.com/paper/2301.08959/) (2023)
- [LSR: A Light-Weight Super-Resolution Method](https://mlsanity.com/paper/2302.13596/) (2023)
- [A Tiny Machine Learning Model for Point Cloud Object Classification](https://mlsanity.com/paper/2303.10898/) (2023)
- [GWPT: A Green Word-Embedding-based POS Tagger](https://mlsanity.com/paper/2401.07475/) (2024)
- [GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration](https://mlsanity.com/paper/2404.00807/) (2024)

## Abstract (arXiv)

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): 1) why a non-linear activation function is essential at the filter output of every convolutional layer? 2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the "REctified-COrrelations on a Sphere" (RECOS) is proposed to answer these two questions. After the CNN training process, the converged filter weights define a set of anchor vectors in the RECOS model. Anchor vectors represent the frequently occurring patterns (or the spectral components). The necessity of rectification is explained using the RECOS model. Then, the behavior of a two-layer RECOS system is analyzed and compared with its one-layer counterpart. The LeNet-5 and the MNIST dataset are used to illustrate discussion points. Finally, the RECOS model is generalized to a multi-layer system with the AlexNet as an example. Keywords: Convolutional Neural Network (CNN), Nonlinear Activation, RECOS Model, Rectified Linear Unit (ReLU), MNIST Dataset.