# Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification

arXiv: https://arxiv.org/abs/1902.02771 · HTML: https://mlsanity.com/paper/1902.02771/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2019.

## Built on by (most cited first, 19 of 19)

- [Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2109.14545/) (2021)
- [A Survey on Failure Analysis and Fault Injection in AI Systems](https://mlsanity.com/paper/2407.00125/) (2024)
- [Characterizing and Measuring the Similarity of Neural Networks with Persistent Homology](https://mlsanity.com/paper/2101.07752/) (2021)
- [Insights on Neural Representations for End-to-End Speech Recognition](https://mlsanity.com/paper/2205.09456/) (2022)
- [Frequency Disentangled Residual Network](https://mlsanity.com/paper/2109.12556/) (2021)
- [DNN Modularization via Activation-Driven Training](https://mlsanity.com/paper/2411.01074/) (2024)
- [Deep learning for multi-label classification of coral conditions in the Indo-Pacific via underwater photogrammetry](https://mlsanity.com/paper/2403.05930/) (2024)
- [Novel Deep Learning Pipeline for Automatic Weapon Detection](https://mlsanity.com/paper/2309.16654/) (2023)
- [Feature Fusion for Human Activity Recognition using Parameter-Optimized Multi-Stage Graph Convolutional Network and Transformer Models](https://mlsanity.com/paper/2406.16638/) (2024)
- [SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performance](https://mlsanity.com/paper/2407.08232/) (2024)
- [TrIM, Triangular Input Movement Systolic Array for Convolutional Neural Networks: Dataflow and Analytical Modelling](https://mlsanity.com/paper/2408.01254/) (2024)
- [Constructive Interpretability with CoLabel: Corroborative Integration, Complementary Features, and Collaborative Learning](https://mlsanity.com/paper/2205.10011/) (2022)
- [Deep learning forward and reverse primer design to detect SARS-CoV-2 emerging variants](https://mlsanity.com/paper/2209.13591/) (2022)
- [Optimization of Topology-Aware Job Allocation on a High-Performance Computing Cluster by Neural Simulated Annealing](https://mlsanity.com/paper/2302.03517/) (2023)
- [Integrating Features for Recognizing Human Activities through Optimized Parameters in Graph Convolutional Networks and Transformer Architectures](https://mlsanity.com/paper/2408.16442/) (2024)
- [Deep Feature Response Discriminative Calibration](https://mlsanity.com/paper/2411.13582/) (2024)
- [FLAIR: Frequency- and Locality-Aware Implicit Neural Representations](https://mlsanity.com/paper/2508.13544/) (2025)
- [Machine learning approach to single-shot multiparameter estimation for the non-linear Schr"odinger equation](https://mlsanity.com/paper/2509.18479/) (2025)
- [A Survey on Semantic Communication for Vision: Categories, Frameworks, Enabling Techniques, and Applications](https://mlsanity.com/paper/2601.22202/) (2026)

## Abstract (arXiv)

The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of dataset-specific CNN architecture, which mostly performed by either experience or expertise is a time-consuming and error-prone process. To automate the process of learning a CNN architecture, this paper attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets. The CNN architectures, and recently datasets also, are categorized as deep, shallow, wide, etc. This paper tries to formalize these terms along with answering the following questions. (i) What is the impact of deeper/shallow architectures on the performance of the CNN w.r.t. FC layers?, (ii) How the deeper/wider datasets influence the performance of CNN w.r.t. FC layers?, and (iii) Which kind of architecture (deeper/ shallower) is better suitable for which kind of (deeper/ wider) datasets. To address these findings, we have performed experiments with three CNN architectures having different depths. The experiments are conducted by varying the number of FC layers. We used four widely used datasets including CIFAR-10, CIFAR-100, Tiny ImageNet, and CRCHistoPhenotypes to justify our findings in the context of the image classification problem. The source code of this research is available at https://github.com/shabbeersh/Impact-of-FC-layers.