An Introduction to Convolutional Neural Networks

By Keiron O'Shea, Ryan Nash. arXiv.org, 2015

4,138 citations recorded by the source corpus.

The field of machine learning has taken a dramatic twist in recent times, with the rise of the Artificial Neural Network (ANN). These biologically inspired computational models are able to far exceed the performance of previous forms of artificial intelligence in common machine learning tasks. One of the most impressive forms of ANN architecture is that of the Convolutional Neural Network (CNN). CNNs are primarily used to solve difficult image-driven pattern recognition tasks and with their precise yet simple architecture, offers a simplified method of getting started with ANNs. This document provides a brief introduction to CNNs, discussing recently published papers and newly formed techniques in developing these brilliantly fantastic image recognition models. This introduction assumes you are familiar with the fundamentals of ANNs and machine learning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f46714d200d69eb9cb5cce176297b89a3f5e3a2c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Houssem Maghrebi
2. Thibault Portigliatti
3. Sharareh R. Niakan Kalhori
4. Emmanuel Prouff
5. Gianni Barlacchi
6. Tong Zhang
7. Wei Zhang
8. Luís Pinto-Coelho

In Computer Vision and Pattern Recognition

1. Sharareh R. Niakan Kalhori
2. Emmanuel Prouff
3. Gianni Barlacchi
4. Tong Zhang
5. Imen Charfi
6. Wei Zhang
7. Luís Pinto-Coelho
8. Luca Pappalardo

Citations in the corpus

• A Survey on Deep Learning for Human Mobility (2020, background): “A mathematical formalization of CNNs can be found in Reference [207].”
• How Artificial Intelligence Is Shaping Medical Imaging Technology: A Survey of Innovations and Applications (2023, background): “Current architectures follow a structured sequence of layers, each with specific functions to process and extract features from the input data [23].”
• MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques (2023, methodology): “In image processing, the most successful techniques currently used are Convolutional Neural Networks (CNNs), as they have many layers and high diagnostic accuracy if the number of input images is high [9, 10].”
• Breaking Cryptographic Implementations Using Deep Learning Techniques (2016, background): “A Convolutional Neural Network (CNN) is a specific kind of neural network built by stacking the following layers [31,40]:”
• EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain (2024, methodology): “Specifically, we utilize ViT [12] to capture the spatial contextual information at different levels for images and employ CNN [13] to extract the local information present across multiple scales.”
• Deep CNN for Brain Tumor Classification (2021, background): “CNN represents the most exploited in image processing field due to its ability to recognize patterns in images [54].”