🕷️ Crawler Inspector

[Skip to content](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/CNN/#content_start) - [Regions](https://taylorandfrancis.com/contact/global-offices/) - [ Africa](https://taylorandfrancis.com/africa/) - [ China](https://china.taylorandfrancis.com/) - [ Japan](https://taylorandfrancis.com/japan/) - [ MENA](https://taylorandfrancis.com/mena/) - [Contact](https://taylorandfrancis.com/help/) - [Careers](https://taylorandfrancis.com/about/careers) - [Search](https://taylorandfrancis.com#) [](https://taylorandfrancis.com/ "Click to return to the homepage")  - [Who we serve](https://taylorandfrancis.com/who-we-serve/) Expand submenu - Academia - [Authors](https://taylorandfrancis.com/who-we-serve/academia/authors) - [Journal authors](https://taylorandfrancis.com/who-we-serve/academia/authors/journal-authors) - [Book authors](https://taylorandfrancis.com/who-we-serve/academia/authors/book-authors) - [Faculty/instructors](https://taylorandfrancis.com/who-we-serve/academia/lecturers) - [Librarians](https://taylorandfrancis.com/who-we-serve/academia/librarians/) - [Journal editors](https://taylorandfrancis.com/who-we-serve/academia/journal-editors/) - Industry & government - [Practitioners](https://taylorandfrancis.com/who-we-serve/industry-government/practitioners) - [R\&D professionals](https://taylorandfrancis.com/who-we-serve/industry-government/business) - [Authors](https://taylorandfrancis.com/partnership/commercial/publishing-services/) - [Government](https://taylorandfrancis.com/who-we-serve/industry-government/government) - [Healthcare professionals](https://taylorandfrancis.com/who-we-serve/industry-government/healthcare) - [Marketing & brand managers](https://taylorandfrancis.com/who-we-serve/industry-government/marketing) - Partners - [Societies](https://taylorandfrancis.com/who-we-serve/partners/societies) - [Booksellers](https://taylorandfrancis.com/who-we-serve/partners/booksellers) - [Funders](https://taylorandfrancis.com/who-we-serve/partners/funders) - [Publishers](https://taylorandfrancis.com/who-we-serve/partners/publishers/) - [Knowledge](https://taylorandfrancis.com/knowledge/) Expand submenu - [ Medicine & healthcare](https://taylorandfrancis.com/knowledge/medicine-healthcare/) - [ Education](https://taylorandfrancis.com/knowledge/humanities-and-social-sciences/education/) - [ Business & management](https://taylorandfrancis.com/knowledge/humanities-and-social-sciences/business-management/) - [ Psychology](https://taylorandfrancis.com/knowledge/humanities-and-social-sciences/psychology/) - [ Environmental sciences](https://taylorandfrancis.com/knowledge/science-technology/environmental-sciences/) - [ Bioscience](https://taylorandfrancis.com/knowledge/science-technology/bioscience/) - [ Computer & information sciences](https://taylorandfrancis.com/knowledge/science-technology/computer-information-sciences/) - [ Mathematics](https://taylorandfrancis.com/knowledge/science-technology/mathematics/) - [ Engineering](https://taylorandfrancis.com/knowledge/engineering/) - [ Civil](https://taylorandfrancis.com/knowledge/engineering/civil-engineering/) - [ Electrical](https://taylorandfrancis.com/knowledge/engineering/electrical-engineering/) - [ Industrial & manufacturing](https://taylorandfrancis.com/knowledge/engineering/industrial-manufacturing-engineering) - [ Mechanical](https://taylorandfrancis.com/knowledge/engineering/mechanical-engineering/) - [ Chemical engineering](https://taylorandfrancis.com/knowledge/engineering/chemical-engineering/) - [ Automotive engineering](https://taylorandfrancis.com/knowledge/engineering/automotive-engineering/) - [ Energy and oil](https://taylorandfrancis.com/knowledge/engineering/energy-oil/) - [ Materials science research](https://taylorandfrancis.com/knowledge/engineering/material-science-engineering/) - [Explore our research portfolio](https://taylorandfrancis.com/knowledge/) - [Corporate solutions](https://taylorandfrancis.com/corporate-solutions/) Expand submenu - [Pharmaceutical](https://taylorandfrancis.com/medical-publication-professionals/) - [Finance](https://taylorandfrancis.com/partnership/commercial/research-access/finance/) - [Materials sciences](https://taylorandfrancis.com/corporate-solutions/materials-science-research/) - [Technology](https://taylorandfrancis.com/partnership/commercial/research-access/technology/) - [Law](https://taylorandfrancis.com/partnership/commercial/research-access/law/) - [Automotive engineering](https://taylorandfrancis.com/partnership/commercial/research-access/automotive-industry/) - [Chemical engineering](https://taylorandfrancis.com/partnership/commercial/research-access/chemical-engineering/) - [Energy and oil](https://taylorandfrancis.com/partnership/commercial/research-access/energy/) - [Defense](https://taylorandfrancis.com/partnership/commercial/research-access/defense/) - [Food science](https://taylorandfrancis.com/partnership/commercial/research-access/food-science/) - [News](https://newsroom.taylorandfrancisgroup.com/) Expand submenu - [Newsroom](https://newsroom.taylorandfrancisgroup.com/) - [Insights, analysis, and blogs](https://insights.taylorandfrancis.com/) - [Events](https://taylorandfrancis.com/events/) - [About](https://taylorandfrancis.com/about/) Expand submenu - [Company](https://taylorandfrancis.com/about/) - [Our brands](https://taylorandfrancis.com/about/our-brands/) - [Executive leadership team](https://taylorandfrancis.com/about/executive-leadership-team/) - [Our history](https://taylorandfrancis.com/about/history/) - [Careers](https://taylorandfrancis.com/about/careers/) - [Our policies](https://taylorandfrancis.com/our-policies/) - [Open research](https://taylorandfrancis.com/openresearch/) - [Corporate responsibility](https://taylorandfrancis.com/about/corporate-responsibility/) - [Artificial intelligence (AI)](https://taylorandfrancis.com/about/ai/) - - [Regions](https://taylorandfrancis.com/contact/global-offices/) - [Africa](https://taylorandfrancis.com/africa/) - [ China](https://china.taylorandfrancis.com/) - [ Japan](https://taylorandfrancis.com/japan/) - [MENA](https://taylorandfrancis.com/mena/) - [Contact](https://taylorandfrancis.com/help/) - [Careers](https://taylorandfrancis.com/about/careers) Search Publish with us I want to publish [a book](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/CNN/) [in a journal](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/CNN/) To find out how to publish or submit your book proposal: Go to Author Services \> To find a journal or submit your article to a journal: Go to our journal suggester \> # CNN A convolutional neural network (CNN) is a type of deep learning method that is used for image recognition and processing, as well as signal processing and classification tasks. It is characterized by convolutional layers, pooling operations, and fully connected layers, which result in feature maps. A traditional CNN is made up of convolution and pooling layers alternatively, followed by a fully connected layer to perform classification. CNN-based techniques have evolved as powerful visual models and achieved state-of-the-art performance in solving different problems of computer vision and pattern recognition like object detection and image classification. From: [ICT for Competitive Strategies](https://www.routledge.com/ICT-for-Competitive-Strategies-Proceedings-of-4th-International-Conference-on-Information-and-Communication-Technology-for-Competitive-Strat/Mishra-Dey-Deora-Joshi/p/book/9781003052098) \[2020\], [Biometric Authentication from Photic Stimulated EEG Records](https://www.tandfonline.com/doi/10.1080/08839514.2021.1981660) \[2021\], [Deep Learning in Biometrics](https://www.routledge.com/Deep-Learning-in-Biometrics/Vatsa-Singh-Majumdar/p/book/9781351265003) \[2018\], [Behavior Analysis with Machine Learning Using R,](https://www.tandfonline.com/doi/10.1080/00401706.2022.2087427) \[2022\], [The Dynamics of Vehicles on Roads and Tracks](https://www.routledge.com/Dynamics-of-Vehicles-on-Roads-and-Tracks-Vol-2-Proceedings-of-the-25th-International-Symposium-on-Dynamics-of-Vehicles-on-Roads-and-Tracks-I/Spiryagin-Gordon-Cole-McSweeney/p/book/9781351057189) \[2018\], [Patch-based Segmentation of Latent Fingerprint Images Using Convolutional Neural Network](https://www.tandfonline.com/doi/10.1080/08839514.2018.1526704) \[2019\] more **Related Topics** - [Backpropagation](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/Backpropagation "Backpropagation") - [Computer vision](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/Computer_vision "Computer vision") - [Convolution](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Engineering_support_and_special_topics/Convolution "Convolution") - [Feature vectors](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/Feature_vectors "Feature vectors") - [NLP](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Computer_science/NLP "NLP") - [Overfitting](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Engineering_support_and_special_topics/Overfitting "Overfitting") - Layers **About this page** The research on this page is brought to you by Taylor & Francis Knowledge Centers. This collection is automatically generated from our most recent books and journals on this topic. - [Home](https://taylorandfrancis.com/ "Taylor & Francis") - [Knowledge](https://taylorandfrancis.com/knowledge/) - [Engineering and technology](https://taylorandfrancis.com/knowledge/Engineering_and_technology) - [Artificial intelligence](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence) - CNN ## Explore chapters and articles related to this topic ### A Comprehensive Study on MLP and CNN, and the Implementation of Multi-Class Image Classification using Deep CNN [**View Chapter**](https://doi.org/10.1201/9781003217497) [**Purchase Book**](https://www.routledge.com/Machine-Learning-and-Deep-Learning-Techniques-for-Medical-Science/Devi-Balasubramanian-Ngoc/p/book/9781003217497) *Published in [K. Gayathri Devi](https://www.routledge.com/search?author=K.%20Gayathri%20Devi "Search for more titles by K. Gayathri Devi"), [Kishore Balasubramanian](https://www.routledge.com/search?author=Kishore%20Balasubramanian "Search for more titles by Kishore Balasubramanian"), [Le Anh Ngoc](https://www.routledge.com/search?author=Le%20Anh%20Ngoc "Search for more titles by Le Anh Ngoc"), [Machine Learning and Deep Learning Techniques for Medical Science](https://www.routledge.com/Machine-Learning-and-Deep-Learning-Techniques-for-Medical-Science/Devi-Balasubramanian-Ngoc/p/book/9781003217497), 2022* *[S.P. Balamurugan](https://www.routledge.com/search?author=S.P.%20Balamurugan "Search for more titles by S.P. Balamurugan")* CNN is extensively used for image classification and object detection. It has several advantages over MLP. They are,CNN's are capable of working with image data in 2D. So, there is no need to flatten the input images to 1D like MLP. It helps in retaining the spatial properties of images.It finds the relevant traits without the need for human interventionIt converges faster than the MLP modelIt has the highest accuracy than MLP in image predictionIt is also computationally efficient ### Deep Learning for Medical Dataset Classification Based on Convolutional Neural Networks [**View Chapter**](https://doi.org/10.1201/9781003038450) [**Purchase Book**](https://www.routledge.com/Integrating-Deep-Learning-Algorithms-to-Overcome-Challenges-in-Big-Data-Analytics/Sujatha-Aarthy-Vettriselvan/p/book/9781003038450) *Published in [R. Sujatha](https://www.routledge.com/search?author=R.%20Sujatha "Search for more titles by R. Sujatha"), [S. L. Aarthy](https://www.routledge.com/search?author=S.%20L.%20Aarthy "Search for more titles by S. L. Aarthy"), [R. Vettriselvan](https://www.routledge.com/search?author=R.%20Vettriselvan "Search for more titles by R. Vettriselvan"), [Integrating Deep Learning Algorithms to Overcome Challenges in Big Data Analytics](https://www.routledge.com/Integrating-Deep-Learning-Algorithms-to-Overcome-Challenges-in-Big-Data-Analytics/Sujatha-Aarthy-Vettriselvan/p/book/9781003038450), 2021* *[S. Nathiya](https://www.routledge.com/search?author=S.%20Nathiya "Search for more titles by S. Nathiya"), [R. Sujatha](https://www.routledge.com/search?author=R.%20Sujatha "Search for more titles by R. Sujatha")* Figure 8.2 illustrates the classification framework based on CNNs. In order to achieve the classification of the dataset, the dataset first needs to be preprocessed; then, the data is selected; the data is cleaned; and, finally, the feature extraction method is used (Yadav & Jadhav, 2019). A CNN-based method has been used broadly in medical classification systems. When processing on small datasets, a CNN has the capability of classification with a higher performance. To improve the performance of using CNN methods, there are a few different strategies, including data augmentation and transfer learning (Sarraf & Tofighi, 2016). SVM classifiers are also used in the transfer learning of VGG-16 and Inception-V3 because SVMs also provide efficient performance. Using data augmentation prevents the overfitting of the network model. ### Biometric Monitoring in Healthcare IoT Systems Using Deep Learning [**View Chapter**](https://doi.org/10.1201/9781003054115) [**Purchase Book**](https://www.routledge.com/IoT-Security-Paradigms-and-Applications-Research-and-Practices/Sharma-Bhushan-Debnath/p/book/9781003054115) *Published in [Sudhir Kumar Sharma](https://www.routledge.com/search?author=Sudhir%20Kumar%20Sharma "Search for more titles by Sudhir Kumar Sharma"), [Bharat Bhushan](https://www.routledge.com/search?author=Bharat%20Bhushan "Search for more titles by Bharat Bhushan"), [Narayan C. Debnath](https://www.routledge.com/search?author=Narayan%20C.%20Debnath "Search for more titles by Narayan C. Debnath"), [IoT Security Paradigms and Applications](https://www.routledge.com/IoT-Security-Paradigms-and-Applications-Research-and-Practices/Sharma-Bhushan-Debnath/p/book/9781003054115), 2020* *[Shefali Arora](https://www.routledge.com/search?author=Shefali%20Arora "Search for more titles by Shefali Arora"), [Veenu](https://www.routledge.com/search?author=Veenu "Search for more titles by Veenu"), [M.P.S. Bhatia](https://www.routledge.com/search?author=M.P.S.%20Bhatia "Search for more titles by M.P.S. Bhatia"), [Gurjot Kaur](https://www.routledge.com/search?author=Gurjot%20Kaur "Search for more titles by Gurjot Kaur")* Convolutional neural networks (convnets, CNNs) are mainly used for image classification. Originally developed by Geoffery Hinton, they are ideal in detecting objects in different positions in different images. These networks make use of convolution. Given 1D input x and a filter k, this operation is defined as: y\[n\]=(x\*k)\[n\]∑−∞∞x\[m\]k\[n−m\] ### Deep learning framework for biometric authentication using retinal images [**View Article**](https://www.tandfonline.com/doi/10.1080/21681163.2022.2111718) [**Journal Information**](https://www.tandfonline.com/journals/TCIV) *Published in [Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization](https://www.tandfonline.com/journals/TCIV), 2023* *[Jarina B. Mazumdar](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Jarina%20B.%20Mazumdar "Search for more articles by Jarina B. Mazumdar"), [S. R. Nirmala](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=S.%20R.%20Nirmala "Search for more articles by S. R. Nirmala")* The objective of the proposed work is to establish a robust retinal identification using colour retinal images as input. We have adopted a CNN model to solve this problem. CNN is a powerful architecture which is extensively used in image processing and pattern recognition. The structure of CNN includes a feature extraction layer where the input of each neuron is connected to the local receptive field of the former layer and extracts the local feature. The next layer is feature map layer, where features are calculated as convolution between receptive field and the filter. The outputs are collected as feature map. Furthermore, the filters in the same feature map plane have identical weight, so that the entire input image can be studied with the same feature detector. This is the benefit of convolution network with respect to the neuronal network connected to each other. Furthermore, the structure of feature map uses the sigmoid function as an activation function of the convolution network, which makes the feature map shift invariant. This makes CNN advantageous over classical machine learning approaches. ### A Deep Learning Approach for Classification of Dentinal Tubule Occlusions [**View Article**](https://www.tandfonline.com/doi/10.1080/08839514.2022.2094446) [**Journal Information**](https://www.tandfonline.com/journals/UAAI) *Published in [Applied Artificial Intelligence](https://www.tandfonline.com/journals/UAAI), 2022* *[Anday Duru](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Anday%20Duru "Search for more articles by Anday Duru"), [İsmail Rakıp Karaş](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=%C4%B0smail%20Rak%C4%B1p%20Kara%C5%9F "Search for more articles by İsmail Rakıp Karaş"), [Fatih Karayürek](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Fatih%20Karay%C3%BCrek "Search for more articles by Fatih Karayürek"), [Aydın Gülses](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Ayd%C4%B1n%20G%C3%BClses "Search for more articles by Aydın Gülses")* The architecture of CNN was biologically inspired by the organization of the Visual Cortex (Fukushima 1988; Hubel and Wiesel 1968). Particularly, the structure of the visual system behaves in such a way as to encode visual relations layer by layer. Each layer gradually represents more specific features (Hubel and Wiesel 1962). CNN is designed to emulate the same organizational behavior. CNN is a type of deep learning model, and they are one of the most powerful tools to do image recognition, classifications, segmentation, and many more tasks (Girshick et al. 2014; Ren et al. 2017; Sermanet et al. 2014). Each input image passes through a series of building blocks to classify relevant objects. Building blocks are the sequence of layers used to assign weights and biases to neurons. ### Prostate cancer classification with MRI using Taylor-Bird Squirrel Optimization based Deep Recurrent Neural Network [**View Article**](https://www.tandfonline.com/doi/10.1080/13682199.2023.2165242) [**Journal Information**](https://www.tandfonline.com/journals/YIMS) *Published in [The Imaging Science Journal](https://www.tandfonline.com/journals/YIMS), 2022* *[Goddumarri Vijay Kumar](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Goddumarri%20Vijay%20Kumar "Search for more articles by Goddumarri Vijay Kumar"), [Mohammed Ismail Bellary](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Mohammed%20Ismail%20Bellary "Search for more articles by Mohammed Ismail Bellary"), [Thota Bhaskara Reddy](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Thota%20Bhaskara%20Reddy "Search for more articles by Thota Bhaskara Reddy")* The pre-processed result is the noise-free image , which is passed as input to the segmentation stage for partitioning the image into a number of segments using the CNN approach \[47,48\]. CNN is comprised with the number of self-optimized neurons. It is the deep learning network model that automatically divides the image into different segments. For tasks including object detection, image segmentation, face recognition, and others, CNN is a frequently utilized technique. The CNN effectively completes the segmentation process since it is made up of multilayers connected to neurons. CNN learns the pre-processed output and segments the image automatically as a result of its transfer learning and automated features. The CNN structure consists of the input layer, hidden layer, and output layer. The hidden layer of this network topology consists of the convolutional layer, the pooling layer, and the fully connected layer. [Scroll to Top](https://taylorandfrancis.com/knowledge/Engineering_and_technology/Artificial_intelligence/CNN/#newtfg) ##### Explore - [Our company](https://taylorandfrancis.com/about/) - [Our leadership team](https://taylorandfrancis.com/about/executive-leadership-team/) - [Careers](https://taylorandfrancis.com/careers/) - [Contact us](https://taylorandfrancis.com/contact/) - [Taylor & Francis Online](https://www.tandfonline.com/) - [Routledge.com](https://www.routledge.com/) ##### Our policies - [Privacy policy](https://www.informa.com/privacy-policy/) - [Cookies](https://taylorandfrancis.com/cookies/) - [Terms and conditions](https://taylorandfrancis.com/terms-and-conditions/) - [Accessibility](https://taylorandfrancis.com/about/corporate-responsibility/accessibility-at-taylor-francis/) - [Modern slavery](https://www.informa.com/globalassets/documents/corporate-responsibility/informa-modern-slavery-statement-2019.pdf) - [Anti-bribery and corruption](https://www.informa.com/globalassets/documents/policies/inf_anti-bribery-global-policy.pdf) - [Corporate responsibility](https://taylorandfrancis.com/about/corporate-responsibility/) - [Gender pay gap report](https://www.informa.com/uk-colleagues-and-pay-report-2020/) - [Code of conduct for conference proceedings](https://authorservices.taylorandfrancis.com/editorial-policies/code-of-conduct-for-conference-proceedings-organizers/) ##### Information for - [Book Authors](https://taylorandfrancis.com/who-we-serve/academia/authors/book-authors/) - [Journal Authors](https://taylorandfrancis.com/who-we-serve/academia/authors/journal-authors/) - [Librarians](https://taylorandfrancis.com/who-we-serve/academia/librarians/) - [Editors](https://taylorandfrancis.com/who-we-serve/academia/journal-editors/) - [Societies](https://taylorandfrancis.com/who-we-serve/partners/societies/) - [Booksellers](https://taylorandfrancis.com/who-we-serve/partners/booksellers/) - [Press and media](https://newsroom.taylorandfrancisgroup.com/) ##### Support - [Customer support](https://taylorandfrancis.com/help/) - [Rights and permissions](https://taylorandfrancis.com/corporate-solutions/solutions/) - [Royalty recipients](https://www.routledge.com/faqs/author-faqs/royalties) ##### Follow us Taylor & Francis ##### Informa ##### Routledge **© 2026 Informa plc.** Taylor & Francis is a division of Informa plc Registered in England & Wales No. 3099067 5 Howick Place \| London \| SW1P 1WG

Explore chapters and articles related to this topic ### Deep learning framework for biometric authentication using retinal images *Published in [Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization](https://www.tandfonline.com/journals/TCIV), 2023* *[Jarina B. Mazumdar](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Jarina%20B.%20Mazumdar "Search for more articles by Jarina B. Mazumdar"), [S. R. Nirmala](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=S.%20R.%20Nirmala "Search for more articles by S. R. Nirmala")* The objective of the proposed work is to establish a robust retinal identification using colour retinal images as input. We have adopted a CNN model to solve this problem. CNN is a powerful architecture which is extensively used in image processing and pattern recognition. The structure of CNN includes a feature extraction layer where the input of each neuron is connected to the local receptive field of the former layer and extracts the local feature. The next layer is feature map layer, where features are calculated as convolution between receptive field and the filter. The outputs are collected as feature map. Furthermore, the filters in the same feature map plane have identical weight, so that the entire input image can be studied with the same feature detector. This is the benefit of convolution network with respect to the neuronal network connected to each other. Furthermore, the structure of feature map uses the sigmoid function as an activation function of the convolution network, which makes the feature map shift invariant. This makes CNN advantageous over classical machine learning approaches. ### A Deep Learning Approach for Classification of Dentinal Tubule Occlusions *Published in [Applied Artificial Intelligence](https://www.tandfonline.com/journals/UAAI), 2022* *[Anday Duru](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Anday%20Duru "Search for more articles by Anday Duru"), [İsmail Rakıp Karaş](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=%C4%B0smail%20Rak%C4%B1p%20Kara%C5%9F "Search for more articles by İsmail Rakıp Karaş"), [Fatih Karayürek](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Fatih%20Karay%C3%BCrek "Search for more articles by Fatih Karayürek"), [Aydın Gülses](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Ayd%C4%B1n%20G%C3%BClses "Search for more articles by Aydın Gülses")* The architecture of CNN was biologically inspired by the organization of the Visual Cortex (Fukushima 1988; Hubel and Wiesel 1968). Particularly, the structure of the visual system behaves in such a way as to encode visual relations layer by layer. Each layer gradually represents more specific features (Hubel and Wiesel 1962). CNN is designed to emulate the same organizational behavior. CNN is a type of deep learning model, and they are one of the most powerful tools to do image recognition, classifications, segmentation, and many more tasks (Girshick et al. 2014; Ren et al. 2017; Sermanet et al. 2014). Each input image passes through a series of building blocks to classify relevant objects. Building blocks are the sequence of layers used to assign weights and biases to neurons. ### Prostate cancer classification with MRI using Taylor-Bird Squirrel Optimization based Deep Recurrent Neural Network *Published in [The Imaging Science Journal](https://www.tandfonline.com/journals/YIMS), 2022* *[Goddumarri Vijay Kumar](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Goddumarri%20Vijay%20Kumar "Search for more articles by Goddumarri Vijay Kumar"), [Mohammed Ismail Bellary](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Mohammed%20Ismail%20Bellary "Search for more articles by Mohammed Ismail Bellary"), [Thota Bhaskara Reddy](https://www.tandfonline.com/action/doSearch?field1=Contrib&text1=Thota%20Bhaskara%20Reddy "Search for more articles by Thota Bhaskara Reddy")* The pre-processed result is the noise-free image , which is passed as input to the segmentation stage for partitioning the image into a number of segments using the CNN approach \[47,48\]. CNN is comprised with the number of self-optimized neurons. It is the deep learning network model that automatically divides the image into different segments. For tasks including object detection, image segmentation, face recognition, and others, CNN is a frequently utilized technique. The CNN effectively completes the segmentation process since it is made up of multilayers connected to neurons. CNN learns the pre-processed output and segments the image automatically as a result of its transfer learning and automated features. The CNN structure consists of the input layer, hidden layer, and output layer. The hidden layer of this network topology consists of the convolutional layer, the pooling layer, and the fully connected layer.