I would like to suggest you first to understand it conceptually : https://medium.com/analytics-vidhya/convolutional-neural-networks-cnn-explained-step-by-step-69137a54e5e7

https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks/

What application field?

why not spending time wathchin LeCun lecture here :https://www.youtube.com/watch?v=oOB4evKlEmQ&list=PL80I41oVxglJ0kTDV7i3aHBIXe65nTxE7

you might want to check ths Chapter Issues in Training a Convolutional Neural Network Model for ...

Hi, if you cannot find exactly what you thought you will get, then its a good research question to answer.

a bit of guideline that can help based on my understanding

1. Group the applications or problem that computer vision scientist always aims to solves such Segmentation problems, classification and image-to-image translation. You can then find a survey or review papers based on the particular problem and see how researchers are weighting the solution of deep learning(CNN) vs traditional techniques which will then give you better pros and cons with evidence.

2. You could then select review and survey works from different application domains where these techniques(deep learning ) are been used such as in face recognition, biodiversity applications, human activity recognition and many other domains. This will give you a picture of how researchers of that particular domain of application are adapting the techniques.

Attached is one of the article that you can start with

1. Article A Survey on Deep Learning: Algorithms, Techniques, and Applications

As far as I know convolutional neural networks are usually not trained while processing a hitherto unknown image. Consider a medical image with a structure in it. In order to do a segmentation, an algorithm might start on a border and follow it. On its way, there is a left area and a right area. Their properties like texture, and color, may change gradually in an unforseeable way. An algorithm can cope with that by updating its internal state, but a convolutional neural network is not designed to do this.

Or imagine an image with polygons on it. Even if some lines might be blurred and portions of them missing, an algorithm could be able the reconstruct them by knowing about the nature of the underlying polygon, as opposed to convolutional neural networks.

Attached is an image with an enclosed area. The problem is now to classify the blue, red, white, green, and yellow square as being inside or outside. With an algorithm this would be no problem: it would count the number of border crossings starting at a square and marching away. But a convolutional neural network has no built-in capability of executing simple algorithms like counting events.

Regards,

Joachim

Francis Jesmar Perez Montalbo

https://www.quora.com/What-are-the-advantages-and-disadvantages-of-fully-connected-layers-in-convolutional-neural-network

https://www.researchgate.net/post/What_are_Convolutional_Neural_Networks_CNN_weakness

https://intellipaat.com/community/21886/advantages-and-disadvantages-of-neural-networks

https://cs.stackexchange.com/questions/75118/what-are-the-drawbacks-of-fully-convolutional-neural-networks

https://www.experfy.com/blog/pros-and-cons-of-neural-networks

I recommend handbooks and specialized books about Convolutional Neural Networks

https://b-ok.cc/book/3432255/35d065

https://b-ok.cc/book/3664285/bd47e7

https://b-ok.cc/book/2740843/6cf9f9

https://b-ok.cc/book/5258319/c6ce54

https://b-ok.cc/book/3495450/4d0281

https://b-ok.cc/book/3308156/da09f9

Thank you everyone who helped! I'll be reading it and try to summarize this... Hope everyone is ok! Please be safe my friends!

May be these links would help you,

https://www.ripublication.com/ijaer19/ijaerv14n3_24.pdf

https://www.quora.com/What-are-the-advantages-and-disadvantages-of-fully-connected-layers-in-convolutional-neural-network

Not sure this directly relates to your question, but here is a database of some papers on CNNs every data scientist might find helpful. https://towardsdatascience.com/5-papers-on-cnns-every-data-scientist-should-read-c689b686aa83

I would suggest the following paper:

A Survey of the Recent Architectures of Deep Convolutional Neural Networks,

DOI: https://doi.org/10.1007/s10462-020-09825-6

In-depth analysis is presented here. Performance of CNN in terms of action recognition.

Article Aggressive Action Estimation: A Comprehensive Review on Neur...

Please see this paper: Conference Paper Aplicación de una Red Neuronal Convolucional para el Reconoc...

Hi,

in this (open access) paper: Article Enhanced robustness of convolutional networks with a push–pu...

we discussed the problems of robustness of CNNs to corruptions/perturbations of the test images that have not been seen during training, and proposed a new type of layer that improves the generalization.

these are all amazing works! Thank you so much for the help everyone!

A Survey of the Recent Architectures of Deep Convolutional Neural Networks,

DOI: https://doi.org/10.1007/s10462-020-09825-6

https://arxiv.org/ftp/arxiv/papers/1901/1901.06032.pdf

Article A Survey of the Recent Architectures of Deep Convolutional N...