@promila

Here is the link for CNN architecture and you can continue with the playlist. However, if you have time this series is pretty good.

https://youtu.be/jNW1Hi7Yi4c

Hello,

I agree with Alireza as Keras is really a very useful tool for building networks.

Also, have you considered an online university course such as through Coursera which has several courses on CNNs? You don't always have to pay for these courses but they can be really valuable in providing a framework to learn something and many of the courses have suggestions of further reading that is related to the subject.

Best wishes with your research,

Mary

Thanks a lot @all. Actually I am following youtube videos, coursera and using keras in my project. Just trying to know is there anything more to learn with more detail.

I noticed on Coursera that there was a project using CNNs. But if you are already looking there and also edX (and any other university learning sites), here are some articles, apologies if you have already seen them:

https://towardsdatascience.com/building-a-convolutional-neural-network-cnn-in-keras-329fbbadc5f5

https://victorzhou.com/blog/keras-cnn-tutorial/

https://www.tutorialspoint.com/keras/keras_convolution_neural_network.htm

https://machinelearningmastery.com/how-to-develop-a-cnn-from-scratch-for-cifar-10-photo-classification/

https://elitedatascience.com/keras-tutorial-deep-learning-in-python

Hopefully one or more of these will help fill in some detail for you.

Mary

I suggest those for you:

• This pretty book: "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems" for the author Aurelien Geron.
• This blog: https://machinelearningmastery.com/how-to-use-transfer-learning-when-developing-convolutional-neural-network-models/
• You can learn a lot from this youtube channel: https://www.youtube.com/channel/UC68KSmHePPePCjW4v57VPQg

https://towardsdatascience.com/convolutional-neural-networks-explained-9cc5188c4939

If you're willing to learn in detail you need to first give information on what level you're currently at. I mean as in mathematical aspects of machine learning. If you're already acquainted and have good hold over those aspects then I'd suggest a book.