[mikewarot]

While diving into the nitty-gritty of exactly how gradient descent and backpropagation work might (and only might) be beyond you, it's a temporary thing. You can learn it all, if you want, at some point.

Thanks to TensorFlow, and Keras, etc.. you can just use the work of others as you learn AI and ML, just as many have no idea how a car engine works, or how exactly dynamic RAM in their computers works.

There are many practical aspects to ML/AI that you can learn straight away, like how to partition up your training data into training, validation, and test datasets to keep things honest, and avoid overfitting.

Stay curious, and dig in anywhere it seems interesting. More knowledge is generally a good thing.

Good luck

[SwayamShrimali]

Thanks a bunch! Your support means a lot. I'll take a look at TensorFlow and Keras.

[mejutoco]

Any will do, so I do not want to nitpick too much. I want to point out that most people are using pytorch these days. If you use the book that uses Keras it is also fine, but I would not start with Tensorflow today.