How to solve ML problems being an absolute beginner?

Question

Machine learning

there are two tasks: 1. to classify images of people as real or as generated (the accuracy of the model must be at least 0.9)
2. there are two fragments of text, and it is necessary to determine whether there is a causal relationship between 2 fragments of text (at least 0.2)

to By the end of July, I need to solve at least one problem, also, in practice, I am a complete zero in machine learning, I know the very basics of python, there are no problems with mathematics. I ask you to direct me in the right direction by throwing off the literature / courses / other resources and preferably the specific topics necessary for these particular tasks. in general, is it possible to solve them in such a short time, having studied everything necessary?

Answer 1

As a book on artificial intelligence, I recommend the global work "Artificial Intelligence Modern Approach". This monumental 1,500-page book provides systematic knowledge about the most diverse areas of AI, not only about neural networks, there is much more. I hope this becomes a useful reference for you.
For general programming, I recommend the classic work Structure and Interpretation of Computer Programs (SICP). It covers programming from the highest to the lowest level of abstraction. This is already a tutorial, in addition, you will find many wonderful exercises in it. Wonderful book!