Ehh... too deep too fast?

What's a good book for learning Tensorflow... and maybe ML Basics through usages/examples?

Can I use TF, ML without the math/lin alg? cuz idon't have that and don't really wamt to learn unless you can convince me otherwise **through usages/examples**

📌📌📌

I would say you have to know the math / background knowledge to do anything cutting edge with tensorflow / pytorch etc.

If you're just looking to do something simple like image classification then it is possible to get by with just blogs and tutorials. There are many tutorials where you can just run a script on some data and get the output. If you want to go beyond just being a "script kiddy" I would recommend fast.ai for a course with a good mix of math and applied coding.

It's like the difference between a programmer who knows algorithms / data structures versus a person who learned web dev directly. Both may be very adept at what they do but having a deep foundational knowledge will allow the programmer to recognize and solve more interesting problems.

@edwardhu well the problem with algods is there are no interesting problems to pick it up with? Prepping for technical interviews is a lousy motivator...

So far I've never seen a real that really need to know Big O or runtime analysis to solve.

Also I know a lot of people that can pass technical interviews but write shit code...

@billgates Yes, I agree with your point on how most of the time we only see algos used in technical interviews. Your day to day will probably revolve around for loops, arrays etc.

The first question is if you are looking for a job in Deep Learning. If you are, I would recommend learning maths / read papers over knowing the TF API because the field of ML is distinct from software engineering. It values theory / fundamentals over knowledge of libraries. From what I've seen, it's hard for software engineers to break into deep learning positions without some research / math background.

If you're not looking for a job and are just playing around, I would still say having knowledge of maths will make it much easier for you to pick up new concepts and papers. I personally learn "top down", where I first do a project, and learn the background maths at the same time. However, my footing in linear alg, probability, and calculus have made it much easier to understand concepts in the field.

.