0
$\begingroup$

For the past month I have been studying machine/deep learning, thus I have completed both the machine learning course and the deep learning specialization by Prof. Andrew Ng on coursera.

In these courses, the assignements in python are very guided, so I think I would have a hard time starting my own project from a blank notebook. I am looking for advice on where to go next. I would like to improve my applied skills. My goal is (in the long run), to be able to deploy AI systems (with frontend-backend interactions).

Here is a list of things I've considered as the next step:

I am also considering the Deep Learning book by Goodfellow et al, however theory is not my main concern right now.

$\endgroup$
  • $\begingroup$ Hi. Unfortunately, this site isn't really suited to ask for recommendations. Please, read ai.stackexchange.com/help/on-topic for details. Anyway, although I have never followed that specialization, I can say that what you should learn next depends on what you want to do in the future. If you think your theoretical foundations are already good but you haven't had any serious practical experience, maybe something like solving some Kaggle problem may be a good start. $\endgroup$ – nbro Jul 16 at 16:48
  • $\begingroup$ @nbro Thanks for the answer! Any idea of a more appropriate forum? $\endgroup$ – DeepNet Jul 16 at 16:59
  • 1
    $\begingroup$ This site is appropriate (actually, the best site, I would say) to ask questions about Artificial Intelligence, but we are looking for questions that can be answered objectively. Your question asks for opinions, although one could give a more objective answer if you describe what exactly you're looking for. Can you rephrase your question differently so that it can be answered more objectively? $\endgroup$ – nbro Jul 16 at 17:00
  • $\begingroup$ Alternatively, although fewer people will probably see it, you could also ask your question in our chat room: The Singularity, where the strict rules about opinions do not apply ;) $\endgroup$ – nbro Jul 16 at 17:09
  • 1
    $\begingroup$ Now, can you please ask a more specific question (in the title)? $\endgroup$ – nbro Jul 16 at 21:29
0
$\begingroup$

Ai is moving very fast. Nobody is really sure what's the best approach. As of today, consider to get involved in Ai communities. Kaggle is a very good place to start, see others' notebooks and thoughts, and consider some easy to understand blogs in data science and Ai like medium.

Also don't worry about learning deep learning in TF1. The main difference between TF2 and TF1 is that TF2 uses Keras as its default API. You just want to understand concept and then in your work, try to do everything in TF2.

Probably this question will be removed, by then I hope you find my answer useful.

| improve this answer | |
$\endgroup$
0
$\begingroup$

The most important thing for you is to actually have fun while coding. There are a lot of courses(it's overwhelming to me sometimes), a lot of books, blogs and other stuff on this topic. When it comes to the learning, find a person you enjoy learning from(for you that might be Andrew NG, for me it's say Daniel Bourke), and slowly start working on your own projects, implementing the things you are learning on the go. My biggest problem at the begininning was that I found it easy to listen someone and learn from someone, but when I was supposed to brainstorm and code something, I would just procrastinate and get bored, as it is "harder" than just listening to someone and following their code. In summary, learn to love writing code, and learn from the person you enjoy watching!

| improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.