Hacker News new | past | comments | ask | show | jobs | submit login
Ask HN: Re-coding algorithms to improve knowledge on deep learning
9 points by Givemeyourhoof 8 days ago | hide | past | web | favorite | 4 comments
Greetings,

I've recently got my hands on Deep Learning book by Ian Goodfellow, Yoshua Bengio and Aaron Courville. For some reason I got the urge to re-write the concepts of the book in code, probably c++ and create a small local library.

However, at the moment I am also spending quite a bit of time on enhancing my prototyping and production grade coding skills.

Due to time constrains I'm unable to do both at the same time, so I was wondering which of the options is more preferable.

My goals are to be able to quickly understand the concepts of new research papers and apply it for prototyping purposes. However, I also want to be able to turn that prototype code into production ready code.

P.S. I also thought about taking a month off from work to do this challenge, but I don't know if vacation and topic at hand mixes well. Any experiences?






You are really the only person who can answer this, but let me offer some guidance:

Creative people are most energized when they have autonomy, mastery and purpose.

It seems you already have autonomy, because you can select what you are spending your time on.

It seems like you already have purpose, because you can see the long term value in skills enhancement.

The last part is mastery. You gain mastery by pushing at the limits of your abilities through deliberate practice, so which one of the two makes you feel the best when you're working on it? Select the one where you get the most done, and not the one that appeals to your ego or intellectual vanity, be very honest with yourself, and hopefully the answer will surface.

Putting my two cents in, I would say do the deep learning stuff, because there's lots more engineers out there who can put models into production whereas having deep knowledge of deep learning is probably more valuable. But I'm a Deep Learning developer, so I might be biased!


Select the one where you get the most done, and not the one that appeals to your ego or intellectual vanity, be very honest with yourself, and hopefully the answer will surface.

This is pure gold advice. Really listen to this.

Also you don't have to do everything perfect first time.Try to keep that energy and curiosity to get better. People get burn out easily in their quest most of time.


Thank you for your input.

You lost me at

However, I also want to be able to turn that prototype code into production ready code

Invariably the chances of this not coming back to bite you in the ass is zero.




Applications are open for YC Summer 2019

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact

Search: