Top-down learning path: Machine Learning for Software Engineers
1–10 of 31 posts
Re: Top-down learning path: Machine Learning for Software Engineers
#2Looks to be both a thoughtful listing of resources / tutorials, but also reinforces that to become ML capable, there is considerable effort involved. Things worth doing may require a lot of work, and I'm happy this wasn't another "Learn ML is 24 hours!" type resource.
Re: Top-down learning path: Machine Learning for Software Engineers
#3Seems interesting. I haven't been able to look through all of the links, but I assume there are practical exercises and "homework"?
When people say "I don't do or have the opportunity to do ML at work" it's because they don't have data to analyze or actual things to program or do in order to gain the experience they need to make the videos worthwhile to watch.
If I were to watch 10 videos on ML, but not actually go write code or analyze data, then the videos aren't going to get me a ML job or be that helpful other than learning a little about the topic.
It's kind of like watching a open course on ancient history or some similar topic, but without writing a paper on it. Yes the video is interesting, but what gets me a job and experience is the thought and work that goes into the homework.
But even if these were just videos, it's a good resource.
Re: Top-down learning path: Machine Learning for Software Engineers
#4I appreciate a list of ML learning resources, but does anything about this strike you as strange?
Over 9000 github stars and 1,260 forks for a repo started on 9th October????
Re: Top-down learning path: Machine Learning for Software Engineers
#5I appreciate a list of ML learning resources, but does anything about this strike you as strange? Over 9000 github stars and 1,260 forks for a repo started on 9th October????
Disclaimer: I am the author of this guide. My main goal was to find an approach to studying Machine Learning that is mainly hands-on and abstracts most of the Math for the beginner. This approach is unconventional because it’s the top-down and results-first approach designed for software engineers. You can read more here: http://sdtimes.com/sd-times-github-project-week-machine-lear...
Re: Top-down learning path: Machine Learning for Software Engineers
#6Seems interesting. I haven't been able to look through all of the links, but I assume there are practical exercises and "homework"? When people say "I don't do or have the opportunity to do ML at work" it's because they don't have data to analyze or actual things to program or do in order to gain the experience they need to make the videos worthwhile to watch. If I were to watch 10 videos on ML, but not actually go w…
It has a lot of practical exercises, homework and dataset.
Re: Top-down learning path: Machine Learning for Software Engineers
#7This looks excellent, thank you for this! I actually get a chance to be involved with some very very basic/light ML at work, but i'm also completely new to the field. I really appreciate this style of guide, as i can hopefully jumpstart my knowledge, while i work to gain the required math knowledge.
The Math will be my most difficult challenge, and i'm starting to brush up / learn courses to hopefully enable the proper skillset. /fingerscrossed
Re: Top-down learning path: Machine Learning for Software Engineers
#8Seems interesting. I haven't been able to look through all of the links, but I assume there are practical exercises and "homework"? When people say "I don't do or have the opportunity to do ML at work" it's because they don't have data to analyze or actual things to program or do in order to gain the experience they need to make the videos worthwhile to watch. If I were to watch 10 videos on ML, but not actually go w…
It has a lot of practical exercises, homework and dataset.
Thanks!
Re: Top-down learning path: Machine Learning for Software Engineers
#9It's great, but it's a mess - a heap of articles, github repos, books and such. A new learner can't deal with that. What a new learner needs is an interactive system to guide a learner through the process. Not a static list - one size doesn't fit all. I might know Python and not know math, another one might come from stats and Matlab but not know Python. One might know about SVMs and Naive Bayes but not about neural nets, another might have played with Keras neural nets but neglected to read up on basic ML. We need an adaptive learning system. Who's going to make one?
Re: Top-down learning path: Machine Learning for Software Engineers
#10It's great, but it's a mess - a heap of articles, github repos, books and such. A new learner can't deal with that. What a new learner needs is an interactive system to guide a learner through the process. Not a static list - one size doesn't fit all. I might know Python and not know math, another one might come from stats and Matlab but not know Python. One might know about SVMs and Naive Bayes but not about neural…
It's a step-by-step guide on how to learning machine learning from overview to detail. Any comments are welcome.
If you want the interactive system, please check "A Visual Introduction to Machine Learning:http://www.r2d3.us/visual-intro-to-machine-learning-part-1/"