{"id":2313,"date":"2020-10-01T16:03:25","date_gmt":"2020-10-01T16:03:25","guid":{"rendered":"https:\/\/data-science.gotoauthority.com\/2020\/10\/01\/10-days-with-deep-learning-for-coders\/"},"modified":"2020-10-01T16:03:25","modified_gmt":"2020-10-01T16:03:25","slug":"10-days-with-deep-learning-for-coders","status":"publish","type":"post","link":"https:\/\/wealthrevelation.com\/data-science\/2020\/10\/01\/10-days-with-deep-learning-for-coders\/","title":{"rendered":"10 Days With \u201cDeep Learning for Coders\u201d"},"content":{"rendered":"
\n

By Arnuld on Data<\/a>, Freelance Data Scientist<\/b><\/p>\n

\n\"Figure\"
<\/p>\n

<\/span>\n<\/div>\n

\u00a0<\/p>\n

The Background<\/h3>\n

\u00a0
I started Practical Deep Learning for Coders 10 days ago. I am compelled to say their pragmatic approach is exactly what I needed.<\/p>\n

I started data science by learning Python, Pandas, NumPy, and whatever I needed in a short few months. I did whatever courses I need to do (e.g.\u00a0Kaggle micro-courses<\/a>) and whatever books I needed to read (e.g.\u00a0Python for Data Analysis<\/a>). All of this I did as a part of a\u00a090-day MOOC\u2019athlon learning challenge<\/a>\u00a0started back in April this year. It was one of the greatest learning periods of my life. After this, I completed both Iris data and Boston house price prediction projects at Kaggle. Then I scraped data from the internet and used my Pandas skills to clean them out. And implementing research papers was still confusing and frustrating. I struggled with research papers and Kaggle projects. I am good at C language. You can give me any programming language and I can learn it pretty quickly than most because programming is my 2nd nature. Computer Programming just flows in my thoughts. And this wasn\u2019t happening with data science. Even though there were learning and a lot of work but in the end, I couldn\u2019t remember any of what I did (yes, data wrangling is a hell lot of work). I was in a constant state of frustration. I started getting irritated at little things and it spilled into my personal life. I thought of quitting data science and machine learning. It had been 4 months and I was nowhere near having the capability to accomplish anything deemed usable for business. I felt trapped in a 4×4 feet concrete box.<\/p>\n

\u00a0<\/p>\n

End of Frustration<\/h3>\n

\u00a0
I am always in constant search for different approaches to problems. I consider a different\u00a0point of view<\/strong>\u00a0as a blessing from the universe. Yes, we all have our own \u201cpoint of view\u201d and it is always refreshing when someone approaches the same problem from a different and strange angle you never thought of. What changed my situation was a blog-post by\u00a0Caleb Kaiser<\/a>:<\/p>\n

Don\u2019t learn machine learning<\/b>
Learn how to build software with ML models<\/a>
\u00a0<\/p>\n

His blog-post made me understand that this frustration doesn\u2019t belong just to me, it is what every coder\/programmer can get, that I am not alone. This completely changed my perspective and I decided to use his approach. I decided to do both: read the book and watch the videos.<\/p>\n

In just one week with this course, I was able to comprehend\u00a0this research paper on weight-poisoning<\/a>\u00a0by\u00a0Appsilon Data Science<\/a>.<\/p>\n

Another few days and after many failures, I successfully implemented the bear detection model as a web-app on binder. You can try this web-app. Just pass it an image of any of:<\/p>\n

    \n
  1. American black bear\n<\/li>\n
  2. Grizzly\n<\/li>\n
  3. Polar bear\n<\/li>\n
  4. Teddy bear\n<\/li>\n<\/ol>\n

    and it will detect which one it is. Pass it anything else, a shoe e.g., and it will try to match it with 150×4 images of bear pics in the model and do its best. It is not human =:o) :
    https:\/\/mybinder.org\/v2\/gh\/ArnuldOnData\/fastai-projects\/master?urlpath=%2Fvoila%2Frender%2FCh02%2Fbear-detection.ipynb<\/a><\/p>\n

    \n\"Figure\"
    <\/p>\n

    <\/span>\n<\/div>\n

    \u00a0<\/p>\n

    And I seem to remember most of what I did. Data science is finally becoming my 2nd nature. This fastai course has given me more confidence to pursue more and higher machine learning knowledge. I think if some learning approach doesn\u2019t work for you then you need to give the pragmatic approach of this course a try.<\/p>\n

    \u00a0<\/p>\n

    The Why<\/h3>\n

    \u00a0
    It is not to say that traditional approaches of learning like doing MOOCs and then Kaggle projects or the university route of graduating in data science don\u2019t work. They might or they might not. People are different and we all have different backgrounds and we can\u2019t all be following traditional or hybrid approaches. Times have changed. Thanks to the internet, its decentralized nature, and\u00a0    net neutrality<\/a>, the world is far more connected than it used to be. The world has become a smaller place where everyone can connect to everyone. This has resulted in the 4th industrial revolution:<\/p>\n

    \n\"Figure\"
    <\/p>\n

    <\/span>\n<\/div>\n

    \u00a0<\/p>\n

    \n\"Figure\"
    <\/p>\n

    <\/span>\n<\/div>\n

    \u00a0<\/p>\n

    4th industrial revolution will lead to:<\/p>\n