Thursday, July 23, 2015

How Data Science Saigon took the lead in a Kaggle Competition


Last month, at Tech Talk Tuesday,  we formed a team for the Kaggle Competition Getting Started with Julia. Last week, out team Data Science Saigon took the number one spot on the leaderboard.  Here's how it happened.


Entering a Kaggle competition

You've got to be in it to win it.  When our team met on June 16th, we created accounts on Kaggle's site, and on bitbucket by Atlasian, a company with offices here in Saigon.  We reviewed DataFrames with Julia, and got the code from the Julia Tutorial and the K-Nearest-Neighbor tutorial working with help from the Kaggle forums.  In particular,  some method calls have changed since the tutorials were created, but we found the workaround in the Convert method error when reading image files topic.  Our versions work as of Julia 0.3.7.   Implementing the tutorial code got us to about 46th place at the time.

Machine Learning with Julia

At our next meeting we took a look at how to build a predictive model based on the Random Forest algorithm.


But boosting parameters to our Random Forest algorithm didn't drastically improve our score.  This is when we found out about the Mocha package.

Convolutional Neural Networks 



The recent resurgence in popularity of Neural Networks is due the the amazing performance of Convolutional Neural Networks (CNNs) at image classification.  This was exactly the solution our problem needed.   Dung Thai is very knowledgeable about Deep Learning, and encouraged us to try out the Mocha Package for Deep Learning in Julia. As a result we quickly moved into the top 20 on the leaderboard.




Pulling out all the Stops

At our next meeting Dung (pronounced Yung) summarized Learn from the Best , and we talked about how to get to the next level. Data Science Saigon has talent across a variety of platforms and languages including C++, Caffe, Scilab, Python and of course Julia.  We also noticed a few things about the rules for this particular competition:

  1. Outside Data is not forbidden
  2. Semi-supervised learning is not forbidden
  3. The language does not have to be Julia  
We pondered how a Convolutional Network form a good Python library like Theano would perform. We also accessed lots more training images from the Chars74k dataset and the Street View House Numbers dataset

Saigon là số một.

 Then last week Dung Thai,  Vinh Vu, and  Nguyen Quy checked in Python code using Theano that recognizes over 92% of the images correctly, and vaulted us into the #1 spot on the Getting Started with Julia leaderboard.  Congratulations to everyone taking part in Data Science Saigon.

Our Remaining Challenge

So clearly, training with lots more data improved the score.  But the question remains,  would using a CNN in Julia with the additional training data generate a similar score as the Python code?  We hope to find out when we meet again. All of our code is here.  






34 comments:

Michael Blake said...

Our score is no long on the leaderboard. Kaggle has implemented a rolling leaderboard: https://www.kaggle.com/c/digit-recognizer/forums/t/6250/rolling-leaderboards/36132 . Just as well, since we used Python code in a Julia competition.

Aashi siva said...

I simply want to say I’m very new to blogs and actually loved you’re blog site. Almost certainly I’m going to bookmark your blog post . You absolutely come with great well written articles. Thanks a lot for sharing your blog.

Online Training in Chennai

Sowmiya said...


ya it is really i had a fun and auspicious time by reading your blog thus it makes me to be proud to get many more credentials. thus i had a good time with your blog it attracts me with large types of collections.


Best Android Training Institute in Chennai

Riya R said...

nice theme,I liked this ..SEO jobs in Hyderabad

Divya madhuri said...

I am reading your post from the beginning, it was so interesting to read & I feel thanks to you for posting such a good blog, keep updates regularly
CCNA jobs in Hyderabad .

Packers And Movers Bangalore said...

Packers and Movers Bangalore 100% Affordable Local Shifting Services. Compare Charges, Get Free Best Quotes Packers and Movers in Bangalore, Urban and Domestic Household Relocation @
Packers And Movers Bangalore

Priya B said...

ya it is really i had a fun and auspicious time by reading your blog thus it makes me to be proud to get many more credentials. thus i had a good time with your blog it attracts me with large types of collections.



Android Training Institite in Chennai

Taylor Bell said...

If you would like to top essay writing reviews grow your knowledge just keep visiting this website and be updated with the newest news update posted here.

packers movers hyderabad said...

Thanks for sharing such a valuable information.Im very thankful to you that you had given me this opportunity to write on this blog.please visit our website I assure you that it will be very useful for our website.....
Packers And Movers Hyderabad

Shalini Mudhalayar said...

Your Java blog has explained the concepts clearly with suitable examples. Many programming languages have evolved but Java is still in NO:1 position due to its great features.

Regards:

Java Training |
JAVA Training Institutes in Chennai

Ishu Sathya said...

I have seen only the same thing is reapeating in many blogs, but your blog includes the unique content with many recent updates about the Hadoop technology. Thank you for sharing with us, I also like to share your blog to my friends.


Regards:
Hadoop Training Chennai |
Hadoop Course in Chennai

ijazz jazz said...

Thank you a lot for providing individuals with a very spectacular possibility to read critical reviews from this site.

Android Training in Bangalore

LauraMedley said...

Thanks for making such a cool my assignment help australia review project. I've been checking the site for the Windows version, but I never left a comment about it. I know you are working hard and doing it for free so you shouldn't feel rushed or anything. I hope you can continue this type of hard work to this site in future also. Because this blog is really very informative and it helps me lot.

Andria BZ said...

Excellent post!!! In this competitive market, customer relationship management plays a significant role in determining a business success. That too, cloud based CRM product offer more flexibility to business owners to main strong relationship with the consumers. Cloud Computing Training in Chennai | Cloud Computing Training

ASO Services said...

Thanks a lot for sharing this with all of us, I like it and we can communicate. Do you need buy app ratings and reviews. To boost app ranking and double app downloads now.

joselin mary said...

Great.Nice information.It is more useful and knowledgeable. Thanks for sharing keep going on.. and I expect more blog like this
Digital Marketing Company in India
Seo Company in India

jhansi joe said...

Excellent post!!! In this competitive market, customer relationship management plays a significant role in determining a business success. That too, cloud based CRM product offer more flexibility to business owners to main strong relationship with the consumers.
Cloud computing courses in Chennai|Cloud computing Training in Chennai

Manish Packers and Movers Pvt Ltd said...

Hire Manish Packers and Movers Pvt Ltd in India for hassle-free Household Shifting, Office Relocation, Car Transportation, Loading Unloading, packing Unpacking at affordable Price Quotation. Top Rated Safe and Secure Service Providers who can help you with 24x7 and make sure a Untroubled Relocation Services at Cheapest/Lowest Rate. Visit More :-
Manish Packers and Movers Pvt Ltd
Packers and Movers Bangalore
Packers and Movers Gurgaon
Packers and Movers Indore
Packers and Movers Kolkata
Packers and Movers Mumbai
Packers and Movers Nagpur
Packers and Movers Ahmedabad
Manish Packers in Indore
Manish Packers and Movers Pvt Ltd Sitemap

Manish Packers and Movers Pvt Ltd said...

Best Movers and Packers in India for Moving and Shifting Door to Door Transportation Services to all over India. Visit More :-
Manish Packers and Movers Pvt Ltd Blog
Packers and Movers Bhopal
Packers and Movers Jabalpur
Packers and Movers Vadodara
Packers and Movers Udaipur
Packers and Movers Jaipur
Packers and Movers Chandigarh
Packers and Movers Chennai
Packers and Movers Hyderabad
Packers and Movers in Indore

Manish Packers and Movers Pvt Ltd said...

Packers and Movers Dewas Naka Indore
Packers and Movers Vijay Nagar Indore
Packers and Movers Scheme 54 Indore
Packers and Movers Delhi
Packers and Movers Pune
Packers and Movers Jodhpur
Packers and Movers Kanpur
Packers and Movers Ghaziabad
Packers and Movers Noida
Packers and Movers Navi Mumbai

Manish Packers and Movers Pvt Ltd said...

Manish Packers and Movers Pvt Ltd as a Services providing company can make all the difference to your Home Relocation experience. Indore based Company which offers versatile solutions, Right team that easily reduce the stress associated with a Household Shifting, Vehicle Transportation. we help things run smoothly and reduce breakages and offer you seamless, Affordable, Reliable Shifting Services, Compare Shifting Charges, Visit :
Manish Packers and Movers Ptv Ltd @ https://www.manishpackersmoversindore.in/
Packers and Movers Indore @ https://www.manishpackersmoversindore.in/packers-and-movers-indore.html
Manish Packers Indore @ https://www.manishpackersmoversindore.in/manish-packers-and-movers-indore.html
Packers and Movers Gurgaon @ https://www.manishpackersmoversindore.in/packers-movers-gurgaon.html
Packers and Movers Kolkata @ https://www.manishpackersmoversindore.in/packers-movers-kolkata.html
Packers and Movers Mumbai @ https://www.manishpackersmoversindore.in/packers-movers-mumbai.html
Packers and Movers Bhopal @ https://www.manishpackersmoversindore.in/packers-movers-bhopal.html
Packers and Movers Nagpur @ https://www.manishpackersmoversindore.in/packers-movers-nagpur.html
Packers and Movers Raipur @ https://www.manishpackersmoversindore.in/packers-movers-raipur.html
Packers and Movers Ahmedabad @ https://www.manishpackersmoversindore.in/packers-movers-ahmedabad.html

johnsy sai said...

Thanks for your informative article, Your post helped me to understand the future and career prospects & Keep on updating your blog with such awesome article.
advanced excel training in bangalore

Chitra devi said...


This is most informative and also this post most user friendly and super navigation to all posts... Thank you so much for giving this information to me.. 

best rpa training in chennai |
rpa training in chennai | rpa online training |
rpa training in chennai |
rpa training in bangalore
rpa training in pune
rpa training in marathahalli
rpa training in btm

Saro said...

Inspiring writings and I greatly admired what you have to say , I hope you continue to provide new ideas for us all and greetings success always for you..Keep update more information.

best rpa training in chennai
rpa training in chennai |
rpa online training
rpa course in bangalore
rpa training in pune
rpa training in marathahalli
rpa training in btm

kevin john said...

Inspiring writings and I greatly admired what you have to say , I hope you continue to provide new ideas for us all and greetings success always for you..Keep update more information.

best rpa training in chennai
rpa training in chennai |
rpa online training
rpa course in bangalore
rpa training in pune
rpa training in marathahalli
rpa training in btm

Mouni yoga said...

Superb. I really enjoyed very much with this article here. Really it is an amazing article I had ever read. I hope it will help a lot for all. Thank you so much for this amazing posts and please keep update like this excellent article. thank you for sharing such a great blog with us.
python training institute in marathahalli | python training institute in btm | Python training course in Chennai

jeeva said...

This is most informative and also this post most user friendly and super navigation to all posts... Thank you so much for giving this information to me.

best rpa training in chennai
rpa training in chennai |
rpa online training
rpa course in bangalore
rpa training in pune
rpa interview questions and answers | blueprism interview questions and answers

simbu said...

Thanks for the informative article. This is one of the best resources I have found in quite some time. Nicely written and great info. I really cannot thank you enough for sharing.
Java training in Chennai | Java training in Annanagar

Java training in Chennai | Java training institute in Chennai | Java course in Chennai

Java training in Chennai | Java training institute in Chennai | Java course in Chennai

Java training in Bangalore | Java training in Electronic city

shalinipriya said...

I have read a few of the articles on your website now, and I really like your style of blogging. I added it to my favourites blog site list and will be checking back soon.

Data Science course in Indira nagar
Data Science course in marathahalli
Data Science Interview questions and answers
Data science training in tambaram | Data Science Course in Chennai
Data Science course in btm layout | Data Science training in Bangalore
Data science course in kalyan nagar | Data Science Course in Bangalore

shalinipriya said...

I have read a few of the articles on your website now, and I really like your style of blogging. I added it to my favourites blog site list and will be checking back soon.

Data Science course in Indira nagar
Data Science course in marathahalli
Data Science Interview questions and answers
Data science training in tambaram | Data Science Course in Chennai
Data Science course in btm layout | Data Science training in Bangalore
Data science course in kalyan nagar | Data Science Course in Bangalore

keith kristoper said...

I am really happy with your blog because your article is very unique and powerful for new reader.
Click here:
selenium training in chennai | selenium course in chennai
selenium training in bangalore | selenium course in bangalore
selenium training in Pune | selenium course in pune | selenium class in pune
selenium training in Pune | selenium course in pune | selenium class in pune
selenium online training | selenium training online | online training on selenium

ijazz jazz said...

Greetings. I know this is somewhat off-topic, but I was wondering if you knew where I could get a captcha plugin for my comment form? I’m using the same blog platform like yours, and I’m having difficulty finding one? Thanks a lot.

AWS Interview Questions And Answers

AWS Tutorial |Learn Amazon Web Services Tutorials |AWS Tutorial For Beginners


AWS Online Training | Online AWS Certification Course - Gangboard

AWS Training in Toronto| Amazon Web Services Training in Toronto, Canada

sathya shri said...

It is amazing and wonderful to visit your site.Thanks for sharing this information,this is useful to me...

angularjs-Training in tambaram

angularjs-Training in sholinganallur

angularjs-Training in velachery

angularjs Training in bangalore

angularjs Training in bangalore

Nizar niz said...

I am really happy with your blog because your article is very unique and powerful for new reader.
Click here:
selenium training in chennai | selenium course in chennai
selenium training in bangalore | selenium course in bangalore
selenium training in pune | selenium course in pune | selenium class in pune
selenium training in pune | selenium course in pune | selenium class in pune
selenium online training | selenium training online | online training on selenium

Popular Articles