I am currently attending Conference on Intelligent Data Understanding (CIDU) here in Boulder.
The conference theme for this year is "Bringing Data and Models Together". The presentations consist of scientists from a wide variety of fields: Space Science, Earth and Environment Systems, and Aerospace and Engineering Systems. This is a great conference bringing researchers practicing data mining, machine learning or computational intelligence.
I am enjoying all the talks. The final agenda for CIDU 2012 can be found here.
This is the first time that the CIDU is being held in NCAR, Boulder, away from its "home".
I presented yesterday. First day first slot: nice!!
It was about "Estimation and Bias Correction of Aerosol Abundance using Data driven Machine Learning and Remote Sensing ". Basically this paper discusses a general framework to choosing the optimal set of variables for machine learning/bias correction. Neural network was used, however one can insert his/her favorite Machine learning tool (SVM, DT, RF, GP etc). This involves massive number crunching for brute force search among all possible combination of variables. For 15 variable case, it has more than 32 thousands of combinations to try. I wonder if Bayes Net can help me to intelligently reduce the search.
Forgot my SD card, and it is cloudy+started to snow. While driving down the road, I saw nice mountains!! However, no pictures on this post!
(Happy Dashain!!)
-->
The conference theme for this year is "Bringing Data and Models Together". The presentations consist of scientists from a wide variety of fields: Space Science, Earth and Environment Systems, and Aerospace and Engineering Systems. This is a great conference bringing researchers practicing data mining, machine learning or computational intelligence.
I am enjoying all the talks. The final agenda for CIDU 2012 can be found here.
This is the first time that the CIDU is being held in NCAR, Boulder, away from its "home".
I presented yesterday. First day first slot: nice!!
It was about "Estimation and Bias Correction of Aerosol Abundance using Data driven Machine Learning and Remote Sensing ". Basically this paper discusses a general framework to choosing the optimal set of variables for machine learning/bias correction. Neural network was used, however one can insert his/her favorite Machine learning tool (SVM, DT, RF, GP etc). This involves massive number crunching for brute force search among all possible combination of variables. For 15 variable case, it has more than 32 thousands of combinations to try. I wonder if Bayes Net can help me to intelligently reduce the search.
(Happy Dashain!!)
-->
