The result

I went to my old school the day before yesterday, I like my old school.
An event about chemoinformatics was held here.
I enjoyed presentation of all participants.
My prediction result was …….(please don’t ask ;-))

All teams used two approaches SBDD or LBDD, and winner used LBDD approach.
It’s worth to think about which method is more effective for VS.
Is it not always true that more rich resource produces more effective prediction ?
I don’t have the answer yet.

In the contest, two teams used deep learning for the prediction.
An academia team that used DL, presented very cool approach.
Sometime turning of hyper parameters are problematic in the deep learning.
Because a lots of parameters have to optimise and the process is very time consuming step.
So they chose random sampling strategy to optimise the parameters. And they run the calculation using super computer.
I agree the strategy.
Benjo et.al. reported random search for hyper-parameter optimisation before.
http://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf

Is DL still hot area in ML? I’ll check some papers.
My snippet was uploaded git hub.(not include results and SDF)
https://github.com/iwatobipen/chemo_info/tree/master/ipab2015

I thank all participants for having good discussion, and thank my family for allowing me to cording in my off-time.

Bonus..
Yesterday, I found a Dinosaur !!
Wow 😉
IMG_1349

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s