verne.freenode.net changed the topic of #mlpack to: http://www.mlpack.org/ -- We don't respond instantly... but we will respond. Give it a few minutes. Or hours. -- Channel logs: http://www.mlpack.org/irc/
travis-ci has joined #mlpack
< travis-ci> mlpack/mlpack#3633 (master - cba9ff9 : Marcus Edel): The build has errored.
travis-ci has left #mlpack []
petris_ has joined #mlpack
petris_ is now known as petris
K4k has joined #mlpack
vivekp has quit [Ping timeout: 248 seconds]
vivekp has joined #mlpack
govg has joined #mlpack
vivekp has quit [Ping timeout: 264 seconds]
vivekp has joined #mlpack
kj_ has joined #mlpack
kj_ has quit [Client Quit]
keonkim has quit [Ping timeout: 252 seconds]
keonkim has joined #mlpack
joydeepdas96 has joined #mlpack
joydeepdas96 has quit [Client Quit]
joydeepdas96 has joined #mlpack
joydeepdas96 has quit [Client Quit]
vivekp has quit [Ping timeout: 240 seconds]
vivekp has joined #mlpack
govg has quit [Ping timeout: 268 seconds]
govg has joined #mlpack
govg has quit [Ping timeout: 240 seconds]
govg has joined #mlpack
abstract has joined #mlpack
< abstract> Hello Everyone.
abstract is now known as Guest86462
< zoq> abstract: Hello there!
< Guest86462> I have been reading documentation for mlpack for last few days and wanted to start contributing. I looked over issues page but there was not anything latest. It would be very kind of you if you direct me in some direction so that I can start contributing or implementing something for mlpack.
< zoq> I'm sure we can figure something out.
< zoq> You can always go through the codebase and see if you find something interesting that can be added or improved, but if you like you can also contribute something new.
< zoq> There is an open issue, that is quite popular: https://github.com/mlpack/mlpack/issues/1112 it's bascially all about adding new optimization methods.
Guest86462 has quit [Ping timeout: 260 seconds]
Guest86462 has joined #mlpack
< Guest86462> I have been reading documentation for mlpack for last few days and wanted to start contributing. I looked over issues page but there was not anything latest. It would be very kind of you if you direct me in some direction so that I can start contributing or implementing something for mlpack.
< zoq> Guest86462: Welcome back, please take a look at the logs: http://www.mlpack.org/irc/
< Guest86462> Oh sorry about sending same message again. I got disconnected.
< zoq> Guest86462: No worries.
< Guest86462> I have basic knowledge of Machine Learning. Will that suffice if I want to start contributing? Or should I strengthen it first?
< zoq> In most cases a willingnes to learn new paradigm is fine to get started. In any case http://mlpack.org/gsoc.html might be helpful it lists some references that might be helpful.
< Guest86462> Will mlpack be participating in GSoC this year?
< zoq> We will submit an application, but we have to wait until February 12 to know for sure if we get in.
< Guest86462> Okay. Should I start learning about and implementing R
< Guest86462> RPROP
< Guest86462> What do you say?
< zoq> RPROP is already take, but if you like you can take a look into Natural Evolution Strategies (NES) - https://arxiv.org/pdf/1106.4487.pdf
< zoq> *taken
< Guest86462> Okay. Anything specific in that?
< zoq> It might be a good idea to start with the standard algortihm before looking into xNES etc.
< Guest86462> Can you elaborate a bit more?
< zoq> CMAES is already implemented, might be helpful to look into the code to get a feeling about the structure.
< zoq> There are a couple of methods to improve the standard NES method like by using an exponential map (xNES)
< zoq> I would start by going through the paper.