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/
sujith has joined #mlpack
djhoulihan has quit [Quit: A deep and dreamless slumber.]
djhoulihan has joined #mlpack
hassanmahmood has joined #mlpack
manthan has joined #mlpack
CuriousCub has joined #mlpack
CuriousCub has quit [Ping timeout: 260 seconds]
hassanmahmood has quit [Ping timeout: 256 seconds]
sumedhghaisas2 has quit [Ping timeout: 240 seconds]
sujith has quit [Quit: Page closed]
hassanmahmood has joined #mlpack
csoni has joined #mlpack
csoni has quit [Ping timeout: 248 seconds]
sumedhghaisas has joined #mlpack
vivekp has quit [Ping timeout: 265 seconds]
vivekp has joined #mlpack
govg has joined #mlpack
hassanmahmood has quit [Ping timeout: 256 seconds]
csoni has joined #mlpack
vivekp has quit [Ping timeout: 240 seconds]
vivekp has joined #mlpack
< manthan>
zoq : rcurtin : i want to use gdb to debug a particular test. I tried bin/mlpack_test -t ANNLayerTest/GradientAddLayerTest >> a.out | gdb a.out but it gave errors. Any idea how to do so?
csoni has quit [Ping timeout: 256 seconds]
hassanmahmood has joined #mlpack
united_ has joined #mlpack
< united_>
Hi! I am a final year student working in computer vision at NTU, Singapore. Does mlpack have any beginner level deep learning/computer vision issues? I would like to start contributing. Thanks!
dmatt has joined #mlpack
hassanmahmood has quit [Ping timeout: 260 seconds]
sumedhghaisas has quit [Ping timeout: 240 seconds]
sumedhghaisas2 has joined #mlpack
hassanmahmood has quit [Ping timeout: 240 seconds]
sumedhghaisas has joined #mlpack
sumedhghaisas has quit [Read error: Connection reset by peer]
sumedhghaisas3 has joined #mlpack
sumedhghaisas2 has quit [Ping timeout: 240 seconds]
manish7294 has joined #mlpack
csoni has quit [Read error: Connection reset by peer]
dmatt has joined #mlpack
< manish7294>
manthan: Try this - gdb bin/mlpack_test
< manish7294>
then run -t ANNLayerTest/GradientAddLayerTest
< united_>
haritha1313: Thanks
seeni has joined #mlpack
sourabhvarshney1 has joined #mlpack
dmatt has quit [Quit: Page closed]
haritha1313 has quit [Quit: Page closed]
csoni has joined #mlpack
govg has quit [Ping timeout: 240 seconds]
united_ has quit [Ping timeout: 260 seconds]
seeni has quit [Quit: seeni]
sumedhghaisas3 has quit [Read error: Connection reset by peer]
sumedhghaisas has joined #mlpack
seeni has joined #mlpack
sumedhghaisas has quit [Read error: Connection reset by peer]
sumedhghaisas has joined #mlpack
seeni has quit [Client Quit]
manish7294 has quit [Ping timeout: 264 seconds]
csoni has quit [Ping timeout: 265 seconds]
govg has joined #mlpack
hassanmahmood has joined #mlpack
sourabhvarshney1 has quit [Ping timeout: 260 seconds]
united_ has joined #mlpack
< manthan>
manish7294 : thanks! :D
K4k has joined #mlpack
ImQ009 has joined #mlpack
< sumedhghaisas>
@Atharva: Sorry for the late response
< sumedhghaisas>
ahh yes. You will also need changes in ffn.hpp and ffn_impl.hpp
< sumedhghaisas>
I have been meaning to complete that Par for a while now. I should get around doing it this summer :)
united_ has quit [Ping timeout: 260 seconds]
csoni has joined #mlpack
ImQ009_ has joined #mlpack
Prabhat-IIT has joined #mlpack
ImQ009 has quit [Ping timeout: 256 seconds]
csoni has quit [Read error: Connection reset by peer]
manish7294 has joined #mlpack
< manish7294>
rcurtin: Can you please provide just some quick comments over the proposal timeline? I hope, I am not bugging you!
sumedhghaisas2 has joined #mlpack
sumedhghaisas has quit [Read error: Connection reset by peer]
< rcurtin>
manish7294: sure, I can do that, I will make a little time for it today
< rcurtin>
lots of emails over the weekend to catch up with first though
csoni has joined #mlpack
< manish7294>
rcurtin: Thanks, It will help a lot!
eddyrene has joined #mlpack
< eddyrene>
hi
< eddyrene>
everybody
< eddyrene>
i was working in develop a MLP using Armadillo
Atharva has joined #mlpack
< eddyrene>
that's working right now,
< eddyrene>
with some BP algortihms like Stockastic and Momentum
< eddyrene>
I thing that could be a incredible aport to mlpack
< eddyrene>
*think
< eddyrene>
and I would like improve more to extends to other learning algorithms
< eddyrene>
someone can guideme where I need to contact or whom?
< rcurtin>
eddyrene: hi there, we actually already have a neural network infrastructure that one could use to build an MLP
< rcurtin>
and we have a single-layer perceptron also
< rcurtin>
but maybe some of the code that you have written could be ported to these existing infrastructures, if we are missing something that you have written
< Atharva>
sumedhghaisas2: Also, you said core/distributions will be useful for us. I am not really sure how. For example, for a 2d image, we can just use logisticfunction as the last layer and get parameters for Bernoulli distribution.
< sumedhghaisas2>
@Atharva: Sorry don't think I understand what you mean. Which network is using logistic layer for output? Encoder or decoder?
< Atharva>
Decoder, Can you tell me how you would use the core/dists. What I meant was by using a logistic layer for output in the decoder, we can get a value between 0-1 for each pixel.
< Atharva>
Each pixel will take the value 1 with this probability p and zero with 1 - p
sumedhghaisas has joined #mlpack
sumedhghaisas2 has quit [Ping timeout: 252 seconds]
sumedhghaisas2 has joined #mlpack
sumedhghaisas has quit [Read error: Connection reset by peer]
sumedhghaisas2 has quit [Read error: Connection reset by peer]
sumedhghaisas has joined #mlpack
< manthan>
rcurtin : I know you would be very busy but could you have a quick look at my proposal. Its almost the final draft now. I have included zoq's suggestions. Thanks.
haritha1313 has joined #mlpack
< haritha1313>
@zoq: Hi, I guess it was you who reviewed my draft as Anonymous. I had replied to the comments regarding ANN layers to be used and need of another merge layer. Should I repeat them here so we can resolve it, in case there is any point which needs more clarity?
< rcurtin>
manthan: if I have a chance I will take a look, but there are a lot of requests
< zoq>
haritha1313: Let me take a look.
< manthan>
rcurtin : sure thanks, zoq : i have included your suggestions, could you have a quick look if you get time. Thanks
< zoq>
haritha1313: Jsut add the comment to the application is fine. thanks for the clarification.
< Atharva>
rcurtin: is the discrete distribution in core/dist a generalisation of binomial distribution?
< rcurtin>
Atharva: yes, I think you can see it that way
< haritha1313>
zoq: Thanks
< manthan>
zoq : could you have a look at TokenizerEncoder especially. Thanks
< haritha1313>
rcurtin: As per earlier discussion I have edited the proposal to accomodate NCF within CF class. I had one more doubt.
< Atharva>
rcurtin: Okay got it
< haritha1313>
I also intend to make some changes in the existing CF (using matrix factorization) to manage global effects (biases etc.). I have mentioned it in the timeline and in deliverables. Should I describe its implementation too? Any direction would be helpful.
< haritha1313>
Since major part of the proposal is focussed on NCF, it could look a bit out of place, hence the doubt.
eddyrene has quit [Ping timeout: 260 seconds]
< manthan>
zoq : thanks
sujth has quit [Ping timeout: 260 seconds]
dmatt has joined #mlpack
sumedhghaisas2 has joined #mlpack
sumedhghaisas has quit [Ping timeout: 256 seconds]
eddyrene has joined #mlpack
< eddyrene>
rcurtin, so I can write a proposal for develop some functions to add to the infrastructure that you already have
< rcurtin>
eddyrene: I don't really see a need to add any functions that we do already have, but if you identify things that mlpack does not have, I think that is okay
< eddyrene>
rcurtin, I understand.
< eddyrene>
On the other hand I was working also in the PSO algorithm, I develop o algorothim
< eddyrene>
I'm sorry for my english,
< rcurtin>
no worries about the english, I think I understand :)
< eddyrene>
hahaha
rajiv_ has joined #mlpack
< rcurtin>
I am not familiar with the GSoC projects for deep learning but I do think there are some open PRs for PSO now, so maybe it is worth looking there
haritha1313 has quit [Ping timeout: 260 seconds]
< rajiv_>
Hi @rcurtin, I have mailed you my GSoC proposal. If possible, it would be great if you could provide any feedback to improve it :)
< rcurtin>
hi rajiv, there are I think nearly 60 proposals and lots of other things for me to respond to so I may not have time, but I will try
< rajiv_>
Thanks! I would love to hear your feedback!
rajiv_ has quit [Quit: Page closed]
sumedhghaisas2 has quit [Read error: Connection reset by peer]
sumedhghaisas has joined #mlpack
sumedhghaisas has quit [Read error: Connection reset by peer]
sumedhghaisas has joined #mlpack
sumedhghaisas has quit [Ping timeout: 246 seconds]
sumedhghaisas has joined #mlpack
hassanmahmood has quit [Ping timeout: 268 seconds]
eddyrene has quit [Quit: Page closed]
sumedhghaisas has quit [Ping timeout: 240 seconds]
hassanmahmood has joined #mlpack
sumedhghaisas has joined #mlpack
hassanmahmood has quit [Ping timeout: 240 seconds]
< Atharva>
sumedhghaisas: what do you think about how we should use core/dists?
sumedhghaisas has quit [Ping timeout: 240 seconds]
dmatt has quit [Quit: Page closed]
manthan has quit [Ping timeout: 260 seconds]
manish7294 has quit [Ping timeout: 264 seconds]
Prabhat-IIT has quit [Ping timeout: 260 seconds]
Prabhat-IIT has joined #mlpack
ImQ009_ has quit [Quit: Leaving]
sumedhghaisas has joined #mlpack
dmatt has joined #mlpack
sumedhghaisas has quit [Read error: Connection reset by peer]
sumedhghaisas has joined #mlpack
travis-ci has joined #mlpack
< travis-ci>
mlpack/mlpack#4522 (master - a8d2b3b : Marcus Edel): The build has errored.