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/
mentekid has quit [Ping timeout: 240 seconds]
mentekid has joined #mlpack
aashay has quit [Quit: Connection closed for inactivity]
mikeling has joined #mlpack
andrzejku has joined #mlpack
dfne has joined #mlpack
< dfne> hi ryan, thanks. I saw your message afterwards. I will try adding more noise.
mikeling is now known as mikeling|afk
dfne has quit [Ping timeout: 260 seconds]
kris1 has joined #mlpack
kris1 has quit [Quit: kris1]
andrzejku has quit [Quit: Textual IRC Client: www.textualapp.com]
kris1 has joined #mlpack
mikeling|afk is now known as mikeling
kris1 has quit [Quit: kris1]
shikhar has joined #mlpack
aashay has joined #mlpack
kris1 has joined #mlpack
shikhar has quit [Ping timeout: 240 seconds]
shikhar has joined #mlpack
shikhar has quit [Ping timeout: 260 seconds]
shikhar has joined #mlpack
aashay has quit [Quit: Connection closed for inactivity]
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
shikhar has quit [Quit: WeeChat 1.7]
aashay has joined #mlpack
shikhar_ has joined #mlpack
kris1 has quit [Quit: kris1]
kris1 has joined #mlpack
shikhar_ has quit [Quit: WeeChat 1.7]
bill__ has joined #mlpack
bill__ has quit [Quit: Page closed]
andrzejku has joined #mlpack
< lozhnikov> kris1: I derived the free energy function for the ssRBM, take a look. https://usercontent.irccloud-cdn.com/file/dNefmL2X/formulae.jpg
< kris1> great i wil have look
mikeling has quit [Quit: Connection closed for inactivity]
andrzejku has quit [Quit: Textual IRC Client: www.textualapp.com]
aashay has quit [Quit: Connection closed for inactivity]
sumedhghaisas has joined #mlpack
< sumedhghaisas> zoq: Hey Marcus... there?
< sumedhghaisas> had couple of questions...
< sumedhghaisas> why is identity layer used?
kris1 has quit [Quit: kris1]
< zoq> sumedhghais: Actually, it's expected that a model has at least two layers, so for the Gradient check, where you like to check a single layer, adding an identity layer is just a cheap trick, to fulfill that requirement. I think we could detect that inside the model implementation, but I'm not sure that's necessary right now. Also, I see some of the recurrent test models also use an identity layer, we can
< zoq> remove that one.
< sumedhghaisas> zoq: ahh okay. I added Forward tests for the GRU. those are passing.
< sumedhghaisas> but the gradient tests are failing. Going over the gradient calculations again.
< zoq> sumedhghais: Okay, I'll recheck the Gradient as well.
< sumedhghaisas> zoq:
< sumedhghaisas> I made a stupid mistake there
< sumedhghaisas> forgot to take into consideration the effect of forget gate. My god. That was really bad...
< sumedhghaisas> and the network was still learning... Fixed it just now