ensmallen
mlpack
fast, flexible C++ machine learning library

mlpack IRC logs, 2018-12-13

Logs for the day 2018-12-13 (starts at 0:00 UTC) are shown below.

December 2018
Sun
Mon
Tue
Wed
Thu
Fri
Sat
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
29
30
31
--- Log opened Thu Dec 13 00:00:03 2018
01:13 -!- davida [~blakjak88@118.189.183.172] has quit [Read error: Connection reset by peer]
01:14 -!- davida [blakjak888@gateway/vpn/privateinternetaccess/blakjak888/x-23519756] has joined #mlpack
04:02 -!- zoq [~marcus_zo@urgs.org] has quit [Ping timeout: 245 seconds]
04:10 -!- zoq [~marcus_zo@urgs.org] has joined #mlpack
07:32 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Read error: Connection reset by peer]
07:35 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
11:18 -!- cjlcarvalho [~caio@2804:d47:1d02:ef00:eb3b:7e8c:897a:2ce] has joined #mlpack
12:04 < jenkins-mlpack2> Project docker mlpack nightly build build #152: STILL UNSTABLE in 6 hr 50 min: http://ci.mlpack.org/job/docker%20mlpack%20nightly%20build/152/
12:05 -!- cjlcarvalho [~caio@2804:d47:1d02:ef00:eb3b:7e8c:897a:2ce] has quit [Ping timeout: 250 seconds]
12:13 -!- mlPackApprentice [4dfb19d9@gateway/web/freenode/ip.77.251.25.217] has joined #mlpack
12:16 < mlPackApprentice> Hello. My team and I have made steady progress on building an RNN that predicts stockprices. There's just 1 thing that's bothering me. The RNN<>.Train(predictors, responses) function takes an arma::cube of predictors and an arma::cube of responses. The predictors is our cube of training data of hourly stockprices, divided in sequences of 24 (so 24 slices).
12:20 < mlPackApprentice> For the responses cube, I understand it to work as follows: the rows should be what classes you want predicted (in our case 5 values so 5 rows). Then the columns should be equal to the predictors cube, as you want a prediction for each column (or data sample). Then for the slices is my question: If you only make your "responses" cube to have 1 slices, does that mean it will predict only the next 1 hour based on the 24 previo
12:22 < mlPackApprentice> In other words, if my "Predictors" cube is 12x100x24, does that mean that if I make my "Responses" cube 5x100x1, I will get 100 x 1 predictions of all 5 classes for each of the samples in the corresponding slice?
12:24 < mlPackApprentice> A second question: I noticed that if I initialize my "Responses" cube with "zeros" (so a matrix with only 0's everywhere), the Train() function will give me an IndexOutOfBoundsException. But if I initialize the "Responses" cube with "randu" (so values between 0 and 1), it works. So I am wondering: If the "Responses" cube is going to be filled with predictions from the RNN anyway, why should the fill values matter? They're go
12:26 < mlPackApprentice> Thank you in advance for taking the time to read.
12:29 -!- cjlcarvalho [~caio@186-241-25-52.user.veloxzone.com.br] has joined #mlpack
13:36 -!- cjlcarvalho [~caio@186-241-25-52.user.veloxzone.com.br] has quit [Read error: No route to host]
13:36 -!- cjlcarvalho [~caio@186-241-25-52.user.veloxzone.com.br] has joined #mlpack
13:45 -!- cjlcarvalho [~caio@186-241-25-52.user.veloxzone.com.br] has quit [Ping timeout: 240 seconds]
13:52 -!- dagar [~anirudh@103.77.186.196] has joined #mlpack
13:54 -!- dagar [~anirudh@103.77.186.196] has left #mlpack ["WeeChat 1.9.1"]
14:22 -!- vivekp [~vivek@unaffiliated/vivekp] has quit [Read error: Connection reset by peer]
14:25 -!- vivekp [~vivek@unaffiliated/vivekp] has joined #mlpack
14:30 -!- cjlcarvalho [~caio@177.98.226.176] has joined #mlpack
14:35 -!- cjlcarvalho [~caio@177.98.226.176] has quit [Ping timeout: 245 seconds]
16:36 -!- mlPackApprentice [4dfb19d9@gateway/web/freenode/ip.77.251.25.217] has quit [Ping timeout: 256 seconds]
17:48 -!- athithya12 [9d3243a9@gateway/web/freenode/ip.157.50.67.169] has joined #mlpack
17:50 -!- athithya12 [9d3243a9@gateway/web/freenode/ip.157.50.67.169] has quit [Client Quit]
17:53 -!- davida [blakjak888@gateway/vpn/privateinternetaccess/blakjak888/x-23519756] has quit [Ping timeout: 250 seconds]
17:54 -!- davida [~blakjak88@118.189.183.172] has joined #mlpack
19:05 -!- davida [~blakjak88@118.189.183.172] has quit [Read error: Connection reset by peer]
19:18 -!- davida [~blakjak88@118.189.183.172] has joined #mlpack
19:36 -!- davida [~blakjak88@118.189.183.172] has quit [Ping timeout: 250 seconds]
19:37 -!- davida [~blakjak88@118.189.183.172] has joined #mlpack
20:07 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has joined #mlpack
20:52 -!- ImQ009 [~ImQ009@unaffiliated/imq009] has quit [Quit: Leaving]
--- Log closed Fri Dec 14 00:00:04 2018