Hi
user
Admin Login:
Username:
Password:
Name:
Some things you can do with a recurrent neural network
--client
lca
--show
lca_2015
--room OGGB_260098 9410 --force
Next: 12 When Your Codebase Is Nearly Old Enough To Vote
show more...
Marks
Author(s):
Douglas Bagnall
Location
OGGB 260-098
Date
jan Fri 16
Days Raw Files
Start
10:40
First Raw Start
10:39
Duration
0:45:00
Offset
0:00:32
End
11:25
Last Raw End
11:28
Chapters
00:00
Total cuts_time
43 min.
http://lca2015.linux.org.au/schedule/30225/view_talk
raw-playlist
raw-mp4-playlist
encoded-files-playlist
host
public
tweet
mp4
svg
png
assets
release.pdf
Some_things_you_can_do_with_a_recurrent_neural_network.json
logs
Admin:
episode
episode list
cut list
raw files day
marks day
marks day
image_files
State:
---------
borked
edit
encode
push to queue
post
richard
review 1
email
review 2
make public
tweet
to-miror
conf
done
Locked:
clear this to unlock
Locked by:
user/process that locked.
Start:
initially scheduled time from master, adjusted to match reality
Duration:
length in hh:mm:ss
Name:
Video Title (shows in video search results)
Emails:
email(s) of the presenter(s)
Released:
has someone authorised pubication
Unknown
Yes
No
Normalise:
Channelcopy:
m=mono, 01=copy left to right, 10=right to left, 00=ignore.
Thumbnail:
filename.png
Description:
markdown
In 2013 I wrote a Gstreamer plug-in that used a recurrent neural network (RNN) to generate video in imitation of a program it was watching. Pretty soon the same RNN library was being used in another Gstreamer plug-in to classify speech on the radio according to language, and to detect birds by listening for their calls (the language classification is quite accurate and runs at 1500 faster than real time on an old laptop, which is at least a data-point for those wondering about spying capabilities). The RNN has also been used to generate text and code, and to classify text by language and author at a fine-grained level. I will show how the RNN is trained, and how it might be adapted for other forms of time-series data. I will demonstrate the various plug-ins and text utilities and, for excitement, execute RNN-generated code on the fly. Also I'll explain what a recurrent neural network is and how it relates to a plain (or "deep") neural network.
Comment:
production notes
2015-01-16/10_39_28.dv
Apply:
10:39:28 - 10:45:37 ( 00:06:09 )
S:
10:39:28 -
E:
10:45:37
D:
00:06:09
show more...
vlc ~/Videos/veyepar/lca/lca_2015/dv/OGGB_260098/2015-01-16/10_39_28.dv :start-time=00.0 --audio-desync=0
Raw File
Cut List
10:39:28
seconds: 0.0
Wall: 10:39:28
Duration
00:06:09
10:45:37
seconds: 0.0
Wall: 10:39:28
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
2015-01-16/10_45_37.dv
Apply:
10:45:37 - 11:28:40 ( 00:43:03 )
S:
10:45:37 -
E:
11:28:40
D:
00:43:03
show more...
vlc ~/Videos/veyepar/lca/lca_2015/dv/OGGB_260098/2015-01-16/10_45_37.dv :start-time=00.0 --audio-desync=0
Raw File
Cut List
10:45:37
seconds: 0.0
Wall: 10:45:37
Duration
00:43:03
11:28:40
seconds: 0.0
Wall: 10:45:37
Comments:
mp4
mp4.m3u
dv.m3u
Split:
Sequence:
:
delete
Rf filename:
root is .../show/dv/location/, example: 2013-03-13/13:13:30.dv
Sequence:
get this:
check and save to add this
2015-01-16/10_39_28.dv
2015-01-16/10_45_37.dv
Veyepar
Video Eyeball Processor and Review
