|
Members in Shoutbox
None.
Shoutbox Search
Shoutbox Commands
/w [name] > Whisper
/r > Reply to last whisper /me > Marks as action Shoutbox Information
Moderators may delete any and all shouts at will.
|
Global Shoutbox
Please log in to shout.
[2016-5-02. : 4:48 pm]  TiKels -- Great. You all come out of the woodwork an hour before my project is due[2016-5-02. : 4:38 pm] Clokr_ -- Vrael, it does sound interesting. Do you have any good references to get started on this?[2016-5-02. : 4:26 pm] TiKels -- Also I should mention that this is not some kind of gui, all the code is just Matrix math and standard functions. That's what makes it even more frustrating[2016-5-02. : 3:36 pm]  Vrael -- I'm a research scientist [BUZZWORD ALERT]DATA SCIENTIST[/BUZZWORD ALERT}[2016-5-02. : 3:33 pm] TiKels -- I know I can alter the number of layers but that's a bit outside the scope of my knowledge. The neuron count is pretty simple though[2016-5-02. : 3:32 pm] Vrael -- if the other setup was specifically tuned to that data you could have like, a single node NN or something degenerate like that which isn't working[2016-5-02. : 3:30 pm] Vrael -- you can't train on a data set of shoe sizes and expect to do facial recognition[2016-5-02. : 3:29 pm] TiKels -- Using the exact same network it was able to perfectly approximate a different set of data, but if I switch the data to my case it just looks awful[2016-5-02. : 3:29 pm] Vrael -- thats probably the best, though I also support your decision to go with a simpler model lol[2016-5-02. : 3:28 pm] TiKels -- That's just the thing. I don't know enough about the method to actually tell you what's going wrong. I'm gonna ask the prof about it[2016-5-02. : 3:26 pm] TiKels -- You mean my training data? It's handed to me. I don't get to generate it[2016-5-02. : 3:25 pm] TiKels -- I eneed up swithing to a method using radial feedback with gaussIan activation functions[2016-5-02. : 3:23 pm] TiKels -- There was a set of x and y values that looked similar to a sine wave. I need to make a neutral network approximate this function and then determine its effectiveness in extrapolation and interpolation. Then, perform sensitivity analysis as to how well it converges when changing initial conditions (eg learning rate, iteration count, etc)[2016-5-02. : 3:20 pm] TiKels -- VraelVrael shouted: there's no reason a NN should be limited to only radially symmetric data i was trying to use a particular neural network structure to do curve fitting. The method is called back propogation. The activation/threshold function was bipolar sigmoid.[2016-5-02. : 3:12 pm] Vrael -- but a shitty algorithm with great features will outperform the strongest algorithm with shitty features[2016-5-02. : 3:12 pm] Vrael -- unless you're trying to do automated feature discovery with 'deep learning' you probably don't even need a neural network and will get equivalent results with a faster algorithm, if training time is an issue for you[2016-5-02. : 3:11 pm] Vrael -- however, the point most people miss is that the NN probably is not the problem, most likely it's your feature set[2016-5-02. : 3:10 pm] Vrael -- there's no reason a NN should be limited to only radially symmetric data[2016-5-02. : 3:04 pm] Vrael -- also to use them properly you di need to know how they work and why they work and all those other important details, or you'll end up like my co-workers who use this shit wrong and build shitty models that don't work[2016-5-02. : 3:03 pm] Vrael -- SacrieurSacrieur shouted: It's a waste of effort on my part to even attempt it, since I'm not going to school for eight years to learn about artificial intelligence and neural networks. also 1 semester class will probably bring you up to date[2016-5-02. : 3:03 pm] Vrael -- SacrieurSacrieur shouted: And also since neural networks are relatively new, there really isn't that much support for it. this is not true, also neural networks were developed in the 60's[2016-5-02. : 3:01 pm] Vrael -- TiKelsTiKels shouted: What's a common engineering coding language? Or one that generalizes well to other engineering languages python. also maybe something like julia, scala, or go, but really too many engineers use java[2016-5-02. : 2:56 pm] Clokr_ -- Oh god, I'm looking at the source code and it has not a single comment.[2016-5-02. : 2:38 pm] jjf28 -- LanthanideLanthanide shouted: apparently only to new messages, not to replies LanthanideLanthanide shouted: apparently only to new messages, not to replies LanthanideLanthanide shouted: bit dumb QFT[2016-5-02. : 1:57 pm] Clokr_ -- CorboCorbo shouted: yes it does I was going to look on his webpage. I have been checking the StormLib documentation as I'm rewriting the MPQ I/O code for SF:U.[2016-5-02. : 1:40 pm] lil-Inferno -- Mini Moose 2707Mini Moose 2707 shouted: You're complicated to build, but not to work with. Up at 6:26 like a family man LMAO [2016-5-02. : 1:39 pm] lil-Inferno -- TiKelsTiKels shouted: It's really not that complicated. Don't be so lazy, sacrieur rekt [2016-5-02. : 12:03 pm] Corbo -- Clokr_Clokr_ shouted: Why are there this many MPQ in the StarCraft version you download from the Blizzard store? Starcraft.mpq? Broodwar.mpq? Voyager7456Voyager7456 shouted: Clokr_ I think they're the contents of the disks since they've added official no-CD support pretty much, yeah.[2016-5-02. : 11:51 am] Voyager7456 -- Clokr_Clokr_ shouted: Why are there this many MPQ in the StarCraft version you download from the Blizzard store? Starcraft.mpq? Broodwar.mpq? I think they're the contents of the disks since they've added official no-CD support[2016-5-02. : 11:10 am] Clokr_ -- Why are there this many MPQ in the StarCraft version you download from the Blizzard store? Starcraft.mpq? Broodwar.mpq? |
