Timeline for Best python library for neural networks
Current License: CC BY-SA 3.0
38 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 11, 2018 at 23:39 | answer | added | n1k31t4 | timeline score: 4 | |
| Nov 19, 2018 at 11:51 | comment | added | Marco Fumagalli | I'd add CNTK , presented in jun 2017 by Microsoft , Python API stable , with performance competiting with tensorflow minimaxir.com/2017/06/keras-cntk | |
| Apr 11, 2018 at 19:28 | answer | added | Federico Caccia | timeline score: 3 | |
| Oct 13, 2017 at 11:06 | comment | added | j b | Please define your criteria for "best" | |
| Jul 17, 2017 at 23:33 | comment | added | gerrit | Cross-site duplicate: scicomp.stackexchange.com/q/5110/3212 | |
| May 29, 2017 at 17:43 | history | edited | Blaszard | CC BY-SA 3.0 |
remove thanks
|
| Jan 27, 2017 at 18:46 | answer | added | Franck Dernoncourt | timeline score: 4 | |
| Dec 12, 2016 at 15:58 | history | made wiki | Post Made Community Wiki by Sean Owen | ||
| Dec 12, 2016 at 15:20 | review | Close votes | |||
| Dec 12, 2016 at 15:58 | |||||
| Dec 11, 2016 at 21:03 | answer | added | itdxer | timeline score: 2 | |
| Oct 26, 2016 at 20:40 | answer | added | Franck Dernoncourt | timeline score: 3 | |
| Apr 28, 2016 at 6:27 | history | protected | CommunityBot | ||
| Apr 1, 2016 at 2:13 | review | Close votes | |||
| Apr 1, 2016 at 15:22 | |||||
| Feb 9, 2016 at 19:29 | answer | added | scttl | timeline score: 1 | |
| Jan 1, 2016 at 9:19 | answer | added | hoaphumanoid | timeline score: 5 | |
| Dec 8, 2015 at 17:59 | comment | added | Ogaday | I can't vouch for it, but Brainstorm seems to be the spiritual successor to PyBrain and looks promising. | |
| Dec 7, 2015 at 1:10 | answer | added | Franck Dernoncourt | timeline score: 5 | |
| Nov 26, 2015 at 17:49 | review | Close votes | |||
| Nov 27, 2015 at 13:53 | |||||
| Nov 19, 2015 at 4:16 | answer | added | Franck Dernoncourt | timeline score: 7 | |
| Nov 10, 2015 at 18:28 | answer | added | srobinson | timeline score: 6 | |
| Nov 10, 2015 at 1:00 | answer | added | Franck Dernoncourt | timeline score: 19 | |
| Jul 13, 2015 at 16:11 | comment | added | Emre | So use multiple GPUs...nobody uses CPUs for serious work in neural networks. If you can get Google-level performance out of a good GPU or two, just what are you going to do with a thousand CPUs? | |
| Jul 13, 2015 at 15:25 | comment | added | Neil Slater | @Emre: Scalable is different to high performance. It typically means you can solve larger problems by adding more resources of the same type you have already. Scalability still wins out, when you have 100 machines available, even if your software is 20 times slower on each of them . . . (although I'd rather pay the price for 5 machines and have benefits of both GPU and multi-machine scale). | |
| Jul 11, 2015 at 6:51 | comment | added | Emre | h2o doesn't even use the GPU yet so it's hardly scalable. | |
| Jul 9, 2015 at 21:20 | comment | added | 0xF | Does any of this packages scale like h2o deep learning? As far as I know lasagne doesn't.Theano does support GPU so as any library basing on it,but does any of them support mapreduce or spark. | |
| Jul 9, 2015 at 8:37 | comment | added | Neil Slater | There is also Keras - github.com/fchollet/keras - which is relatively recent. The problems with tracking "best" by any measure, and keeping the Q&A valid over time is why this sort of question is usually off topic in other Stack Exchange networks. | |
| Jul 9, 2015 at 0:15 | answer | added | Def_Os | timeline score: 9 | |
| Jul 7, 2015 at 12:20 | comment | added | Rafael_Espericueta | And now there's a new contender - Scikit Neuralnetwork: Has anyone had experience with this yet? How does it compare with Pylearn2 or Theano? | |
| Mar 25, 2015 at 19:45 | answer | added | Martin Thoma | timeline score: 41 | |
| Sep 17, 2014 at 11:42 | comment | added | user70747 | If you want to only use Restricted Boltzmann Machine, you can stick with scikit-learn as well. | |
| Jul 21, 2014 at 15:35 | answer | added | royalstream | timeline score: 9 | |
| Jul 17, 2014 at 18:25 | answer | added | user2556 | timeline score: 6 | |
| Jul 9, 2014 at 0:05 | vote | accept | marcodena | ||
| Jul 8, 2014 at 20:14 | comment | added | Air | See also stackoverflow.com/q/2276933/2359271 | |
| Jul 8, 2014 at 12:38 | review | Close votes | |||
| Jul 9, 2014 at 0:08 | |||||
| Jul 8, 2014 at 10:36 | answer | added | jnovacho | timeline score: 23 | |
| Jul 7, 2014 at 19:55 | answer | added | Madison May | timeline score: 132 | |
| Jul 7, 2014 at 19:17 | history | asked | marcodena | CC BY-SA 3.0 |