Viewing a response to: @geoffrey/re-krishtopa-what-are-neural-networks-why-they-are-so-popular-and-what-problems-can-solve-20160805t044934756z
It depends on the task, but basically you are right. Training stage requires a lot of computational power. If someone implements Deep Learning at Amazon servers, he probably spends few million dollars for just server infrastructure
| author | krishtopa |
|---|---|
| permlink | re-geoffrey-re-krishtopa-what-are-neural-networks-why-they-are-so-popular-and-what-problems-can-solve-20160805t054327153z |
| category | academia |
| json_metadata | {"tags":["academia"]} |
| created | 2016-08-05 05:43:30 |
| last_update | 2016-08-05 05:43:30 |
| depth | 2 |
| children | 2 |
| last_payout | 2016-09-04 15:43:36 |
| cashout_time | 1969-12-31 23:59:59 |
| total_payout_value | 0.000 HBD |
| curator_payout_value | 0.000 HBD |
| pending_payout_value | 0.000 HBD |
| promoted | 0.000 HBD |
| body_length | 231 |
| author_reputation | 48,350,480,258,009 |
| root_title | "What Are Neural Networks, Why They Are So Popular And What Problems Can Solve" |
| beneficiaries | [] |
| max_accepted_payout | 1,000,000.000 HBD |
| percent_hbd | 10,000 |
| post_id | 617,595 |
| net_rshares | 0 |
It does require "a lot" of computing power. But considering what leaps and bounds we've come in the last few years, you would be amazed at what you can do with a normal desktop PC or even a smartphone these days.
| author | marcelhattingh |
|---|---|
| permlink | re-krishtopa-re-geoffrey-re-krishtopa-what-are-neural-networks-why-they-are-so-popular-and-what-problems-can-solve-20160805t121859314z |
| category | academia |
| json_metadata | {"tags":["academia"]} |
| created | 2016-08-05 12:19:03 |
| last_update | 2016-08-05 12:19:03 |
| depth | 3 |
| children | 1 |
| last_payout | 2016-09-04 15:43:36 |
| cashout_time | 1969-12-31 23:59:59 |
| total_payout_value | 0.000 HBD |
| curator_payout_value | 0.000 HBD |
| pending_payout_value | 0.000 HBD |
| promoted | 0.000 HBD |
| body_length | 212 |
| author_reputation | 557,841,623,208 |
| root_title | "What Are Neural Networks, Why They Are So Popular And What Problems Can Solve" |
| beneficiaries | [] |
| max_accepted_payout | 1,000,000.000 HBD |
| percent_hbd | 10,000 |
| post_id | 622,885 |
| net_rshares | 0 |
yeah. Computers and processors are developed rapidly. Moreover there are some amazing parallelization technologies that can essentially alleviate computational requirements. I think in a few years training of neural network will barely be a big problem.
| author | krishtopa |
|---|---|
| permlink | re-marcelhattingh-re-krishtopa-re-geoffrey-re-krishtopa-what-are-neural-networks-why-they-are-so-popular-and-what-problems-can-solve-20160805t123053881z |
| category | academia |
| json_metadata | {"tags":["academia"]} |
| created | 2016-08-05 12:31:03 |
| last_update | 2016-08-05 12:31:03 |
| depth | 4 |
| children | 0 |
| last_payout | 2016-09-04 15:43:36 |
| cashout_time | 1969-12-31 23:59:59 |
| total_payout_value | 0.000 HBD |
| curator_payout_value | 0.000 HBD |
| pending_payout_value | 0.000 HBD |
| promoted | 0.000 HBD |
| body_length | 254 |
| author_reputation | 48,350,480,258,009 |
| root_title | "What Are Neural Networks, Why They Are So Popular And What Problems Can Solve" |
| beneficiaries | [] |
| max_accepted_payout | 1,000,000.000 HBD |
| percent_hbd | 10,000 |
| post_id | 623,105 |
| net_rshares | 0 |
hiveblocks