-
#
1. [ cheat sheet about DL/ML architectures](http://www.asimovinstitute.org/neural-network-zoo/)
2. http://deeplearninggallery.com/ - Deep Learning Gallery - a curated list of awesome deep l…
-
- 深層学習 day3
- 深層学習day3-1
> ［訂正］動画中02:09:38時点、資料に誤りがありますので訂正いたします。
【誤】* functions.d_sigmoid(u[:,t+1]) → 【正】* functions.d_sigmoid(u[:,t]) ※最後のuの添え字はu[:,t]が正しい
> ［訂正］動画中04:30:00時点、資料に誤りがありますので訂正いたします…
-
Now that LCZero is training and gaining elo quite rapidly, I'd like to promote it in several forums but I was thinking we need something catchy to attract users so they can not only help, but also fol…
-
I was reviewing a game RoyalZeroSlow lost:
Game: https://online-go.com/game/11665509
SGF: https://online-go.com/api/v1/games/11665509/sgf
Full log: http://termbin.com/1ozj
The interesting thin…
-
Version 0.10 is released now. If no major bugs surface in the next few days the server will start enforcing this version.
There is this 1500+ post issue where most plans for the future were posted …
-
1fdfb1c5 trained to 155(834f35fa)
https://www.dropbox.com/s/64lsyjfefrg1zpy/40b_155_328k.gz?dl=0
https://drive.google.com/file/d/1lsL1bLNJ-ck4FAE3wlI1U0mF1V1EjI6U/view?usp=sharing
-
is the aim to produce much stronger with weight bigger size or not so much stronger and keep the size increases small ?
and also care about the time of self play to get promotion?
some possible size…
-
https://research.fb.com/facebook-open-sources-elf-opengo/
ELF OpenGo
ELF OpenGo is a reimplementation of AlphaGoZero / AlphaZero. It was trained on 2,000 GPUs over a two week period, and has achie…
-
I ran extensive tests of LZ 40b nets for over 3 months, at low visits (1 and 20), medium (400 visits) and nominal 1600 visits. And thx to @herazul who contributed to some of the 1600 visits matches ; …
-
### 深層学習day3
**Section1：再帰型ニューラルネットワークの概念**
【要点】
再帰型ニューラルネットワーク(RNN)とは時間的順序を追って一定間隔ごとに観測され、相互に統計的依存関係が認められるデータ系列(時系列データ)に対応可能なニューラルネットワークである。
RNNの構成例を下記に示す。
![image](https://user-images.githubu…