Skip to content

Commit a051ac6

Browse files
committed
fix readme
1 parent 2508deb commit a051ac6

File tree

2 files changed

+4
-4
lines changed

2 files changed

+4
-4
lines changed

README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -229,9 +229,9 @@ It is also possible to introduce multiple regularizations by increasing the leng
229229

230230
The adaptors is a module for realizing domain adaptation.
231231

232-
Domain adaptation in CML is achieved by adding <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;L(v_i,&space;\\theta)&space;=&space;\\|f(x_i;\\theta)-v_i\\|^2" title="L(v_i, \theta) = \|f(x_i;\theta)-v_i\|^2" /> to the loss for feature <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;x_i" title="x_i" /> of item <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;i" title="i" /> . The same is true for the user. This allows us to reflect attribute information in the embedding vector.
232+
Domain adaptation in CML is achieved by adding <img src="https://latex.codecogs.com/gif.latex?\inline&space;\bg_black&space;L(v_i,&space;\theta)&space;=&space;\|f(x_i;\theta)-v_i\|^2" title="L(v_i, \theta) = \|f(x_i;\theta)-v_i\|^2" /> to the loss for feature <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;x_i" title="x_i" /> of item <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;i" title="i" /> . The same is true for the user. This allows us to reflect attribute information in the embedding vector.
233233

234-
MLPAdaptor is a class of adaptors that assumes a multilayer perceptron in function <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;f(x_i;\\theta)" title="f(x_i;\theta)" />.
234+
MLPAdaptor is a class of adaptors that assumes a multilayer perceptron in function <img src="https://latex.codecogs.com/gif.latex?\inline&space;\bg_black&space;f(x_i;\theta)" title="f(x_i;\theta)" />.
235235

236236
You can set up the adaptor as shown in the code below
237237

README_ja.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -230,9 +230,9 @@ criterion = losses.MinTripletLoss(margin=1, regularizers=regs).to(device)
230230

231231
adaptors はドメイン適合を実現するためのモジュールです。
232232

233-
CMLにおけるドメイン適合はアイテム <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;i" title="i" /> の特徴量 <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;x_i" title="x_i" />に対して、<img src="https://latex.codecogs.com/gif.latex?\bg_black&space;f(x_i;\\theta)" title="f(x_i;\theta)" /> を損失に加えることで達成します。ユーザーについても同様です。これによって埋め込みベクトルに属性情報を反映することができます。
233+
CMLにおけるドメイン適合はアイテム <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;i" title="i" /> の特徴量 <img src="https://latex.codecogs.com/gif.latex?\bg_black&space;x_i" title="x_i" />に対して、<img src="https://latex.codecogs.com/gif.latex?\inline&space;\bg_black&space;L(v_i,&space;\theta)&space;=&space;\|f(x_i;\theta)-v_i\|^2" title="L(v_i, \theta) = \|f(x_i;\theta)-v_i\|^2" /> を損失に加えることで達成します。ユーザーについても同様です。これによって埋め込みベクトルに属性情報を反映することができます。
234234

235-
MLPAdaptor は<img src="https://latex.codecogs.com/gif.latex?\bg_black&space;f(x_i;\\theta)" title="f(x_i;\theta)" />に多層パーセプトロンを仮定した Adaptor クラスです。
235+
MLPAdaptor は<img src="https://latex.codecogs.com/gif.latex?\inline&space;\bg_black&space;f(x_i;\theta)" title="f(x_i;\theta)" />に多層パーセプトロンを仮定した Adaptor クラスです。
236236

237237
以下のようにモデルに組み込むことができます。
238238

0 commit comments

Comments
 (0)