# 03-30 Meeting ## Positive accuracy  Negative sample size加到100 ## All train data accuracy ### Pos跟Neg 1比200  跟positive id很接近的negative sample id  Loss Overall accuracy Positive accuracy  ### 2018 AAAI  ## 減少train的資料 只使用到2015 AAAI前當train搭配100個negative sample train 50 epoch花了6小時    Test 2015 AAAI Recall/ Hit變高 
×
Sign in
Email
Password
Forgot password
or
By clicking below, you agree to our
terms of service
.
Sign in via Facebook
Sign in via Twitter
Sign in via GitHub
Sign in via Dropbox
Sign in with Wallet
Wallet (
)
Connect another wallet
New to HackMD?
Sign up