原创 調參之learning rate

The learning rate is perhaps the most important hyperparameter. If you have time to tune only one hyperparameter,

原创 特徵歸一化

題目(2):爲什麼需要對數值類型的特徵做歸一化 (normalization)? 回答角度: 歸一化的方式 歸一化的作用 各方式的優劣 數據類型 結構化數據:數值型、類別型(ordinal, nominal) 非結構化數據:

原创 Uniform convergence may be unable to explain generalization in deep learning

本文價值:understand the limitations of u.c. based bounds / cast doubt on the power of u.c. bounds to fully explain gene