karpathy / neuraltalk

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
5.41k stars 1.32k forks source link

Why optimizing the Ws matrix directly? #45

Open meanmee opened 8 years ago

meanmee commented 8 years ago

Other approaches like [Show and Tell] use a We matrix for word embedding which optimize the We , But in neuraltalk I found that it direcly optimize the Ws in which each raw represent a word. So Why do this way? or which way performs better?