2 – 02 Leveraging Neural Networks V3

Hi, I’m Calvin Lin and I work for Deep Learning Institute at NVIDIA, where we’re tasked with enabling everyone in the industry to create AI companies. For that, we need very capable AI and image captioning is where we go from mere perception modules to ones with generative capabilities. A captioning model rely on two main components, a CNN and an RNN. You’ve already learned about a variety of applications for convolutional and recurrent neural networks separately, but captioning is all about merging the two to combine their most powerful attributes. CNNs excel at preserving spatial information and images, and RNNs work well with any kind of sequential data, such as generating a sequence of words. So by merging the two, you can get a model that can find patterns and images, and then use that information to help generate a description of those images. In this lesson, I’ll go over the details of how a model like this works

%d 블로거가 이것을 좋아합니다: