Do you think, when you train a Convolutional Neural Network (CNN) to classify between images it is exactly understanding the image as we humans perceive? It’s difficult to answer, as for most of the times Deep learning models are often considered to be a black box. We feed in the data and then we get the output. Whatever happens in between this flow is very difficult to debug. Though we get the accurate predictions, it may not be true that they are intelligent enough to perceive the same way as we do. Continue reading
Tag: CNN
Building a Reverse Image Search Engine
Ever wondered, how does the Google reverse image search engine works which take in an image and returns you the most similar images in a fraction of a second? How does the Pinterest let you search the visually similar images of the selected objects? Sounds interesting? Do you want to understand and build similar kind of a system? If yes then you are at the right place. Continue reading