AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The History of Pattern Recognition
In the mid-2000s, it was possible to build computer vision systems by hand using interest point detectors or a SIFT, DANCY features and sticking an SVM on top. At that time, the datasets were so small that those methods that use more hand engineering work better than components. And there was a C change when basically when, you know, datasets became bigger and GPUs became available. That's what essentially made people change their mind about how they wanted to do things. Now we can train the entire thing end to end with a deep learning system and it learns its own features.