Читать книгу Cyberphysical Smart Cities Infrastructures. Optimal Operation and Intelligent Decision Making онлайн

60 страница из 94

In the past few years, there has been significant progress in the fields of computer vision, natural language processing, and reinforcement learning, thanks to the advancements in deep learning models. Many things are now possible because of these that seemed impossible a few years ago. However, most of the work has been done in isolation from other lines of work. It means that the trained model can only take one type of data (e.g. image, text, video) as the input and perform a single task that it is asked for. Consequently, such a model acts as a single‐sensory machine as opposed to a multi‐sensory one. Also, for the most part, they all belong to Internet artificial intelligence (AI) rather than embodied AI. The goal of Internet AI is learning patterns in text, images, and videos from the datasets collected from the Internet.

If we zoom out and look at the way models in Internet AI being trained, we realize that generally supervised classification is the way to go. For instance, we provide a certain number of dog and cat photos along with the corresponding labels to a perception model. Moreover, if the number is large enough, the model then can successfully learn the differences between these two animals and discriminate between them. Learning via flashcards falls under the same umbrella for humans.