Vision System for AGI: Problems and Directions
| Autor: | Nikolai Skorobogatko, Alexey Potapov, Oleg Scherbakov, Innokentii Zhdanov, Sergey Rodionov, Maxim Peterson |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Machine vision
Computer science media_common.quotation_subject 02 engineering and technology Task (project management) 03 medical and health sciences 0302 clinical medicine Discriminative model Human–computer interaction Perception 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 030217 neurology & neurosurgery Generative grammar media_common |
| Zdroj: | Artificial General Intelligence ISBN: 9783319976754 AGI |
| DOI: | 10.1007/978-3-319-97676-1_18 |
| Popis: | What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI. We show the role of discriminative and generative models in achieving efficient and general solution of this task, thus specifying the task in more detail. We discuss some existing generative and discriminative models and demonstrate their insufficiency for our purposes. Finally, we discuss some architectural dilemmas and open questions. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|