Tomaso Poggio, Qianli Liao, Georgios Evangelopoulos, and Tejas Kulkarni.
Thrust 5: Theories of Intelligence
The thrust aims to provide theoretical frameworks and common mathematical tools for understanding visual intelligence, for guiding computer implementations, and for informing and interpreting experiments in the Center.
Our working hypothesis for vision suggests two main different stages of visual processing:
- The first 100ms of vision in the ventral stream are mostly feedforward and correspond to what we may call immediate perception (following Julesz). We conjecture that the main computational goal is to generate image representations that can be used to answer different types of basic questions. Our theoretical framework to describe feedforward processing in the hierarchy of cortical areas is i-theory.
- More specific, task-dependent questions require different computations that involve top-down, possibly iterative processing. We are working on two theoretical frameworks to deal with this stage: generative models&probabilistic inference and top-down visual routines.
We will give a brief overview of the state of Thrust 5, followed by flash-like presentations of three projects:
- application of i-theory to the face network in macaque brain
- application of i-theory to speech
- examples of models based on the probabilistic/generative framework
We will then open an informal discussion around the approach, its problems and its many open questions.