Just-in-time learning for bottom-up enumerative synthesis

Just-In-Time Learning

Rapid and accelerating changes in job skills and knowledge requirements call for learning responses of increasing complexity. Core life-long learning is necessary to function as thoughtful and productive humans in society. Varieties of on-the-job training (OJT) and just-in-time learning (JITL) techniques are necessary to support evolving learning requirements. We will take the toolbuilder’s per...

Just-in-Time Texture Synthesis

Texture bombing is a texture synthesis approach that saves memory by stopping short of assembling the output texture from the arrangement of input texture patches; instead, the arrangement is used directly at run time to texture surfaces. However, several problems remain in need of better solutions. One problem is improving texture diversification. A second problem is that mipmapping cannot be ...

Graphene synthesis: Nanoribbons from the bottom-up.

A Bottom-Up Model of Skill Learning

We present a skill learning model CLARION. Different from existing models of high-level skill learning that use a topdown approach (that is, turning declarative knowledge into procedural knowledge), we adopt a bottom-up approach toward low-level skill learning, where procedural knowledge develops first and declarative knowledge develops later. CLARION is formed by integrating connectionist, rei...

Bottom-Up Learning of Markov Network Structure

The structure of a Markov network is typically learned using top-down search. At each step, the search specializes a feature by conjoining it to the variable or feature that most improves the score. This is inefficient, testing many feature variations with no support in the data, and highly prone to local optima. We propose bottom-up search as an alternative, inspired by the analogous approach ...