Abstract: We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method lever-ages relational patterns ...
Many real-world optimization applications involve solving expensive optimization problems that have a high cost of computation [1], [2], simulation [3], [4], or experiment [5], [6]. Furthermore, the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results