While therewardcompensation mechanism isunknown,the learner can adapt his (her) decision to the past reward feedback so as to maximize the sum of rewards.

To tackle such an issue as well as promote the quality of object attention, we introduce asimple yet effectiveSelfErasing Network (SeeNet) to prohibit attentions from spreading to unexpected background regions.

Key attributes (cf. Figure 1) include the challenging task of classifying doppelganger animals,

We present a novel approach for nonparametric regression using wavelet basis functions.

Neural Information Processing Systems http://nips.cc/

In real-world applications of education, an effective teacher adaptively chooses the next example to teach based on the learner's current state. However, most existing work in algorithmic machine teachingfocuses on the batch setting, where adaptivity plays no role. In this paper, we study the case of teaching consistent, version space learners in an interactive setting. At any time step, the teacher provides an example, the learner performs an update, and the teacher observes the learner'snew state.

Neural Information Processing Systems http://nips.cc/