What to measure next to improve decision making? On top-down task driven feature saliency

Abstract

Top-down attention is modeled as decision making based on incomplete information. We consider decisions made in a sequential measurement situation where initially only an incomplete input feature vector is available, however, where we are given the possibility to acquire additional input values among the missing features. The procecure thus poses the question what to do next? We take an information theoretical approach implemented for generality in a generative mixture model. The framework allows us reduce the decision about what to measure next in a classification problem to the estimation of a few onedimensional integrals per missing feature. We demonstrate the viability of the framework on four well-known classification problems.

The Role of Top-Down Attention in the Cocktail Party: Revisiting Cherry's Experiment after Sixty Years

“…Task-driven top-down attention as in [5] is obtained when β = 1, γ = ∞. In this work we use β = 0.2, γ = 0.33.…”

“…In these expressions µ j,k , σ More details and further references are given in [5], where the attention model was validated on four benchmark classification problems and shown to outperform a 'random' attention alternative.…”

“…While the latter definition is in broad consensus, there has been remarkably few attempts to formalize top-down attention as a statistical problem. In [5] we model the top-down attention as a decision problem based on incomplete information and analyze which feature to measure next in a classification problem.…”

“…As discussed in [1], this problem can help shed light on the mechanisms applied by human cognition. We are particularly interested in the influence of top-down attention [5], [6].…”

“…We have recently proposed a computational mechanism for task driven top-down attention based on a generative statistical model of inputs, corresponding to a 'gist' of the scene and to potential elements for attention, and task labels corresponding to possible actions chosen based on gist and attended inputs ( [5], [6]). The notion of gist refers to unspecific inputs generated in part by bottom-up attention [21].…”