English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Information theory has been very successful in obtaining performance limitsfor various problems such as communication, compression and hypothesis testing.Likewise, stochastic control theory provides a characterization of optimalpolicies for Partially Observable Markov Decision Processes (POMDPs) usingdynamic programming. However, finding optimal policies for these problems iscomputationally hard in general and thus, heuristic solutions are employed inpractice. Deep learning can be used as a tool for designing better heuristicsin such problems. In this paper, the problem of active sequential hypothesistesting is considered. The goal is to design a policy that can reliably inferthe true hypothesis using as few samples as possible by adaptively selectingappropriate queries. This problem can be modeled as a POMDP and bounds on itsvalue function exist in literature. However, optimal policies have not beenidentified and various heuristics are used. In this paper, two new heuristicsare proposed: one based on deep reinforcement learning and another based on aKL-divergence zero-sum game. These heuristics are compared withstate-of-the-art solutions and it is demonstrated using numerical experimentsthat the proposed heuristics can achieve significantly better performance thanexisting methods in some scenarios.

Policy Design for Active Sequential Hypothesis Testing using Deep Learning