Grounded semantics is typically learnt from utterance-level meaning representations (e.g., successful database retrievals, denoted objects in images, moves in a game). We explore learning word and utterance meanings by continuous observation of the actions of an instruction follower (IF). While an instruction giver (IG) provided a verbal description of a configuration of objects, IF recreated i...

In a recent paper (Chliamovitch, et al., 2015), we suggested using the principle of maximum entropy to generalize Boltzmann’s Stosszahlansatz to higher-order distribution functions. This conceptual shift of focus allowed us to derive an analog of the Boltzmann equation for the two-particle distribution function. While we only briefly mentioned there the possibility of a hydrodynamical treatment...

The maximum entropy method has been used to reconstruct images in a wide range of astronomical fields, but in its traditional form it is restricted to the reconstruction of strictly positive distributions. We present an extension of the standard method to include distributions that can take both positive and negative values. The method may therefore be applied to a much wider range of astronomi...

Objective Bayesianism has been criticised on the grounds that objective Bayesian updating, which on a finite outcome space appeals to the maximum entropy principle, differs from Bayesian conditionalisation. The main task of this paper is to show that this objection backfires: the difference between the two forms of updating reflects negatively on Bayesian conditionalisation rather than on objec...

In many practical situations, we only know a few first moments of a random variable, and out of all probability distributions which are consistent with this information, we need to select one. When we know the first two moments, we can use the Maximum Entropy approach and get normal distribution. However, when we know the first three moments, the Maximum Entropy approach doe snot work. In such ...

The Maximum Entropy Principle (MEP) maximises the entropy provided that the effort remains constant. The Principle of Least Effort (PLE) minimises the effort provided that the entropy remains constant. The paper investigates the relation between these two principles. In some kinds of effort functions, called admissible, it is shown that these two principles are equivalent. The results are illus...

This work was supported in part by the Office of Naval Research under Grant F-149. AbstractIn this paper, we design, and also experimentally verify, a passivity-based controller that forces an induction motor which has significant magnetic saturation to track a time-varying optimal flux trajectory. As a result, we are able to provide close tracking of a time-varying speed/position trajectory t...

Given physical systems, counting rule for their statistical mechanical descriptions need not be unique, in general. It is shown that this nonuniqueness leads to the existence of various canonical ensemble theories, which equally arise from the definite microcanonical basis. Thus, the Gibbs theorem for canonical ensemble theory is not universal, and maximum entropy principle is to be appropriate...

This paper describes the New York University 2012 system for the KBP regular slot filling (SF) task. The NYU 2012 SF system has a similar architecture to the NYU 2011 system. We improved our distant-supervision based slot-filling component with a few techniques including filtering errors by statistical measures collected from the source corpus, and relabeling erroneous training examples with a ...