Substantial research on deep learning-based emergent communication uses the referential game framework, specifically the Lewis signaling game, however we argue that successful communication in this game typically only need one or two symbols for target image classification because of a sampling pitfall in the training data. To address this issue, we provide a theoretical analysis and introduce a combinatorial algorithm SolveMinSym (SMS) to solve the symbolic complexity for classification, which is the minimum number of symbols in the message for successful communication. We use the SMS algorithm to create datasets with different symbolic complexity to empirically show that data with higher symbolic complexity increases the number of effective symbols in the emergent language.

The graph isomorphism problem remains one of those mysteries in theoretical computer science that fascinates laypersons and experts alike. In 1979, Garey and Johnson mentioned the problem in their renowned book on computers and intractability but, in fact, it dates back even earlier and has been unresolved for over half a century. In 2015, a major advance hit the media: Babai's quasipolynomial algorithm. This was the first improvement for the general problem in over 30 years. And yet it remains an open problem. Maybe surprisingly, there are various and quite distinct areas in which the problem finds applications.

In this paper we present a procedural content generator using Non-negative Matrix Factorisation (NMF). We use representative levels from five dissimilar content generators to train NMF models that learn patterns about the various components of the game. The constructed models are then used to automatically generate content that resembles the training data as well as to generate novel content through exploring new combinations of patterns. We describe the methodology followed and we show that the generator proposed has a more powerful capability than each of generator taken individually. The generator's output is compared to the other generators using a number of expressivity metrics. The results show that the proposed generator is able to resemble each individual generator as well as demonstrating ability to cover a wider and more novel content space.

Object Analysis, from this paper point of view, is just a continuity to the already well defined Object Oriented Programming and modeling techniques, with a difference, that is, we will be looking for automated methods realizing the analysis of the object, and eventually construct an object model of a given environment -or a signal. From one hand the "Object" concept define a central point for Object's Data storage, and the functions, interfacing it to the external world, and on the other hand, the "Object" concept, threw its hierarchy, is an actual investment of "similarities" between different object forms, known as polymorphisms . Object programming has been used, with a great success, in computer science. But the thinking process, or the analysis process, generating these models, is of course nothing but intelligence; our intelligence, with its inherent complexity. In our search for an automated object-analysis capable algorithms -or machines, image processing, and more generally signal processing, are the most capable in what we know in science. To this date, image-processing science, coupled to the information processing science, do provide us with different analysis technique of the signal that can be categorized into these categories: 1.