Knowledge representation for explainable artificial intelligence

Alongside the particular need to explain the behavior of black box artificial intelligence (AI) systems, there is a general need to explain the behavior of any type of AI-based system (the explainable AI, XAI) or complex system that integrates this type of technology, due to the importance of its economic, political or industrial rights impact. The unstoppable development of AI-based applications in sensitive areas has led to what could be seen, from a formal and philosophical point of view, as some sort of crisis in the foundations, for which it is necessary both to provide models of the fundamentals of explainability as well as to discuss the advantages and disadvantages of different proposals. The need for foundations is also linked to the permanent challenge that the notion of explainability represents in Philosophy of Science. The paper aims to elaborate a general theoretical framework to discuss foundational characteristics of explaining, as well as how solutions (events) would be justified (explained). The approach, epistemological in nature, is based on the phenomenological-based approach to complex systems reconstruction (which encompasses complex AI-based systems). The formalized perspective is close to ideas from argumentation and induction (as learning). The soundness and limitations of the approach are addressed from Knowledge representation and reasoning paradigm and, in particular, from Computational Logic point of view. With regard to the latter, the proposal is intertwined with several related notions of explanation coming from the Philosophy of Science.

What transcends the Algorithm - A Critique of the Notions of a Postdigital and a Subsymbolic

Computational logic has, although since its breakthrough with the emergence of digital computers there has always been doubt, mostly been seen as something very different from human thinking; one can e.g. refer to Dreyfus’ famous criticism about what computers can’t do. Facing statistical machine learning as a new paradigm of computing, many seem to think that these lines are getting somewhat blurry. Learning algorithms, their functions not longer explicitly coded, but acquired via optimization methods, are seen as a kind of third mode, located somewhere between classical computational paradigms and human thinking. This view seems to manifest itself in the notions of postdigital and subsymbolic computing. I will argue that this view is mistaken, and machine learning does not soften boundaries posed by the digital and the symbolic, as they were already in effect regarding classical computational logic.

Functions-as-constructors higher-order unification: extended pattern unification

Unification is a central operation in constructing a range of computational logic systems based on first-order and higher-order logics. First-order unification has several properties that guide its incorporation in such systems. In particular, first-order unification is decidable, unary, and can be performed on untyped term structures. None of these three properties hold for full higher-order unification: unification is undecidable, unifiers can be incomparable, and term-level typing can dominate the search for unifiers. The so-called pattern subset of higher-order unification was designed to be a small extension to first-order unification that respects the laws governing λ-binding (i.e., the equalities for α, β, and η-conversion) but which also satisfied those three properties. While the pattern fragment of higher-order unification has been used in numerous implemented systems and in various theoretical settings, it is too weak for many applications. This paper defines an extension of pattern unification that should make it more generally applicable, especially in proof assistants that allow for higher-order functions. This extension’s main idea is that the arguments to a higher-order, free variable can be more than just distinct bound variables. In particular, such arguments can be terms constructed from (sufficient numbers of) such bound variables using term constructors and where no argument is a subterm of any other argument. We show that this extension to pattern unification satisfies the three properties mentioned above.

Quantum Uncertainties and Holism Seem to Render Irrelevant Qudit-Semantics

We consider a semantics based on the peculiar holistic features of the quantum formalism. Any formula of the language gives rise to a quantum circuit that transforms the density operator associated to the formula into the density operator associated to the atomic subformulas in a reversible way. The procedure goes from the whole to the parts against the compositionality-principle and gives rise to a semantic characterization for a new form of quantum logic that has been called “ukasiewicz quantum computational logic”. It is interesting to compare the logic based on qubit-semantics with that on qudit-semantics. Having in mind the relationships between classical logic and ukasiewicz-many valued logics, one could expect that the former is stronger than the fragment of the latter. However, this is not the case. From an intuitive point of view, this can be explained by recalling that the former is a very weak form of logic. Many important logical arguments, which are valid either in Birkhoff and von Neumann’s quantum logic or in classical logic, are generally violated.

Material Computation for a New Equilibrium in Architecture

Morphogenesis defines the schema of natural material formations as a set of merging self-organized behaviours, rules, relative forces, and limits of materialization that analytically characterize a spatial arrangement within a specific environment for achieving an equilibrium state. However, in architecture, material organization, which acts as a threshold to space, has always been treated as a secondary component in design processes. This attitude has reduced the capability to generate an architecture that is intelligently aware of its functionality and of its environment. Transforming computational models of biological systems into the computational logic of material organization found in architecture would produce an architecture that is a product of full interactions between those material logics and space. This inquiry elaborates a set of biological computational frameworks to cultivate stratified developments of knowledge-based architectural prototypes of complex hybrid-structure material morphologies as contextual schemata

Material Computation for a New Equilibrium in Architecture

Morphogenesis defines the schema of natural material formations as a set of merging self-organized behaviours, rules, relative forces, and limits of materialization that analytically characterize a spatial arrangement within a specific environment for achieving an equilibrium state. However, in architecture, material organization, which acts as a threshold to space, has always been treated as a secondary component in design processes. This attitude has reduced the capability to generate an architecture that is intelligently aware of its functionality and of its environment. Transforming computational models of biological systems into the computational logic of material organization found in architecture would produce an architecture that is a product of full interactions between those material logics and space. This inquiry elaborates a set of biological computational frameworks to cultivate stratified developments of knowledge-based architectural prototypes of complex hybrid-structure material morphologies as contextual schemata

Argumentation Mining: Techniques and Emerging Trends

By Argument we mean persuasion of a reason or reasons in support of a claim or evidence. In Artificial Intelligence computational argumentation is the field dealing with computational logic upon which many models of argumentation have been suggested. The goal of Argumentation Mining is to automatically extract structured arguments from the unstructured text. It has the potential of extracting information from web and social media, making it one of the most sought after research area. Some recent advances in computational logic and Machine Learning methods do provide a new insight to the applications for policy making, economic sciences, legal, medical and information technology. Different models have been proposed for argumentation mining with different machine learning methods applied on the argumentation frameworks proposed for this particular mining task. In this survey article we will review the existing systems and applications and will cover the three categories of argumentation models and a comparative table depicting the most frequently applied ML method. This survey paper will also cover the various challenges of the field with the new potential perspectives in this new emerging research area.

ON THE APPLİCATİON OF THE BİNARY NUMBER SYSTEM İN CREATİNG QUESTİONS STRATEGY

It is obvious that the binary number system has found widespread application in modern computer technology in order to sufficiently simplify the computational logic operations. The simple principle of operation of the binary number system allows its application in areas other than computer technology. This article examines the application of the principles of binary numbers and information technology to simplify the questioning system. In this regard, the publication of this article is relevant.

Enacting the Pandemic

This article has two objectives: First, the article seeks to make a methodological intervention in the social study of algorithms. Today, there is a worrying trend to analytically reduce algorithms to coherent and stable objects whose computational logic can be audited for biases to create fairness, accountability, and transparency (FAccT). To counter this reductionist and determinist tendency, this article proposes three methodological rules that allows an analysis of algorithmic power in practice. Second, the article traces ethnographically how an algorithm was used to enact a pandemic, and how the power to construct this disease outbreak was moved around through by an algorithmic assemblage. To do this, the article traces the assembling of a recent epidemic at the European Centre for Disease Control and Prevention—the Zika outbreak starting in 2015—and shows how an epidemic was put together using an array of computational resources, with very different spaces for intervening. A key argument is that we, analysts of algorithms, need to attend to how multiple spaces for agency, opacity, and power open and close in different parts of algorithmic assemblages. The crux of the matter is that actors experience different degrees of agency and opacity in different parts of any algorithmic assemblage. Consequently, rather than auditing algorithms for biased logic, the article shows the usefulness of examining algorithmic power as enacted and situated in practice.