Symbolic Architectures Research Articles

Cellular Automata Can Reduce Memory Requirements of Collective-State Computing.

Various nonclassical approaches of distributed information processing, such as neural networks, reservoir computing (RC), vector symbolic architectures (VSAs), and others, employ the principle of collective-state computing. In this type of computing, the variables relevant in computation are superimposed into a single high-dimensional state vector, the collective state. The variable encoding uses a fixed set of random patterns, which has to be stored and kept available during the computation. In this article, we show that an elementary cellular automaton with rule 90 (CA90) enables the space-time tradeoff for collective-state computing models that use random dense binary representations, i.e., memory requirements can be traded off with computation running CA90. We investigate the randomization behavior of CA90, in particular, the relation between the length of the randomization period and the size of the grid, and how CA90 preserves similarity in the presence of the initialization noise. Based on these analyses, we discuss how to optimize a collective-state computing model, in which CA90 expands representations on the fly from short seed patterns-rather than storing the full set of random patterns. The CA90 expansion is applied and tested in concrete scenarios using RC and VSAs. Our experimental results show that collective-state computing with CA90 expansion performs similarly compared to traditional collective-state models, in which random patterns are generated initially by a pseudorandom number generator and then stored in a large memory.

Trustable service discovery for highly dynamic decentralized workflows

The quantity and capabilities of smart devices and sensors deployed as part of the Internet of Things (IoT) and accessible via remote microservices is set to rise dramatically as the provision of interactive data streaming increases. This introduces opportunities to rapidly construct new applications by interconnecting these microservices in different workflow configurations. The challenge is to discover the required microservices, including those from trusted partners and the wider community, whilst being able to operate robustly under diverse networking conditions. This paper outlines a workflow approach that provides decentralized discovery and orchestration of verifiably trustable services in support of multi-party operations. The approach is based on adoption of patterns from self-sovereign identity research, notably Verifiable Credentials, to share information amongst peers based on attestations of service descriptions and prior service usage in a privacy preserving and secure manner. This provides a dynamic, trust-based framework for ratifying and evaluating the qualities of different services. Collating these new service descriptions and integrating with existing decentralized workflow research based on vector symbolic architecture (VSA) provides an enhanced semantic search space for efficient and trusted service discovery that is necessary to support a diverse range of emerging edge-computing environments. An architecture for a dynamic decentralized service discovery system, is designed, and described through application to a scenario which uses trusted peers’ reported experiences of an anomaly detection service to determine service selection.

VENUE OLAHRAGA DAYUNG KALIMANTAN SELATAN

South Borneo often to take a part in rowing sport competitions starting from local, national, to international class. South Borneo rowing athletes have potency to compete in national into international competition and reach medals that became the pride of South Borneo Province. However, that situation isn’t match with adequate training facility and coaching so that the athlete’s potency is not supported by the coaching situation. South Borneo Rowing Sport Venue is designed with a purpose to fulfill the athlete’s coaching function to be professional athletes from South Borneo. Through Kayuh Baimbai concept program and symbolic architecture method that inspired from dragon boat, this venue is expected to create sense of enthusiasm, motivation, and the meaning of relationship between rowing sport and nature in athletes and South Borneo citizen through physical and non physical setting in rowing sport venue that can realize sustainability in South Borneo rowing sport.

КУЛЬТУРНІ ПРАКТИКИ ПРОСТОРУ ТА ПАМ'ЯТІ: ДОСВІД ТОПОГРАФІЇ ТА КУЛЬТУРНОГО ЛАНДШАФТУ (НА МАТЕРІАЛАХ МЕМОРІАЛЬНОГО ЦЕНТРУ ГОЛОКОСТУ "БАБИН ЯР")

The Babyn Yar memorial complex is one of the few Holocaust memorial spaces in Eastern Europe, located on the site of the mass murder of people during the occupation of Kyiv by German troops in 1941-1943, especially the Jewish population. The article presents the study of logic and aesthetics of memorial space with the help of concepts optics of "Symbolic Architecture" (Georg Hegel), "Sublime" (Immanuel Kant), as well as "Greate Tradition" (Robert Redfield, Milton Singer) and "Walking" (Olga Freidenberg). This optic helps to understand the specificity of de-differentiation of the cultural landscape of historical place and symbolic architecture, as well as the augmented reality in the practice of memorial procession and community, which it constructs through the oppositions highlighting of subterranean and terrestrial, visual and audible, whole and fragmented, and symmetrical and shapeless. Spatial forms of cultural memory organization help avoid memorycide outside ideological disputes and Europeanization of Holocaust tragedy images. It can be noted that the tragic events of World War II, which revealed the "Dialectic of the Enlightenment" and the dark side of Modernity in general, led to the need to re-organize the space of cultural memory. There was a lack of only the internalized structures of the subject and only discursive forms of its objectification to preserve and transmit grief of this level of intensity. The Ukrainian experience of visualizing the tragedy of the Holocaust continues the traditional means of symbolic architecture length and monumentality, sublimity. At the same time, the scale of the complex allows to diversify the practices of the image and thus make new connotations in the practice of its memorialization. In particular, a variety of forms of symbolic architecture and augmented reality was a successful technique, which allows to emphasize the status of the procession as a form of cultural memory, as well as to successfully use the landscape of the historical city in the logic of de-differentiation of subterranean and terrestrial, where other forms of syncretism visual and audio integral and fragmented, symmetrical and shapeless – serve as artistic techniques that work to increase the involvement in the space of the memorial actor of cultural memory.

Vector Symbolic Architectures for Context-Free Grammars

Vector symbolic architectures (VSA) are a viable approach for the hyperdimensional representation of symbolic data, such as documents, syntactic structures, or semantic frames. We present a rigorous mathematical framework for the representation of phrase structure trees and parse trees of context-free grammars (CFG) in Fock space, i.e. infinite-dimensional Hilbert space as being used in quantum field theory. We define a novel normal form for CFG by means of term algebras. Using a recently developed software toolbox, called FockBox, we construct Fock space representations for the trees built up by a CFG left-corner (LC) parser. We prove a universal representation theorem for CFG term algebras in Fock space and illustrate our findings through a low-dimensional principal component projection of the LC parser state. Our approach could leverage the development of VSA for explainable artificial intelligence (XAI) by means of hyperdimensional deep neural computation.

A comparison of vector symbolic architectures

Vector Symbolic Architectures combine a high-dimensional vector space with a set of carefully designed operators in order to perform symbolic computations with large numerical vectors. Major goals are the exploitation of their representational power and ability to deal with fuzziness and ambiguity. Over the past years, several VSA implementations have been proposed. The available implementations differ in the underlying vector space and the particular implementations of the VSA operators. This paper provides an overview of eleven available VSA implementations and discusses their commonalities and differences in the underlying vector space and operators. We create a taxonomy of available binding operations and show an important ramification for non self-inverse binding operations using an example from analogical reasoning. A main contribution is the experimental comparison of the available implementations in order to evaluate (1) the capacity of bundles, (2) the approximation quality of non-exact unbinding operations, (3) the influence of combining binding and bundling operations on the query answering performance, and (4) the performance on two example applications: visual place- and language-recognition. We expect this comparison and systematization to be relevant for development of VSAs, and to support the selection of an appropriate VSA for a particular task. The implementations are available.

Vector Semiotic Model for Visual Question Answering

In this paper, we propose a Vector Semiotic Model as a possible solution to the symbol grounding problem in the context of Visual Question Answering. The Vector Semiotic Model combines the advantages of a Semiotic Approach implemented in the Sign-Based World Model and Vector Symbolic Architectures. The Sign-Based World Model represents information about a scene depicted on an input image in a structured way and grounds abstract objects in an agent’s sensory input. We use the Vector Symbolic Architecture to represent the elements of the Sign-Based World Model on a computational level. Properties of a high-dimensional space and operations defined for high-dimensional vectors allow encoding the whole scene into a high-dimensional vector with the preservation of the structure. That leads to the ability to apply explainable reasoning to answer an input question. We conducted experiments are on a CLEVR dataset and show results comparable to the state of the art. The proposed combination of approaches, first, leads to the possible solution of the symbol-grounding problem and, second, allows expanding current results to other intelligent tasks (collaborative robotics, embodied intellectual assistance, etc.).

ShapeArchit: Shape-Inspired Architecture Design with Space Planning

Various techniques have been proposed to improve the level of automation in stages of architectural design. We present an interactive interface, along with optimization algorithms focused on designing early stage symbolic architecture. The architect specifies some simple shape requirements by inputting a few binary images that resemble the shape of the building from different viewpoints. Our optimizer uses these to generate a conceptual 3D design that is guided by various aesthetic and structural requirements. We also develop an approach for planning the inner space of the given architecture model. The architect specifies idealized requirements on the key functional rooms by using instances of simple 3D primitive shapes. The pose and location of each instance are parameters of the optimization. By coupling this process together with the shape inspired exterior design process, we can construct good initial conceptual designs. We develop modified cuckoo search algorithms to efficiently obtain feasible solutions via offline optimization. Several examples are presented to illustrate the methodology and results. User studies based on a proposed dataset and interviews with domain experts have been carried out to demonstrate the usability and effectiveness of our system and algorithms.

Legacy of Fascist Architecture. Ideology and Conservation: the case of the former Casa del Fascio e dell’Ospitalità in Predappio

The Casa del Fascio e dell'Ospitalita of Predappio is a significant case study of an iconic building that, more than others, has materialized the “architectural propaganda” of the fascist regime in Italy between the two World Wars. The project by Arnaldo Fuzzi (1891-1974) was supposed to be the manifesto of the architectural and technological progress of the Fascist regime, but it will become instead an expression of the failure of its management skills. In the post-war period, this building fell into a state of neglect, due both to the fact that it was one of the most symbolic architectureS of the regime and to the inability to find an adequate re-use – becoming a sort of “dead monument”. In 2010 the former Casa del Fascio was appointed a “listed building” giving a boost to the preservation of this architecture as a document of a “difficult heritage”. The present contribution matches historical research and preservation, explaining the path that leads up to the current restoration project (2019-2020). The intervention methodology searches for a balance between the preservation of the building identity and the necessary adaptation to the current needs, choosing a multidisciplinary and coordinated approach.

Architecture and friendship among nations: the shifting politics of cultural diplomacy in Tbilisi, Georgia

ABSTRACT In 1938, the Soviet Georgian administration inaugurated the iconic Institute of Marx, Engels, and Lenin (IMEL) in Tbilisi under pretences of socialist unity and friendship among Soviet nations. Three quarters of a century later, the same building – now privatised, heavily renovated, and re-branded – was re-inaugurated as the seven-star Biltmore Hotel. The hotel’s grand opening included an enormous video projection on the western façade, telling the story of a new friendship among nations, this time between independent Georgia and the United Arab Emirates as the hotel’s financiers. This article tracks the shifting politics of cultural diplomacy associated with this adaptive reuse project. It contributes to a growing body of scholarship on cultural diplomacy by delving deeper into the social, political, and economic implications surrounding the particular use of friendship rhetoric in such practices. In doing so, it charts the manipulation of architecture to communicate international cooperation and the power of its patrons. Drawing from archival sources, field observations, media analysis, and focus groups, the work argues that, rather than an outmoded means of public service announcement, symbolic architecture continues to be a crucial arena for state politics, one entangled with new modes of spectacle in the city.

Buddhist Kingship and Symbolic Architecture in Silla Korea

The evolution of kingship in the early Korean state of Silla (ca. 300–935) was closely linked with the accommodation of various Buddhist practices that conferred symbolic legitimacy and promoted royal authority. During the sixth and seventh centuries, Silla’s sovereigns assimilated several overlapping approaches to statecraft and kingship drawing on Sinitic and imagined Indian models mediated through such Buddhist literature as the Sūtra for Humane Kings and the Sūtra of Golden Light, resonant with policies followed in the Northern and Southern Dynasties in China. Buddhist monarchs in Silla adopted several overlapping and increasingly sophisticated approaches to symbolically consolidate and project political authority. Silla merged native East Asian cosmological symbolism with Buddhist architecture to establish royal legitimacy. Hwangnyong Monastery combines Sinitic symbolism with Buddhist-inspired propaganda, which both assert Silla’s regional dominion. The significance of the yellow dragon was astrological, signifying Silla’s ascendancy among the Korean states. Hwangnyong Monastery was the locus for state-protection rituals centered on the Sūtra for Humane Kings beginning in the sixth century, but early monasteries built with a single golden hall and two pagodas may have some connection to the Sūtra of Golden Light. Sach’ŏnwang Monastery was the most important twin pagoda monastery in seventh-century Silla, with Yŏngmyo Monastery and Kamŭn Monastery also performing a magico-religious function as loci for ritual centered on divine protection by the four heavenly kings, the eight classes of divine beings, spirit generals, and wholesome deities from the unseen world.

Reasoning and learning with context logic

Context logic (CL), a logical language similar in style to description logics but with a more cognitive motivation as a logical language of cognition, was developed since 2007 to provide a new approach to the symbol grounding problem, a key problem for reliable intelligent environments and other intelligent sensory systems. CL is a three-layered integrated hierarchy of languages: a relational base layer with the expressiveness of propositional logic (CLA), a quantifier-free decidable language (CL0), and an expressive language with full quantification (CL1). As was shown in 2018, the core CLA reasoning can be implemented on a variant of Kanerva’s Vector Symbolic Architecture, the activation bit vector machine (ABVM), shedding new light on the fundamental cognitive faculties of symbol grounding and imagery, but the system raised two questions: first, the core reasoning algorithm was a classical EXPTIME reasoner; second, fundamental aspects for a learning algorithm were sketched but not presented with a full algorithm. This paper addresses those two questions. We present a probabilistic linear time algorithm for reasoning over conjunctive normal form (CNF) CLA formulae together with a dual probabilistic linear time algorithm for learning CLA statements by collecting experienced snapshots in a disjunctive normal form (DNF).

Multi-modal actuation with the activation bit vector machine

Research towards a new approach to the abstract symbol grounding problem showed that through model counting there is a correspondence between logical/linguistic and coordinate representation in the visuospatial domain. The logical/verbal description of a spatial layout directly gives rise to a coordinate representation that can be drawn, with the drawing reflecting what is described. The main characteristic of this logical property is that it does not need any semantic information or ontology apart from a separation into symbols/words referring to relations and symbols/words referring to objects. Moreover, the complete mechanism can be implemented efficiently on a brain inspired cognitive architecture, the Activation Bit Vector Machine (ABVM), an architecture that belongs to the Vector Symbolic Architectures. However, the natural language fragment captured previously was restricted to simple predication sentences, with the corresponding logical fragment being atomic Context Logic (CLA), and the only actuation modality leveraged was visualization. This article extends the approach on all three aspects: adding a third category of action verbs we move to a fragment of first-order Context Logic (CL1), with modalities requiring a temporal dimension, such as film and music, becoming available. The article presents an ABVM generating sequences of images from texts.

Motivational and affective drivers of right-wing populism support: Insights from an Austrian presidential election

Research has identified political disenchantment as an important driver for the recent spread of right-wing populism. The cultural backlash approach explains this relationship as a counter response to progressive socio-political developments in Western societies. Drawing on previous work, the present research examines motivational and affective factors underlying the support of right-wing populist parties. We hypothesize that a perceived alienation from the symbolic architecture of a society may decrease levels of psychological need satisfaction, which may catalyze into anxiety and anger. As the “political system” represents an important reflective surface for the socio-political status quo, we expected lower levels of need satisfaction and its resulting affective consequences to help explain the relationship between political disenchantment and right-wing populist support. We tested these tenets based on data from the 2016 Austrian presidential election (n = 626). The results of a structural equation model corroborated our predictions with some exceptions. Data indicated a negative relationship between political disenchantment and need satisfaction. Moreover, decreased need satisfaction was associated with increased self-reported anxiety and anger. Political disenchantment indirectly predicted support for a right-wing populist presidential candidate through decreased need satisfaction and anger, thus corroborating the role of anger as an important driver underlying right-wing populism support. Counterintuitively, the data indicated a negative relationship between anxiety and right-wing support. We discuss theoretical and practical implications, as well as limitations stemming from sample characteristics and the employed cross-sectional design.

Resonator Networks, 1: An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures.

The ability to encode and manipulate data structures with distributed neural representations could qualitatively enhance the capabilities of traditional neural networks by supporting rule-based symbolic reasoning, a central property of cognition. Here we show how this may be accomplished within the framework of Vector Symbolic Architectures (VSAs) (Plate, 1991; Gayler, 1998; Kanerva, 1996), whereby data structures are encoded by combining high-dimensional vectors with operations that together form an algebra on the space of distributed representations. In particular, we propose an efficient solution to a hard combinatorial search problem that arises when decoding elements of a VSA data structure: the factorization of products of multiple codevectors. Our proposed algorithm, called a resonator network, is a new type of recurrent neural network that interleaves VSA multiplication operations and pattern completion. We show in two examples-parsing of a tree-like data structure and parsing of a visual scene-how the factorization problem arises and how the resonator network can solve it. More broadly, resonator networks open the possibility of applying VSAs to myriad artificial intelligence problems in real-world domains. The companion article in this issue (Kent, Frady, Sommer, & Olshausen, 2020) presents a rigorous analysis and evaluation of the performance of resonator networks, showing it outperforms alternative approaches.

Resonator Networks, 2: Factorization Performance and Capacity Compared to Optimization-Based Methods.

We develop theoretical foundations of resonator networks, a new type of recurrent neural network introduced in Frady, Kent, Olshausen, and Sommer (2020), a companion article in this issue, to solve a high-dimensional vector factorization problem arising in Vector Symbolic Architectures. Given a composite vector formed by the Hadamard product between a discrete set of high-dimensional vectors, a resonator network can efficiently decompose the composite into these factors. We compare the performance of resonator networks against optimization-based methods, including Alternating Least Squares and several gradient-based algorithms, showing that resonator networks are superior in several important ways. This advantage is achieved by leveraging a combination of nonlinear dynamics and searching in superposition, by which estimates of the correct solution are formed from a weighted superposition of all possible solutions. While the alternative methods also search in superposition, the dynamics of resonator networks allow them to strike a more effective balance between exploring the solution space and exploiting local information to drive the network toward probable solutions. Resonator networks are not guaranteed to converge, but within a particular regime they almost always do. In exchange for relaxing the guarantee of global convergence, resonator networks are dramatically more effective at finding factorizations than all alternative approaches considered.

Exploring Learning Capability of an Agent in SOAR: Using 8-Queens Problem

Cognitive architecture deals with describing the intelligent behavior of an agent. The description of intelligent behavior states how well an agent can solve and represent variety of problems of the domain-independent task. The intelligence of an agent is considered in terms of its learning capabilities. In this study, we are exploring solving 8-Queens combinatorial problem using SOAR symbolic cognitive architecture. An 8-Queens problem consists of various constraints which is expressed by Constraint Satisfaction Problem (CSP). The constraints are further generalized in the Fuzzy Constraint Satisfaction Problem (FCSP) (a sub domain of CSP), which simplifies the condition of constraints by providing the priority value to the location of queen. This paper provides a way to solve 8-Queens problem by using a heuristic search and backtracking. These concepts are implemented in SOAR to find an efficient solution of similar task. The implementation of 8-Queens in SOAR provides computation efficiency in solving and a way for an agent to learn their own production rules to solve similar domain problems. The 8-Queens problem is analyzed by two parameters. First parameter defines how an agent can learn and transfer rules to solve similar domain problem. The second parameter describes number of chunks required to solve a problem.

La voz del lugar, el lugar de la voz: cartografías ciudadanas

In this art action project we join different voices to the urban fabric, building an interpersonal dialogue in which different people, all of which live in a given social space, relate the experience of that space in their inner topography. The stone, symbolic architecture of that self that stablishes coordinates and hopes to be found by other, is transformed by art in action in a communication path for the location’s inhabitants. The account of the topographic experiences offered by the citizenship is analysed using a variant of the panel studies participatory methodology (Sun Woong, 2008), called “cohort” (De Keulenaer, 2008), which allows to identify the differences of the human experiences born from the social uses of each space, with the use of spoken maps of the city.

Efficient orchestration of Node-RED IoT workflows using a Vector Symbolic Architecture

Numerous workflow systems span multiple scientific domains and environments, and for the Internet of Things (IoT), Node-RED offers an attractive Web based user interface to execute IoT service-based workflows. However, like most workflow systems, it coordinates the workflow centrally, and cannot run within more transient environments where nodes are mobile. To address this gap, we show how Node-RED workflows can be migrated into a decentralized execution environment for operation on mobile ad-hoc networks, and we demonstrate this by converting a Node-RED based traffic congestion detection workflow to operate in a decentralized environment. The approach uses a Vector Symbolic Architecture (VSA) to dynamically convert Node-Red applications into a compact semantic vector representation that encodes the service interfaces and the workflow in which they are embedded. By extending existing services interfaces, with a simple cognitive layer that can interpret and exchange the vectors, we show how the required services can be dynamically discovered and interconnected into the required workflow in a completely decentralized manner. The resulting system provides a convenient environment where the Node-RED front-end graphical composition tool can be used to orchestrate decentralized workflows. In this paper, we further extend this work by introducing a new dynamic VSA vector compression scheme that compresses vectors for on-the-wire communication, thereby reducing communication bandwidth while maintaining the semantic information content. This algorithm utilizes the holographic properties of the symbolic vectors to perform compression taking into consideration the number of combined vectors along with similarity bounds that determine conflict with other encoded vectors used in the same context. The resulting savings make this approach extremely efficient for discovery in service based decentralized workflows.

Connecting Twenty-First Century Connectionism and Wittgenstein

By pointing to deep philosophical confusions endemic to cognitive science, Wittgenstein might seem an enemy of computational approaches. We agree (with Mills 1993) that while Wittgenstein would reject the classicist’s symbols and rules approach, his observations align well with connectionist or neural network approaches. While many connectionisms that dominated the later twentieth century could fall prey to criticisms of biological, pedagogical, and linguistic implausibility, current connectionist approaches can resolve those problems in a Wittgenstein-friendly manner. We (a) present the basics of a Vector Symbolic Architecture formalism, inspired by Smolensky (1990), and indicate how high-dimensional vectors can operate in a context-sensitive and object-independent manner in biologically plausible time scales, reflecting Wittgenstein’s notions of language-games and family resemblance; we (b) show how “soft” symbols for such a formalism can be formed with plausible learning cycles using Sparse Distributed Memory, resolving disputes surrounding Wittgenstein’s private language argument; and (c) show how connectionist networks can extrapolate meaningful patterns to solve problems, providing “ways to go on” without explicit rules, which indicates linguistic plausibility. Connectionism thus provides a systematicity and productivity that is more than a mere implementation of a classical approach, and provides Wittgenstein-friendly and Wittgenstein-illuminating models of mind and language for cognitive science.