John Mark Bishop

Goldsmiths, University of London · Department of Computing

Artificial Neural Networks have reached “grandmaster” and even “super-human” performance across a variety of games, from those involving perfect information, such as Go, to those involving imperfect information, such as “Starcraft”. Such technological developments from artificial intelligence (AI) labs have ushered concomitant applications across t...

Artificial Neural Networks have reached Grandmaster and even super-human performance across a variety of games: from those involving perfect-information (such as Go) to those involving imperfect-information (such as Starcraft). Such technological developments from AI-labs have ushered concomitant applications across the world of business - where an...

Stochastic diffusion search (SDS) is a global Swarm Intelligence optimisation technique based on the behaviour of ants, rooted in the partial evaluation of an objective function and direct communication between agents. Although population based decision mechanisms employed by many Swarm Intelligence methods can suffer poor convergence resulting in...

Stochastic diffusion search (SDS) is a global Swarm Intelligence optimisation technique based on the behaviour of ants, rooted in the partial evaluation of an objective function and direct communication between agents. Although population based decision mechanisms employed by many Swarm Intelligence methods can suffer poor convergence resulting in...

A Letter to Nature demonstrated that a simple ant-inspired ‘tandem calling’ recruitment mechanism improved task performance in a group of robots. In these experiments a group of robots attempt to locate ‘food’ and return it to base. On its return a successful robot tries to recruit another to help exploit its find. As a result a population of robot...

Recent articles by Schneider and Turner (Turner and Schneider, 0000; Schneider and Turner, 2017) outline an artificial consciousness test (ACT); a new, purely behavioral process to probe subjective experience (“phenomenal consciousness”: tickles, pains, visual experiences, and so on) in machines; work that has already resulted in a provisional pate...

We study an entity search/match problem that requires retrieved tuples match to an input entity query. We assume the input queries are of the same type as the tuples in a materialised relational table. Existing keyword search over relational databases focuses on assembling tuples from a variety of relational tables in order to respond to a keyword...

One of the questions that have defined and simultaneously divided philosophy is the question of the absolute nature of reality. Whether we have the right to ask the very question; whether we can know reality or merely be content with the epistemic conditions that make its experience possible. One response to this question, currently enjoying someth...

In this paper two swarm intelligence algorithms are used, the first leading the “attention” of the swarm and the latter responsible for the tracing mechanism. The attention mechanism is coordinated by agents of Stochastic Diffusion Search where they selectively attend to areas of a digital canvas (with line drawings) which contains (sharper) corner...

For many years three key aspects of creative processes have been glossed over by theorists eager to avoid the mystery of consciousness and instead embrace an implicitly more formal, computational vision: autonomy, phenomenality and the temporally embedded and bounded nature of creative processes. In this paper we will discuss autopoiesis and creati...

Probabilistic record linkage is a well established topic in the literature. Fellegi-Sunter probabilistic record linkage and its enhanced versions are commonly used methods, which calculate match and non- match weights for each pair of records. Bayesian network classifiers – naive Bayes classifier and TAN have also been successfully used here. Recen...

Automatic semantic annotation of data from databases or the web is an important pre-process for data cleansing and record linkage. It can be used to resolve the problem of imperfect field alignment in a database or identify comparable fields for matching records from multiple sources. The annotation process is not trivial because data values may be...

Population based decision mechanisms employed by many Swarm Intelligence methods can suffer poor convergence resulting in ill-defined halting criteria and loss of the best solution. Conversely, as a result of its resource allocation mechanism, the solutions found by Stochastic Diffusion Search enjoy excellent stability. Previous implementations of...

The term autopoiesis, (meaning 'self') and 'poiesis' (meaning 'creation, production') defines a system capable of reproducing and maintaining itself. The term was introduced by the theoretical biologists, Humberto Maturana and Francisco Varela, in 1972 to define the self-maintaining chemistry of living cells. The term has subsequently also been app...

In a reflective and richly entertaining piece from 1979, Doug Hofstadter playfully imagined a conversation between ‘Achilles’ and an anthill (the eponymous ‘Aunt Hillary’), in which he famously explored many ideas and themes related to cognition and consciousness. For Hofstadter, the anthill is able to carry on a conversation because the ants that...

There are many ways to think about systems that choreograph movements that we socially conceive of as dance. This theoretical work is inspired by Alfred North Whitehead’s process view of organisation], viewed though the transformational conceptual-lens of autopoietic theory (Maturana and Varela); according to which we view a creative system as a cl...

This paper touches upon the philosophical concept of evil in the context of creativity in general, and computational creativity in particular. In this work, dark creativity is introduced and linked to two important pre-requisites of creativity (i.e. freedom and constraints). A hybrid computational system is then presented; it includes one swarm int...

Probabilistic record linkage has been well investigated in recent years. The Fellegi-Sunter probabilistic record linkage and its enhanced version are commonly used methods, which calculate match and non-match weights for each pair of corresponding fields of record-pairs. Bayesian network classifiers – naive Bayes classifier and TAN have also been s...

In the spirit of Searle’s definition of weak and strong artificial intelligence, this paper presents a discussion on weak computational creativity in swarm intelligence systems. It addresses the concepts of freedom and constraint and their impact on the creativity of the underlying systems. An analogy is drawn on mapping these two ‘prerequisites’ o...

The use of clustering in various applications is key to its popularity in data analysis and data mining. Algorithms used for optimisation can be extended to perform clustering on a dataset. In this paper, a swarm intelligence technique — Stochastic Diffusion Search — is deployed for clustering purposes. This algorithm has been used in the past as a...

This chapter conceives the history of neural networks emerging from two millennia of attempts to rationalise and formalise the operation of mind. It begins with a brief review of early classical conceptions of the soul, seating the mind in the heart; then discusses the subsequent Cartesian split of mind and body, before moving to analyse in more de...

One of the questions that have defined and simultaneously divided phi-losophy is the question of the absolute nature of reality. Whether we have the right to ask the very question; whether we can know reality or merely be content with the epistemic conditions that make its experience possible. One response to this question, currently enjoying somet...

Title: Decoding De Kooning Swarms of ants and birds set off to decode a complex painting by Willem De Kooning in their own swarmic way. The step-by-step behaviour of the swarms is detailed in [1]. This video displays consecutive cycles of the behaviour of the swarms. A cycle begins when swarms choose a line from the canvas on the right and produc...

John Searle’s Chinese Room Argument (CRA) purports to demonstrate that syntax is not sufficient for semantics, and, hence, because computation cannot yield understanding, the computational theory of mind, which equates the mind to an information processing system based on formal computations, fails. In this paper, we use the CRA, and the debate tha...

Stochastic diffusion search (SDS) is a multi-agent global optimisation technique based on the behaviour of ants, rooted in the partial evaluation of an objective function and direct communication between agents. Standard SDS, the fundamental algorithm at work in all SDS processes, is presented here. Parameter estimation is the task of suitably fitt...

In the fourteenth chapter of The Philosophy of Information, Luciano Floridi puts forth a criticism of `digital ontology' as a step toward the articulation of an `informational structural realism'. Based on the claims made in the chapter, the present paper seeks to evaluate the distinctly Kantian scope of the chapter from a rather unconventional vie...

‘Sensorimotor Theory’ offers a new enactive approach to perception that emphasises the role of motor actions and their effect on sensory stimuli. The seminal publication that launched the field is the target paper co-authored by J. Kevin O’Regan and Alva Noë and published in Behavioral and Brain Sciences (BBS) for open peer commentary in 2001 [27].

This book analyzes the philosophical foundations of sensorimotor theory and discusses the most recent applications of sensorimotor theory to human computer interaction, child’s play, virtual reality, robotics, and linguistics. Why does a circle look curved and not angular? Why does red not sound like a bell? Why, as I interact with the world, is th...

Stochastic Diffusion Search, first incepted in 1989, belongs to the extended family of swarm intelligence algorithms. In contrast to many nature-inspired algorithms, stochastic diffusion search has a strong mathematical framework describing its behaviour and convergence. In addition to concisely exploring the algorithm in the context of natural swa...

Context • Constructivist approaches to cognition have mostly been descriptive, and now face the challenge of specifying the mechanisms that may support the acquisition of knowledge. Departing from cognitivism, however, requires the development of a new functional framework that will support causal, powerful and goal-directed behavior in the context...

We present a hypothetical solution to the binding problem-a subject of fundamental importance for studies of cognition and consciousness. The solution is based on the idea of tagging neuronal messages and on the mechanism of Stochastic Diffusion Search. Tags allow to organise information processing to bind separate features into coherent, stable me...

This paper reviews two main strategies for dealing with the threat posed by radically enactive/embodied cognition to traditional cognitive science. Both strategies invoke action oriented representations (AORs). They differ in emphasizing different features ...

Computational formalisms have been pushing the boundaries of the field of computing for the last 80 years and much debate has surrounded what computing entails; what it is, and what it is not. This paper seeks to explore the boundaries of the ideas of computation and provide a framework for enabling a constructive discussion of computational ideas....

Swarm-based multi-agent systems have been deployed in non-photorealistic rendering for many years. This paper introduces a novel approach in adapting a swarm intelligence algorithm --- Stochastic Diffusion Search --- for producing non-photorealistic images. The swarm-based system is presented with a digital image and the agents move throughout the...

This paper introduces a novel approach deploying the mechanism of 'attention' by adapting a swarm intelligence algorithm --- Stochastic Diffusion Search --- to selectively attend to detailed areas of a digital canvas. Once the attention of the swarm is drawn to a certain line within the canvas, the capability of another swarm intelligence algorithm...

Viewed in the light of the remarkable performance of ‘Watson’ - IBMs proprietary artificial intelligence computer system capable of answering questions posed in natural language - on the US general knowledge quiz show ‘Jeopardy’, we review two experiments on formal systems - one in the domain of quantum physics, the other involving a pictographic l...

The Chinese Room Argument purports to show that ‘syntax is not sufficient for semantics’; an argument which led John Searle to conclude that ‘programs are not minds’ and hence that no computational device can ever exhibit true understanding. Yet, although this controversial argument has received a series of criticisms, it has withstood all attempts...

In this paper, we introduce Stochastic Diffusion Search applied to Trees (SDST), a swarm intelligence heuristic inspired from Stochastic Diffusion Search able to solve the complex and general problem of forward planning. In SDST, each individual agent processes information concerning a unique action without "awareness" of the way in which actions a...

Swarm intelligence via its infamous struggle to identify a suitable balance between exploration and exploitation phases, provides a valuable mean to approach artificial creativity. This work deploys two swarm intelligence algorithms, one simulating the behaviour of birds flocking and fish schooling (Particle Swarm Optimisation) and the other mimick...

This work details the research aimed at applying the powerful resource allocation mechanism deployed in stochastic diffusion search (SDS) to the differential evolution (DE), effectively merging a nature inspired swarm intelligence algorithm with a biologically inspired evolutionary algorithm. The results reported herein suggest that the hybrid algo...

Undeniably, anticipation plays a crucial role in cognition. By what means, to what extent, and what it achieves remain open questions. In a BBS target article, Clark (2013) depicts an integrative model of the brain that builds on hierarchical Bayesian models of neural processing (Rao and Ballard, 1999; Friston, 2005; Brown et al., 2011), and their...

This Special Issue includes a number of those papers, along with others submitted after the event, all of which investigate one or more of these key concepts within AI. The contributors come from a wide range of disciplines, and this adds to the rich fecund of material that the issue contains. The research in this Special Issue contributes to alrea...

This work introduces two swarm intelligence algorithms—one mimicking the behaviour of one species of ants (Leptothorax acervorum) foraging (a ‘stochastic diffusion search’, SDS) and the other algorithm mimicking the behaviour of birds flocking (a ‘particle swarm optimiser’, PSO)—and outlines a novel integration strategy exploiting the local search...

A three year Knowledge Transfer Partnership between @UK plc, University of Reading and Goldsmiths College, London produced an e-procurement system called SpendInsight which the National Audit Office reports could save the NHS Σ500 million per annum. An extension to the system, GreenInsight, enables procurers to assess the environmental impact of th...

A novel approach of integrating two swarm intelligence algorithms is considered, one simulating the behaviour of birds flocking (Particle Swarm Optimisation) and the other one (Stochastic Diffusion Search) mimics the recruitment behaviour of one species of ants - Leptothorax acervorum. This hybrid algorithm is assisted by a biological mechanism ins...

In the spirit of Searle's definition of weak and strong artificial intelligence, this paper presents a discussion on weak com-putational creativity in swarm intelligence systems. It addresses the concepts of freedom and constraint and their impact on the creativity of the underlying systems. An analogy is drawn on mapping these two 'prerequisites'...

When discussing the place of robotic system in civilian and military society, typically two opposing key themes will emerge: dreams of robot heaven and nightmares of robot hell. And it was in the 1960s, in this dual context—the robot as facilitator, the robot as destroyer—that the poet Richard Brautigan highlighted a vision of humans and robots wor...

This study reports early research aimed at applying the powerful resource allocation mechanism deployed in Stochastic Diffusion Search (SDS) [4] to the Particle Swarm Optimiser (PSO) metaheuristic [22], effectively merging the two swarm intelligence algorithms. The results reported herein suggest that the hybrid algorithm, exploiting information sh...

This work details early research aimed at applying the powerful resource allocation mechanism deployed in Stochastic Diffusion Search (SDS) to the Differential Evolution (DE), effectively merging a nature inspired swarm intelligence algorithm with a biologically inspired evolutionary algorithm. The results reported herein suggest that the hybrid al...

In this work, a novel approach of merging two swarm intelligence algorithms is considered - one mimicking the behaviour of ants foraging (Stochastic Diffusion Search [5]) and the other algorithm simulating the behaviour of birds flocking (Particle Swarm Optimisation [17]). This hybrid algorithm is assisted by a mechanism inspired from the behaviour...

The integration of Swarm Intelligence (SI) algorithms and Evolutionary algorithms (EAs) might be one of the future approaches in the Evolutionary Computation (EC). This work narrates the early research on using Stochastic Diffusion Search (SDS) – a swarm intelligence algorithm – to empower the Differential Evolution (DE) – an evolutionary algorithm...

The most cursory examination of the history of artificial intelligence highlights numerous egregious claims of its researchers, especially in relation to a populist form of ‘strong’ computationalism which holds that any suitably programmed computer instantiates genuine conscious mental states purely in virtue of carrying out a specific series of co...

The journal of Cognitive Computation is defined in part by the notion that biologically inspired computational accounts are at the heart of cognitive processes in both natural and artificial systems. Many studies of various important aspects of cognition (memory, observational learning, decision making, reward prediction learning, attention control...

An information-processing paradigm in the brain is proposed, instantiated in an artificial neural net-work using biologically motivated temporal encod-ing. The network will locate within the external world stimulus, the target memory, defined by a specific pattern of micro-features. The proposed network is robust and efficient. Akin in operation to...

A novel Swarm Intelligence method for best-fit search, Stochastic Diffusion Search, is presented capable of rapid location of the optimal solution in the search space. Population based search mechanisms employed by Swarm Intelligence methods can suffer lack of convergence resulting in ill defined stopping criteria and loss of the best solution. Con...

We introduce and describe the Multiple Gravity Assist problem, a global optimisation problem that is of great interest in the design of spacecraft and their trajectories. We discuss its formalization and we show, in one particular problem instance, the performance of selected state of the art heuristic global optimisation algorithms. A deterministi...

The concept of partial evaluation of fitness functions, together with mechanisms manipulating the resource allocation of population based search methods , are presented in the context of Stochastic Diffusion Search, a novel swarm intelligence metaheuristic that has many similarities with ant and evolutionary algorithms. It is demonstrated that the...

The issue of how decomposable objective functions can form an integral part of the analysis of exploration and exploitation is presented, with the aim of investigating how more efficient optimization algorithms may be developed. Stochastic Diffusion Search is presented as an example algorithm, and is shown theoretically to be more efficient than si...

Purpose To present an account of cognition integrating second‐order cybernetics (SOC) together with enactive perception and dynamic systems theory. Design/methodology/approach The paper presents a brief critique of classical models of cognition then outlines how integration of SOC, enactive perception and dynamic systems theory can overcome some w...

With application to the specic problem of multiple gravity assist trajectory design, a deterministic search space pruning algorithm is developed that displays both polynomial time and space com- plexity. This is shown empirically to achieve search space reductions of greater than six orders of magnitude, thus reducing signicantly the complexity of...

An analysis of Stochastic Diffusion Search (SDS), a novel and efficient optimisation and search algorithm, is presented, resulting in a derivation of the minimum acceptable match resulting in a stable convergence within a noisy search space. The applicability of SDS can therefore be assessed for a given problem.

Stochastic Diffusion Search (SDS) is an efficient generic search method, originally developed as a population-based solution to the problem of best-fit pattern matching. In re-cent years, similarities between previously unrelated search methods have been discovered [28] and further unification and hybridisation is expected. In this context this pap...

The initial argument presented herein is not significantly original--it is a simple reflection upon a notion of computation originally developed by Putnam (Putnam 1988; see also Searle, 1990) and criticised by Chalmers et al. (Chalmers, 1994; 1996a, b; see also the special issue, What is Computation?, in Minds and Machines, 4:4, November 1994). In...

Stochastic Diusion Search is an ecient probabilistic best- fit search technique, capable of transformation invariant pattern match- ing. Although inherently parallel in operation it is dicult to implement eciently in hardware as it requires full inter-agent connectivity. This paper describes a lattice implementation, which, while qualitatively re-...

One of the most pervading concepts underlying computa-tional models of information processing in the brain is linear input inte-gration of rate coded uni-variate information by neurons. After a suitable learning process this results in neuronal structures that statically repre-sent knowledge as a vector of real valued synaptic weights. Although thi...

In 1994 John Searle stated (Searle 1994: 11-12) that the Chinese Room Argument (CRA) is an attempt to prove the truth of the premise: led him to the conclusion that ‘programs are not minds’ and hence that computationalism, the idea that the essence of thinking lies in computational processes and that such processes thereby underlie and explain cons...

Traditionally Computer Colorant Formulation has been implemented using a theory of radiation transfer known as Kubelka-Munk (K-M) theory. Kubelka-Munk theory allows the prediction of spectral reflectance for a mixture of components (colorants) that have been characterised by absorption K and scattering S coefficients. More recently it has been sugg...

This article presents the long-term behaviour analysis of Stochastic Diffusion Search (SDS), a distributed agent-based system for best-fit pattern matching. SDS operates by allocating simple agents into different regions of the search space. Agents independently pose hypotheses about the presence of the pattern in the search space and its potential...

An umber of the most powerful robust estimation algorithms, such as RANSAC, MINPRAN and LMS ,h ave their basis in selecting random minimal sets of data to instantiate hypotheses. However, their perfor- mance degrades in higher dimensional spaces due to the exponentially decreasing probability of sampling a set that is composed entirely of inliers....

The most famous challenge to the aims of computational cognitive science and artificial intelligence is the philosopher John Searle's 1980 'Chinese Room' argument. Searle argued that the fact that machines can be devised to pass the 'Turing test', that is respond to input with the same output that a mind would give, does not mean that mind and mac...

The most efiective algorithms for model parameterisation in the presence of high noise, suchas RANSAC,MINPRANand Least Median Squares, use random sampling of data points to instantiate model hypotheses. However, their performance degrades in higher dimensionality due to the exponentially decreasing probability of sampling a set of inliers. It is su...

In the Transcendental Aesthetic part of the Critique of Pure Reason, Immanuel Kant stated the a priori necessity of the singularity of space that, “we can represent to ourselves only one space; and if we speak of diverse spaces, we mean thereby only parts of one and the same space … these parts cannot precede the one all-embracing space … they can...

Discusses the potential of computer-mediated communication to reduce the social isolation experienced by many deaf and hard-of-hearing individuals. Communication presents significant problems for this group of people, some of which can be bridged by communicating via the Internet or e-mail. deaf Internet users were surveyed by use of a questionnair...

The paper discusses ensemble behaviour in the Spiking Neuron Stochas- tic Diusion Network, SNSDN, a novel network exploring biologically plausible information processing based on higher order temporal coding. SNSDN was proposed as an alternative solution to the binding problem (1). SNSDN operation resembles Stochastic Diusion Search, SDS, a non- de...

This paper describes three artificial life research projects that illustrate communication and control in the animal and the machine, thus reflecting Wiener's definition of cybernetics. Mobile robots are described which have been used to test algorithms for learning simple tasks, where for instance the benefits of communication between these robots...

In this paper we present a connectionist searching technique- the Stochastic Diffusion Search (SDS), capable of rapidly locating a specified pattern in a noisy search space. In operation SDS finds the position of the prespecified pattern or if it does not exist - its best instantiation in the search space. This is achieved via parallel exploration...

The conventional computational description of brain operations has to be understood in a metaphorical sense. In this paper arguments supporting the claim that this metaphor is too restrictive are presented. A new metaphor more accurately describing recently discovered emergent characteristics of neuron functionality is proposed and its implications...

Since the advent of the McCulloch/Pitts model, the prevailing metaphor at the core of most connectionist thought is that of neuronal operation being defined in terms of computation. At the WnnW '93 conference a novel weightless network (the Hybrid Stochastic Diffusion Network, HSDN) was introduced. It has since been shown that this network will loc...

This paper introduces the Focused Stochastic Diffusion Network as a novel method of self-localisation for an autonomous wheelchair in a busy, complex environment. The space of possible positions is explored in parallel by a set of cells searching in a competitive co- operative manner for the most likely position of the wheelchair in its environment...

Weightless neural networks have been used in pattern recognition vision systems for many years. The operation of these networks requires that binary values be produced from the input data, and the simplest method of achieving this is to generate a logic '1' if a given sample from the input data exceeds some threshold value, and a logic '0' otherwis...

The Stochastic Diffusion Search algorithm -an integral part of Stochastic Search Networks is investigated. Stochastic Diffusion Search is an alternative solution for invariant pattern recognition and focus of attention. It has been shown that the algorithm can be modelled as an ergodic, finite state Markov Chain under some non-restrictive assumptio...

The SENARIO project is develoing a sensor-aided intelligent navigation system that provides high-level navigational aid to users of powered wheelchairs. The authors discuss new and improved technologies developed within SENARIO concerning task/path planning, sensing and positioning for indoor mobile robots as well as user interface issues. The auto...

This paper compares the speed of convergence of several popular training algorithms over two real problems. The algorithms compared are backpropagation, SuperSAB, Quickprop, conjugate gradient, RPROP and SASS. This work builds on previous studies, by making use of a benchmark collection Proben1, which is designed to improve the quality of training...

This paper describes work in progress carried out as part of the SENARIO project. The SENARIO project is developing a sensor-aided intelligent navigation system that provides high-level navigational aid to users of powered wheelchairs. SENARIO is designed to be adaptable to a range of commercially available, powered wheelchairs. This paper discusse...

The Department of Cybernetics at the University of Reading has recently developed some simple mobile robots which can move around in an environment they perceive through simple ultrasonic sensors. Information from these sensors has allowed the robots to learn simple tasks, but more sensors are needed if the robots are to learn other tasks. Therefor...

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being rea...

Artificial Intelligence: A Modern Myth by KellyJohn, Ellis Horwood, Hemel Hempstead, UK, 1995, 253 pp. (£34.95). - Volume 13 Issue 6 - J. M. Bishop