A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: we take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. (...) We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines. (shrink)

Can humans get arbitrarily capable reinforcement learning agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question impacts how far RL can be scaled, and whether alternative paradigms must be developed in order to build safe artificial general intelligence. In this paper, we study when an RL agent has an instrumental goal to tamper with its reward process, and describe design principles that prevent instrumental (...) goals for two different types of reward tampering. Combined, the design principles can prevent reward tampering from being an instrumental goal. The analysis benefits from causal influence diagrams to provide intuitive yet precise formalizations. (shrink)

The first decade of this century has seen the nascency of the first mathematical theory of general artificial intelligence. This theory of Universal Artificial Intelligence (UAI) has made significant contributions to many theoretical, philosophical, and practical AI questions. In a series of papers culminating in book (Hutter, 2005), an exciting sound and complete mathematical model for a super intelligent agent (AIXI) has been developed and rigorously analyzed. While nowadays most AI researchers avoid discussing intelligence, the award-winning PhD thesis (Legg, (...) 2008) provided the philosophical embedding and investigated the UAI-based universal measure of rational intelligence, which is formal, objective and non-anthropocentric. Recently, effective approximations of AIXI have been derived and experimentally investigated in JAIR paper (Veness et al. 2011). This practical breakthrough has resulted in some impressive applications, finally muting earlier critique that UAI is only a theory. For the first time, without providing any domain knowledge, the same agent is able to self-adapt to a diverse range of interactive environments. For instance, AIXI is able to learn from scratch to play TicTacToe, Pacman, Kuhn Poker, and other games by trial and error, without even providing the rules of the games. These achievements give new hope that the grand goal of Artificial General Intelligence is not elusive. This article provides an informal overview of UAI in context. It attempts to gently introduce a very theoretical, formal, and mathematical subject, and discusses philosophical and technical ingredients, traits of intelligence, some social questions, and the past and future of UAI. (shrink)

Increasingly encompassing models have been suggested for our world. Theories range from generally accepted to increasingly speculative to apparently bogus. The progression of theories from ego- to geo- to helio-centric models to universe and multiverse theories and beyond was accompanied by a dramatic increase in the sizes of the postulated worlds, with humans being expelled from their center to ever more remote and random locations. Rather than leading to a true theory of everything, this trend faces a turning point after (...) which the predictive power of such theories decreases (actually to zero). Incorporating the location and other capacities of the observer into such theories avoids this problem and allows to distinguish meaningful from predictively meaningless theories. This also leads to a truly complete theory of everything consisting of a (conventional objective) theory of everything plus a (novel subjective) observer process. The observer localization is neither based on the controversial anthropic principle, nor has it anything to do with the quantum-mechanical observation process. The suggested principle is extended to more practical (partial, approximate, probabilistic, parametric) world models (rather than theories of everything). Finally, I provide a justification of Ockham's razor, and criticize the anthropic principle, the doomsday argument, the no free lunch theorem, and the falsifiability dogma.", . (shrink)

Can an agent's intelligence level be negative? We extend the Legg-Hutter agent-environment framework to include punishments and argue for an affirmative answer to that question. We show that if the background encodings and Universal Turing Machine (UTM) admit certain Kolmogorov complexity symmetries, then the resulting Legg-Hutter intelligence measure is symmetric about the origin. In particular, this implies reward-ignoring agents have Legg-Hutter intelligence 0 according to such UTMs.

The technological singularity refers to a hypothetical scenario in which technological advances virtually explode. The most popular scenario is the creation of super-intelligent algorithms that recursively create ever higher intelligences. It took many decades for these ideas to spread from science fiction to popular science magazines and finally to attract the attention of serious philosophers. David Chalmers' (JCS 2010) article is the first comprehensive philosophical analysis of the singularity in a respected philosophy journal. The motivation of my article is to (...) augment Chalmers' and to discuss some issues not addressed by him, in particular what it could mean for intelligence to explode. In this course, I will (have to) provide a more careful treatment of what intelligence actually is, separate speed from intelligence explosion, compare what super-intelligent participants and classical human observers might experience and do, discuss immediate implications for the diversity and value of life, consider possible bounds on intelligence, and contemplate intelligences right at the singularity. (shrink)

Understanding inductive reasoning is a problem that has engaged mankind for thousands of years. This problem is relevant to a wide range of fields and is integral to the philosophy of science. It has been tackled by many great minds ranging from philosophers to scientists to mathematicians, and more recently computer scientists. In this article we argue the case for Solomonoff Induction, a formal inductive framework which combines algorithmic information theory with the Bayesian framework. Although it achieves excellent theoretical results (...) and is based on solid philosophical foundations, the requisite technical knowledge necessary for understanding this framework has caused it to remain largely unknown and unappreciated in the wider scientific community. The main contribution of this article is to convey Solomonoff induction and its related concepts in a generally accessible form with the aim of bridging this current technical gap. In the process we examine the major historical contributions that have led to the formulation of Solomonoff Induction as well as criticisms of Solomonoff and induction in general. In particular we examine how Solomonoff induction addresses many issues that have plagued other inductive systems, such as the black ravens paradox and the confirmation problem, and compare this approach with other recent approaches. (shrink)

Sequential decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomonoff's theory of universal induction formally solves the problem of sequence prediction for unknown prior distribution. We combine both ideas and get a parameter-free theory of universal Artificial Intelligence. We give strong arguments that the resulting AIXI model is the most intelligent unbiased agent possible. We outline how the AIXI model can formally solve a number of problem classes, (...) including sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The major drawback of the AIXI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIXItl that is still effectively more intelligent than any other time t and length l bounded agent. The computation time of AIXItl is of the order t x 2^l. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations of the AIXI theory to other AI approaches. (shrink)

Automated reasoning about uncertain knowledge has many applications. One difficulty when developing such systems is the lack of a completely satisfactory integration of logic and probability. We address this problem directly. Expressive languages like higher-order logic are ideally suited for representing and reasoning about structured knowledge. Uncertain knowledge can be modeled by using graded probabilities rather than binary truth-values. The main technical problem studied in this paper is the following: Given a set of sentences, each having some probability of being (...) true, what probability should be ascribed to other (query) sentences? A natural wish-list, among others, is that the probability distribution (i) is consistent with the knowledge base, (ii) allows for a consistent inference procedure and in particular (iii) reduces to deductive logic in the limit of probabilities being 0 and 1, (iv) allows (Bayesian) inductive reasoning and (v) learning in the limit and in particular (vi) allows confirmation of universally quantified hypotheses/sentences. We translate this wish-list into technical requirements for a prior probability and show that probabilities satisfying all our criteria exist. We also give explicit constructions and several general characterizations of probabilities that satisfy some or all of the criteria and various (counter) examples. We also derive necessary and sufficient conditions for extending beliefs about finitely many sentences to suitable probabilities over all sentences, and in particular least dogmatic or least biased ones. We conclude with a brief outlook on how the developed theory might be used and approximated in autonomous reasoning agents. Our theory is a step towards a globally consistent and empirically satisfactory unification of probability and logic. (shrink)

The progression of theories suggested for our world, from ego- to geo- to helio-centric models to universe and multiverse theories and beyond, shows one tendency: The size of the described worlds increases, with humans being expelled from their center to ever more remote and random locations. If pushed too far, a potential theory of everything (TOE) is actually more a theories of nothing (TON). Indeed such theories have already been developed. I show that including observer localization into such theories is (...) necessary and sufficient to avoid this problem. I develop a quantitative recipe to identify TOEs and distinguish them from TONs and theories in-between. This precisely shows what the problem is with some recently suggested universal TOEs. (shrink)

In this paper, we provide a detailed review of previous classifications of 2 × 2 games and suggest a mathematically simple way to classify the symmetric 2 × 2 games based on a decomposition of the payoff matrix into a cooperative and a zero-sum part. We argue that differences in the interaction between the parts is what makes games interesting in different ways. Our claim is supported by evolutionary computer experiments and findings in previous literature. In addition, we provide a (...) method for using a stereographic projection to create a compact 2-d representation of the game space. (shrink)

Inspired by recent progress in multi-agent Reinforcement Learning (RL), in this work we examine the collective intelligent behaviour of theoretical universal agents by introducing a weighted mixture operation. Given a weighted set of agents, their weighted mixture is a new agent whose expected total reward in any environment is the corresponding weighted average of the original agents' expected total rewards in that environment. Thus, if RL agent intelligence is quantified in terms of performance across environments, the weighted mixture's intelligence is (...) the weighted average of the original agents' intelligences. This operation enables various interesting new theorems that shed light on the geometry of RL agent intelligence, namely: results about symmetries, convex agent-sets, and local extrema. We also show that any RL agent intelligence measure based on average performance across environments, subject to certain weak technical conditions, is identical (up to a constant factor) to performance within a single environment dependent on said intelligence measure. (shrink)

The theme of the philosopher as therapist dominates Nietzsche's entire opus, from his earliest writings to the Zarathustra period and beyond. Nietzsche wishes to hasten the coming and future sanctification of a new type of synthetic human being, and his entire teaching is shaped by his own struggles against illness.Yet few Nietzsche scholars have paid this crucial therapeutic element of his thought sufficient attention. This collection of essays by leading scholars in the field is composed around the Nietzschean insight, which (...) has its roots in the Hippocratic tradition of ancient medicine, that beliefs, behaviours, ideals and patterns of striving are not things for which individuals or even cultures are responsible. Rather, they are symptoms of what an individual or culture is, which symptoms require diagnostic interpretation and evaluation. The book identifies three principal approaches in Nietzsche's philosophy: diagnostic, prognostic and therapeutic. Each essay takes up this essential insight into Nietzsche's therapeutic philosophy from a different perspective and collectively they reveal an array of insightful approaches to self-induced enhancement, for both individuals and cultures. (shrink)

An original work of philosophy that highlights the connection between self-understanding and narrative form.

Consider the following three claims. (i) There are no truths of the form ‘p and ~p’. (ii) No one holds a belief of the form ‘p and ~p’. (iii) No one holds any pairs of beliefs of the form {p, ~p}. Irad Kimhi has recently argued, in effect, that each of these claims holds and holds with metaphysical necessity. Furthermore, he maintains that they are ultimately not distinct claims at all, but the same claim formulated in different ways. I find (...) his argument suggestive, if not entirely transparent. I do think there is at least an important kernel of truth even in (iii), and that (i) ultimately explains what’s right about the other two. Consciousness of an impossibility makes belief in the obtaining of the corresponding state of affairs an impossibility. Interestingly, an appreciation of this fact brings into view a novel conception of inference, according to which it consists in the consciousness of necessity. This essay outlines and defends this position. A central element of the defense is that it reveals how reasoners satisfy what Paul Boghossian calls the Taking Condition and do so without engendering regress. (shrink)

Kant’s revolutionary new approach to philosophy was accompanied by the introduction of a largely novel terminology. With the Kant-Lexikon, a lexical reference gives the modern reader access to his work on the basis of present-day editions and takes into account 20th century and contemporary research and advances in lexicology. The Kant-Lexikon includes 2395 entries authored by 221 scholars.

The foundation of historical materialism.--A study on authority.--Sartre's existentialism.--Karl Popper and the problem of historical laws.--Freedom and the historical imperative.

The paper offers an account of luck, fate, and fortune. It begins by showing that extant accounts of luck are deficient because they do not identify the genus of which luck is a species. That genus of properties, the tychic, alert an agent to occasions on which the external world cooperates with or frustrates their goal-achievement. An agent’s sphere of competence is the set of goals that it is possible for them to reliably achieve. Luck concerns occasions on which there (...) is a mismatch between attempt and result; in bad luck the external world thwarts goal-achievement within the agent’s sphere of competence, in good luck the external world assists goal-achievement beyond the agent’s sphere of competence. Fateful events are those where, more passively, the agent finds the external world achieving or frustrating their goals. Fortune concerns the contraction and expansion of the agent’s sphere of competence. Eight reasons are given for accepting the account; its theoretical virtues and various things it explains. Lastly, three objections are answered; that the tychic properties relate to well-being rather than agency, that there are alternative theories of fortune available in the contemporary literature, that the account draws arbitrary distinctions between synonyms. (shrink)

Presenting the first step-by-step commentary on Husserl’s Ideas I, Marcus Brainard’s Belief and Its Neutralization provides an introduction not only to this central work, but also to the whole of transcendental phenomenology. Brainard offers a clear and lively account of each key element in Ideas I, along with a novel reading of Husserl, one which may well cause scholars to reconsider many long-standing views on his thought, especially on the role of belief, the effect and scope of the epoché, (...) and the significance of the universal neutrality modification. (shrink)

ABSTRACTResearch that dissociates different types of processes within a given task using a processing tree approach suggests that attitudes may be acquired through evaluative conditioning in the absence of explicit encoding of CS-US pairings in memory. This research distinguishes explicit memory for the CS-US pairings from CS-liking acquired without encoding of CS-US pairs in explicit memory. It has been suggested that the latter effect may be due to an implicit misattribution process that is assumed to operate when US evocativeness is (...) low. In the present research, the latter assumption was supported neither by two high-powered experiments nor by complementary meta-analytic evidence, whereas evocativeness exerted an influence on explicit memory. This pattern of findings is inconsistent with the view that CS-liking acquired without encoding of CS-US pairs in explicit memory reflects an implicit misattribution process at learning. Hence, the underlying learning process is awaiting further empirical scrutiny. (shrink)

-- Douglas Kellner, University of Texas, Austin.

We argue that many intuitions do not have conscious propositional contents. In particular, many of the intuitions had in response to philosophical thought experiments, like Gettier cases, do not have such contents. They are more like hunches, urgings, murky feelings, and twinges. Our view thus goes against the received view of intuitions in philosophy, which we call Mainstream Propositionalism. Our positive view is that many thought-experimental intuitions are conscious, spontaneous, non-theoretical, non-propositional psychological states that often motivate belief revision, but they (...) require interpretation, in light of background beliefs, before a subject can form a propositional judgment as a consequence of them. We call our view Interpretationalism. We argue (i) that Interpretationalism avoids the problems that beset Mainstream Propositionalism and (ii) that our view meshes well with empirical results in contemporary cognitive science. (shrink)

This paper investigates the following question: when can one reliably infer the existence of an intersection point from a diagram presenting crossing curves or lines? Two cases are considered, one from Euclid's geometry and the other from basic real analysis. I argue for the acceptability of such an inference in the geometric case but against in the analytic case. Though this question is somewhat specific, the investigation is intended to contribute to the more general question of the extent and limits (...) of reliable diagrammatic reasoning in mathematics. (shrink)

Psychoanalysis and Wisdom applies psychoanalytic insights to one of the great examples of wisdom literature, the Ethics of the Fathers, an ethical tractate of the Talmud. Paul Marcus quotes key passages from the Ethics of the Fathers, providing a psychoanalytic commentary to enlarge and deepen our understanding of its contents and focusing primarily on what constitutes a flourishing life. Marcus then considers what psychoanalysis can provide in its engagement with this classic of the wisdom teachings, such as illuminating (...) aspects of the Ethics that are overlooked or underappreciated, and how "pearls of wisdom" from the Ethics can be incorporated into psychoanalytic theory and practice. The book contains clinical material as well as the insights of philosophers like Martin Buber, Gabriel Marcel, and Emmanuel Levinas. Psychoanalysis and Wisdom will appeal to readers interested in psychoanalysis and psychotherapy and to academics and students of psychoanalytic studies, religious studies, Judaic studies, and philosophy. (shrink)

Meditations, aphorisms, maxims, notes, and comments construct a philosophy of thought congruent with the inconsistency of our reality. Those who continue to think never return to their point of departure. —Inconsistencies These 130 short texts—aphoristic, interlacing, and sometimes perplexing—target a perennial philosophical problem: Our consciousness and our experience of reality are inconsistent, fragmentary, and unstable; God is dead, and our identity as subjects discordant. How can we establish a new mode of thought that does not cling to new gods or (...) the false security of rationality? Marcus Steinweg, as he did in his earlier book The Terror of Evidence, constructs a philosophical position from fragments, maxims, meditations, and notes, formulating a philosophy of thought that expresses and enacts the inconsistency of our reality. Steinweg considers, among other topics, life as a game (“To think is to play because no thought is firmly grounded”); sexuality (“wasteful, contradictory, and contingent”); desire (”Desire has a thousand names; It's earned none of them”); reality (“overdetermined and excessively complex”); and world (“a nonconcept”). He disposes of philosophy in one sentence (“Philosophy is a continual process of its own redefinition.”) but spends multiple pages on “A Tear in Immanence,” invoking Nietzsche, Heidegger, Sartre, and others. He describes “Wandering with Foucault” (“Thought entails wandering as well as straying into madness”) and brings together Derrida and Debord. He poses a question: “Why should a cat be more mysterious than a dog?” and later answers one: “Beauty is truth because truth is beauty.” By the end, we have accompanied Steinweg on converging trains of thought. “Thinking means continuing to think,” he writes, adding “But thinking can only pose questions by answering others.” The question of inconsistency? Asked and answered, and asked. (shrink)

Im Anschluss an die Edith Stein-Gesamtausgabe (ESGA) erschliesst das Edith Stein-Lexikon das denkerische Erbe, die philosophiegeschichtliche wie phanomenologische Bedeutung Edith Steins (1891-1942) weiter und macht es im problemgeschichtlichen und systematischen Sinn sichtbar. Die von uber 40 Stein-Forschern aus verschiedenen Landern und Generationen verfassten uber 250 Artikel informieren uber Bedeutung und Genese der fur Edith Stein zentralen Begriffe und Termini. Das Lexikon wendet sich an alle am Denken Edith Steins Interessierte, an Dozierende, Studierende und an alle neugierigen Leser, die ermutigt und (...) angeregt werden, sich den Originaltexten Edith Steins zum ersten Mal zuzuwenden. (shrink)

Quick, accessible, compact guide to understanding key political concepts. Contents include: Liberty, Justice, Equality, Human rights, Social contract, Democracy, Monarchy, Anarchism, Capitalism, Socialism, Nationalism and Globalisation.

This book is concerned with helping you improve your approach to decision-making. The author examines judgement in a selection of managerial contexts and provides important understanding that can help you make better leadership decisions. The book also pinpoints the in-house politics of organisational decision-making. Drawing on the very latest research, it introduces practical techniques that show you how to analyse and develop your own decision-making style. It will help you to deliver sharp and insightful analyses of your business and develop (...) effective solutions. In addition, it presents simple checklists that will give you vital insights throughout the decision-making process. Students and practitioners of leadership, management, and allied fields will find this book useful in order to understand and implement useful methods. (shrink)

Existential-Ontologie und historischer Materialismus bei Herbert Marcuse, von A. Schmidt.--Das Ganze und das ganz Andere; zur Kritik der reinen revolutionären Transzendenz, von W.F. Haug.--Technik und Eindimensionalität; eine Version der Technokratiethese? Von C. Offe.--Technologische Rationalität und spätkapitalistische ökonomie, von J. Bergmann.--Die geschichtliche Dimension des Realitätsprinzips, von H. Berndt und R. Reiche.--Marcuse and the New Left in America, by P. Breines.--Ausgewählte Bibliographie der Schriften Herbert Marcuses (p. 155-[161]).

This collection assembles significant, and in some cases unknown texts from the Herbert Marcuse archives in Frankfurt, including: ? critiques of positivism and ...

Introduction -- Creative experience as the birthplace of the transcendent -- On refinding God during chemotherapy -- Reflections on moments of grace -- On the quiet virtue of humility -- Summoned to courage -- Maintaining personal dignity in the face of the mass society -- On fidelity and betrayal in love relationships -- The kiss.

The Conference on Artificial General Intelligence is the only major conference series devoted wholly and specifically to the creation of AI systems possessing general intelligence at the human level and ultimately beyond. Its second installation, AGI-09, in Arlington, Virginia, March 6-9, 2009, attracted 67 paper submissions, which is a substantial increase from the previous year. Of these submissions, 33 (i.e., 49%) were accepted as full papers for presentation at the conference. Additional 13 papers were included as position papers. The program (...) also included a keynote address by Juergen Schmidhuber on 'The New AI', a post-conference workshop on 'The Future of AI', and a number of pre-conference tutorials on various topics related to AGI. (shrink)

In the following contribution I would like to present Edith Stein´s Philosophical Anthropology in somewhat more detail. I am going to pursue the issue of being human in Stein, to address fundamental issues and key concepts of her oeuvre, to refer to other approaches, to point out to Stein´s innovative contribution to Philosophical Anthropology under the horizon of phenomenology and classical metaphysics. As a preliminary remark, I would first like to outline a few lines of Stein’s biography. It is of (...) course also possible to skip the first chapter and go straight to the philosophical considerations. (shrink)

This essay analyzes the use of military robots in terms of the jus in bello concepts of discrimination and proportionality. It argues that while robots may make mistakes, they do not suffer from most of the impairments that interfere with human judgment on the battlefield. Although robots are imperfect weapons, they can exercise as much restraint as human soldiers, if not more. Robots can be used in a way that is consistent with just war theory when they are programmed to (...) avoid using force against all but the most clearly hostile targets. However, the essay also cautions against using robots for counterinsurgency because they may alienate people in the contested area and lead to an escalation of hostilities. (shrink)

Name der Zeitschrift: Zeitschrift für Religionswissenschaft Jahrgang: 26 Heft: 1 Seiten: 202-205.

Visual thinking -- visual imagination or perception of diagrams and symbol arrays, and mental operations on them -- is omnipresent in mathematics. Is this visual thinking merely a psychological aid, facilitating grasp of what is gathered by other means? Or does it also have epistemological functions, as a means of discovery, understanding, and even proof? By examining the many kinds of visual representation in mathematics and the diverse ways in which they are used, Marcus Giaquinto argues that visual thinking (...) in mathematics is rarely just a superfluous aid; it usually has epistemological value, often as a means of discovery. Drawing from philosophical work on the nature of concepts and from empirical studies of visual perception, mental imagery, and numerical cognition, Giaquinto explores a major source of our grasp of mathematics, using examples from basic geometry, arithmetic, algebra, and real analysis. He shows how we can discern abstract general truths by means of specific images, how synthetic a priori knowledge is possible, and how visual means can help us grasp abstract structures. Visual Thinking in Mathematics reopens the investigation of earlier thinkers from Plato to Kant into the nature and epistemology of an individual's basic mathematical beliefs and abilities, in the new light shed by the maturing cognitive sciences. Clear and concise throughout, it will appeal to scholars and students of philosophy, mathematics, and psychology, as well as anyone with an interest in mathematical thinking. (shrink)