Artificial intelligence(simulating the human mind)


Published on

  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Artificial intelligence(simulating the human mind)

  1. 1. Cognitive Science Artificial Intelligence: Simulating the Human Mind to Achieve Goals Samantha Luber University of Michigan Ann Arbor, U.S.A. E-mail: saluber@umich.eduAbstract: This paper provides a general overview of the ranging from creating and observing artificial neurons tointerdisciplinary study of cognitive science, specifically the area representing the mind as a high-level collection of rules,of the field involving artificial intelligence. In addition, the symbols, and plans [3].paper will elaborate on current research for cognitive scienceartificial intelligence, highlight the importance of this research B. Cognitive Science in Artificial Intelligenceby providing specific examples of its applications in present In addition to simulating intelligence to model andsociety, and briefly discuss future research opportunities forthe overlapping fields of cognitive science and artificial study the human mind, artificial intelligence involves theintelligence. study of cognitive phenomena in machines and attempts to implement aspects of human intelligence in computerKeywords: Artificial intelligence, cognitive science programs. These programs can be used to address a variety of complex problems with the goal of doing so more I. AN OVERVIEW OF COGNITIVE SCIENCE efficiently than a human. New theories in the cognitive ARTIFICIAL INTELLIGENCE science field often influence improved artificial intelligence agents that better simulate the human thought process [2]. Since ancient times, people have conducted Achievements in cognitive science help improve artificialcountless experiments in attempts to better understand the simulation of the human mind. In turn, more accuratehuman mind. These tests eventually lead to the development artificial intelligence provides better models of the humanof psychology. In the late 1930’s, cognitive science emerged mind for cognitive science researchers to use. Although theas an extension of psychology topics; it is concerned with goals of cognitive science and artificial intelligence differ,how information is stored and transferred in the human mind. collaboration between the two fields is essential for theirIt is an interdisciplinary science, linking psychology, success. Cognitive science artificial intelligence refers to thelinguistics, anthropology, philosophy, neuroscience, interdisciplinary study that overlaps these areas in attempt tosociology, and learning sciences [1]. A useful tool for achieve both cognitive science and artificial intelligencecognitive researchers, artificial intelligence is the branch of science concerned with creating simulations thatmodel human cognition. In addition to serving as a research II. CURRENT RESEARCH IN COGNITIVE SCIENCEtool, artificial intelligence also contains a scientific aspect, ARTIFICIAL INTELLIGENCEfocusing on studying cognitive behavior of machines [2]. A fundamental goal of cognitive science artificialDeveloped to encapsulate the concept of both early cognitive intelligence is to use the power of computers to understandscience and intelligence simulated by machines, modern and supplement human thinking. In artificial intelligence, ancognitive science artificial intelligence focuses on how intelligent agent refers to a computer-simulated entity thathumans, animals, and machines store information associated interacts with its environment and works to achieve goals,with perception, language, reasoning, and emotion. both simple and complex [3]. By observing which problems an intelligent agent can solve and how the computer programA. Artificial Intelligence in Cognitive Science solves these problems, researchers in the cognitive science The central principle of cognitive science is that a field aim to develop theories about how the brain learns andcomplete understanding of the mind cannot be obtained constructs logical rules, how intelligence arises within thewithout analyzing the mind on multiple levels. In other brain, insights on which pieces of information humans willwords, numerous techniques must be used to fully evaluate forget and remember, and the kinds of resources the humanand understand a process of the mind. Artificial intelligence mind uses [2].is a powerful approach that allows researchers in cognitive In addition to gaining a better insight into the naturescience to study behavior through computational modeling of the human mind, the ultimate goal of cognitive scienceof the human mind [2]. There are numerous approaches to artificial intelligence is to eventually develop human-level,simulating how the mind is structured with approaches machine intelligence. At this level, the intelligent agent___________________________________978-1-61284-840-2/11/$26.00 ©2011 IEEE
  2. 2. would not be distinguished from human intelligence, a from the intelligent agent’s environment in working memorychallenge known as the Turing test [3]. Because intelligent [6]. Because immediate sensory data is sometimesagents often face situations with incomplete information, insufficient for decision-making in the real world, storingencoding data for all possible situations is a limited approach previous situations is useful in differentiating betweento simulate human intelligence [4]. In other words, because situations that would otherwise appear identical to thethere are infinitely many situations that can arise in the real intelligent agent at a specific instance [7]. In short,world, it is impossible to design an intelligent agent pre- maintaining memory of past events “makes it possible to notprogrammed with solutions to all of the problems it may face. only make correct decisions but to learn the correctInstead, an intelligent agent must be equipped with the decision” [7]. When the intelligent agent enters an impasse,ability to make decisions based on the information it has and the agent can search its memory for a solution to there-evaluate its past solutions to improve future decisions. problem. If the problem is unique, the agent remembers itsConsequently, a more fundamental understanding about how actions in case the problem is encountered again [6]. Inthe human mind learns and solves problems is necessary to summary, the SOAR cognitive architecture system relies ondesign an intelligent agent with the same intelligence. maintaining information from decisions and outcomes inCurrently, numerous research projects are making progress past experiences to improve future decisions in simulatingin these goals of both simulating human intelligence to study human behavior. The SOAR system is a useful tool for usingthe human mind as well as the simulation of human simulated human intelligence to solve complex problems.intelligence to solve complex problems. C. Simulating CreativityA. Simulating Theory of Mind In his papers on the simulation of human level A central topic in cognitive science and psychology, intelligence in the decision process, Dr. Zadeh emphasizestheory of mind refers to “one’s ability to infer and the importance of imitating creativity in intelligent agents.understand the beliefs, desires, and intentions of others, Although knowledge of past experiences is a useful tool ingiven the knowledge one has available” [5]. To investigate decision-making, Dr. Zadeh acknowledges that “creativity isthe various theories that explain how theory of mind takes a gifted ability of human beings in thinking, inference,place on the cognitive level, Dr. Hiatt and Dr. Trafton use problem solving, and product development” [8]. In histhe ACT-R cognitive architecture to simulate how accurately formal definition of the unique ability, creativity is dividedchildren can predict the actions of others as they age, a prime into three categories: abstract, concrete, and artistic. Moreexample of using artificial intelligence to study the human relevant to engineering applications, concrete creativitymind. ACT-R consists of modules associated with different involves generating new, innovative solutions in anareas of the brain, buffers which each hold a symbolic item, environment limited by goals and available conditions [8].and a pattern matcher that determines actions to be taken Aiming to equip intelligent agents with the creative ability ofbased on the contents of the buffers. Furthermore, this core the human mind, Zadeh provides an outlined approach forcognitive architecture has the ability to interface with the implementing the creative process in a computer program.environment via visual, audio, motor, and aural modules and The ability of an intelligent agent to create new approacheslearn new facts and rules through reinforcement learning; to solving problems is vital for modeling human levelbased on these capabilities, ACT-R is a suitable system for intelligence.simulating the mind of a growing child [5]. Based on the D. Simulating Rationalityidea that children learn and mature as they grow, Dr. Hiattand Dr. Trafton include a maturation parameter associated The multi-agent recursive simulation technologywith the age of the simulated child. A higher level of for N-th order rational agents (MARS-NORA) is a procedurematurity corresponds to a more advanced ability in the child developed by Dr. Mussavi Rizi and Dr. Latek to rationallyto select between their inferred beliefs about the beliefs and choose a course of action for multiple artificial intelligenceactions of others [5]. From simulating the theory of mind agents in a dynamic environment. Similar to how a humandevelopment of numerous children, Dr. Hiatt and Dr. weighs the pros and cons of a decision, MARS-NORATrafton found evidence supporting the legitimacy of main requires agents to derive the probability distribution oftheories of how theory of mind is developed in existence utility gained for each possible course of action [9]. MARS-today. NORA has two algorithms for determining the optimal course of action once all possible algorithms are considered:B. The SOAR Project myopic planning and non-myopic planning. In myopic Dr. Laird, a professor in computer science at the planning, the zero-order agent chooses a random action.University of Michigan, developed the SOAR system, a Each proceeding agent chooses its optimal course of actioncognitive architecture programming structure with the goal based on the actions of agents of lower order, overallof simulating a human brain, as a unique, alternative resulting in the on-average optimal action of the multi-agentapproach to the traditional and restricted hard-coding data [9]. Because the actions of previous agents limit the actionsapproach. The SOAR system stores information retrieved of agents of higher order, myopic planning is not suitable for
  3. 3. situations in which the multi-agent acts asynchronously with intelligence agent’s behavior to achieve top-level goals in aother multi-agents. Myopic planning also fails if the multi- dynamic environment.agent wishes to derive multiple optimal courses of action or As seen in these current research projects, cognitivetakes inconsistent amounts of time to complete each action; science artificial intelligence can be used to supplementinstead, non-myopic planning can be used [9]. Because research in cognitive science and vice versa. Furthermore,asynchronous multi-agents’ actions influence each other, the these works contribute to achieving improved human-levelnon-myopic planning algorithm considers three situations. intelligence simulations in the cognitive science artificialFirst, in the event that a multi-agent has both a higher order intelligence field. Although no artificial intelligence hasof rationality and a longer planning horizon than the other come close to achieving the goal of human-level intelligence,multi-agent, the stronger agent selects its optimal course of intelligent agents are consistently being re-evaluated andaction while the latter agent accepts a short term loss and improved.returns to a synchronous state with the stronger agent [9].The second situation involves a multi-agent that has a higher III. APPLICATIONS AND THE IMPORTANCE OForder of rationality than its opposing multi-agent but a short COGNITIVE SCIENCE ARTIFICIAL INTELLIGENCEplanning horizon. In this situation, the multi-agent with the As seen in the goals of the previously mentionedshorter planning time is “locked” into their path of actions researchers in the field, there are numerous, important, realand will not make optimal decisions. The third situation world applications of cognitive science artificial intelligenceinvolves multi-agents with relatively equal orders of research. In our society, engineers and architects constantlyrationality and planning horizon length. In this case, the face tasks, such as constructing a highway or designing aagents have similar cognitive abilities and can cooperate to traffic light, that require optimizing a design despite physicaloptimize their actions [9]. With two algorithms for deriving and financial limitations. For instance, in the traffic lightan optimal choice of action for multi-agents, MARS-NORA example, an engineer must consider the tradeoff economicsallows agents to behave rationally by following the decision between using stronger materials and the price of theseprocess of humans during the action selection process. materials or calculate statistics on the large amounts ofE. Achieving Top-down Goals traffic data available for the intersection to determine light timing. With the ability to consider large amounts of The ICARUS Architecture is a cognitive information and design considerations in a short period ofarchitecture comparable to SOAR. The architecture supports time, advanced intelligence can be developed to solve thesetop-level goals by guiding the agent’s behavior to types of complex logic problems [2]. In this way, the use ofaccomplish its tasks while maintaining reactivity. However, artificial intelligence as a tool for engineers could make thebecause ICARUS does not support adding, deleting, or design process faster, more efficient, and more accurate.reordering top-level goals, the ability to manage multipletop-level goals in this cognitive architecture is somewhat In addition, the creation of a human level intelligentlimited, especially since the goals of a human are often agent provides a “better mirror” of the human mind that ischanged and prioritized [10]. Dr. Choi at Stanford University easier to study than the human brain for cognitive scienceaddresses this limitation in his extension of the ICARUS researchers. By studying realistic simulations of humanarchitecture. In his revision of the goal management system, cognition, theories can be drawn about humans’ nature andeach general goal now includes a goal description and cognitive limitations. Furthermore, researchers can achieverelevance conditions, used to prioritize goals based on the specific cognitive science goals, such as understanding howcurrent state of the agent [10]. The new system receives intelligence develops in the brain or how damage to differentinformation about its surroundings during each “cycle.” parts of the brain affect cognition [2]. Progress in these areasOnce information about the environment is retrieved, the can powerfully impact how the human mind is understood,goal management system can add, remove, or re-prioritize with the potential of leading to improvements in presentgoals based on the agent’s “belief state” through a goal society. For instance, a better understanding of how thenomination process. Top-level goals are prioritized based on human mind learns and retains information can lead toinitial priority and relevancy to the current state of the improved learning methods implemented in schools toenvironment [10]. Furthermore, when selecting actions to accelerate human progress. In the same way, improvedachieve goals, Dr. Choi’s extension retrieves the agent’s theories on how different areas of the brain affect behaviorskills relevant to the current goal and generates a plan to can help develop medical solutions for victims of brainaccomplish the goal, utilizing the non-primitive skills first trauma [3]. The useful applications of pursuing research in[10]. This goal management system design is more realistic cognitive science artificial intelligence continue to grow asto a human’s behavior as goals change as the surrounding research in the field continues.environment changes. Improved by modifying the IV. THE FUTURE OF COGNITIVE SCIENCEarchitecture to better resemble a human’s goal management ARTIFICIAL INTELLIGENCEprocess, Dr. Choi’s extension of the ICARUS cognitivearchitecture is an effective system for guiding an artificial
  4. 4. Although there have been many breakthroughs in addresses the goals of both cognitive science and artificialthe cognitive science artificial intelligence field, researchers intelligence. As research in the field continues, improvedare continually working to improve intelligent agents. The intelligent agents will be developed with the ability tohuman mind has the impressive capability of preforming simulate human-level intelligence in the final cognitivenumerous mental and physical tasks with little mental strain science research goal of fully understanding the human mind[2]. On the other hand, computer simulated intelligence is or to address important, complex problems of mankindlimited by the speed and capacity of hardware for through artificial intelligence.performing computations. The development of advancednanotechnology to increase hardware speed and memorywill reduce this restraint on simulating human level REFERENCESintelligence [11]. Furthermore, while theories of cognitive [1] Thagard, Paul. (2009). Cognitive Science. The Stanford Encyclopediascience artificial intelligence have fostered improved of Philosophy (Fall 2008 Edition), Edward N. Zalta (ed.).understanding of the human mind, advancements in the [2] Simon, H. (2010). Cognitive Science: Relationship of AI to Psychologypsychology and cognitive science fields, that help better and Neuroscience. AAAI.understand human behavior, can be used to further improve [3] Wang, Y. (2008). Proceedings of the Seventh IEEE Internationalintelligent agents [3]. Finally, an issue more acknowledged Conference on Cognitive Informatics: ICCI 2008: August 14-16, 2008, Stanford University, California, USA. [Piscataway, N.J.]: IEEEby the public than researchers in the field, include ethical Xplore.and organizational concerns with the coevolution of humans [4] Bickhard, M., and Terveen, L. (1995). Foundational Issues in Artificialand intelligent systems; these issues may one day have to be Intelligence and Cognitive Science. Elsevier Science Publishers.addressed [11]. For instance, society would have to address [5] Hiatt, L. M., and Trafton, J. G. (2010). A Cognitive Model of Theory ofrestrictions on how a human-simulating robot can behave. Mind. 10th International Conference on Cognitive Modeling: ICCM 2010: August 5-8, 2010, Philadelphia, PA, USA. Because intelligent agents are still far from [6] Lehman, J.F., Laird, J., and Rosenbloom, P. (2006). A Gentleachieving artificial intelligence goals, such as passing the Introduction to SOAR, an Architecture for Human Cognition: 2006Turing test, or cognitive science goals, such as achieving Update.human level intelligence or improving the present [7] Laird, J.E., and Wang, Y. (2007). The Importance of Action History in Decision Making and Reinforcement Learning. Proceedings of theunderstanding of the human mind, there are still many Eighth International Conference on Cognitive Modeling. Ann Arbor,opportunities for research achievements in the cognitive artificial intelligence field. This room for growth [8] Zadeh, L. (2008). On Cognitive Foundations of Creativity and theshows great potential for developing technology to increase Cognitive Process of Creation. Proceedings of the Seventh IEEE International Conference on Cognitive Informatics: ICCI 2008 :the progress of mankind. August 14-16, 2008, Stanford University, California, V. CONCLUSIONS USA. [Piscataway, N.J.]: IEEE Xplore. [9] Latek, M., and Mussavi Rizi, S.M. (2010). Plan, replan and plan to Artificial intelligence is an extremely useful tool for replan Algorithms for robust courses of action under strategiccognitive science research of both fundamental and high uncertainty. BRIMS 2010: March 21-24, 2010, Charleston, SC, USA.level understanding of the human mind by simulating the [10] Choi, D. (2010). Nomination and Prioritization of Goals in a Cognitivehuman mind. In the same way, cognitive science theories Architecture. 10th International Conferenceon Cognitive Modeling: ICCM 2010: August 5-8, 2010, Philadelphia, PA, USA.provide useful insight on human cognition that can be [11] Jacobstein, N. (2005). The Prospects for AI. IT Conversations.encoded into artificial intelligence. Cognitive science < tml>.artificial intelligence is a powerful research area that