LIDA (認知架構)
LIDA ( 学习型智能分配代理 ) 認知架構是一个整合的人工认知系统 ,试图对生物系统中「廣效的认知」進行建模,範圍涵蓋低等的知覺動作到高等的推理。 LIDA架构以认知科学和认知神经科学為經驗基礎,主要开发者為孟菲斯大学的斯坦·富蘭克林(Stan Franklin)與其同事。除了提供假設來指導進一步的研究之外,該架構也支援软件代理與机器人的控制结构。 LIDA概念模型为许多认知过程提供了合理的解释,同時也是思考心智如何運作的工具。
LIDA架構及其對應的概念模型有兩個假設:
- 人類的許多認知功能藉著「認知循環」,即在意識內容、各种記憶系統和動作選擇之間頻繁迭代(~ 10hz)的交互作用所實現。
- 這些認知循環就像認知的“原子”,構成了更高等的認知歷程。
綜述
LIDA既不是符號方法,也不是严格的联結主义,而是一种混合架構,采用了多种计算机制,而这些计算机制是根据其心理合理性而选择的。LIDA認知循環是由採用這些机制的模塊和歷程所組成。
LIDA的認知循環
LIDA认知循環可分为三个阶段:「理解阶段」、「注意(意识)阶段」以及「动作选择和学习阶段」。首先是從「理解阶段」開始,輸入的刺激會激活感觉记忆中的低级特征检测器,輸出則涉及到知覺聯想記憶,使得更加抽象的實體被輸入到其高級特征檢測器,如目標、類別、動作、事件等。由此產生的知覺會被移至工作空間,並在那里插入暫態的情節記憶和陳述性記憶以產生局部關聯,而這些局部關聯會與知覺相結合,生成當前的情境模型,這也就是代理對當前所發生事情的理解。「注意阶段」始于当前情境模型中最显着部分之結合,這樣的結合會去競爭一個當前意識內容中的「注意力」。接著,這些有意識的內容會被全域廣播,並進入「學習和動作選擇階段」。當有意識的廣播到達各种形式的記憶(知覺、情節和程序)時,新實體、新關聯以及對舊實體、關聯的強化就會出現。在進行這些學習以及使用意識內容的同時,合适的動作基模會從程序記憶中被實例化,并發送到動作選擇中,並在那里競相追求成為這個認知循環所選擇的行為。而所選定的行為會觸發感覺-運動記憶,以產生適合其執行的演算法,從而完成認知循環。
历史
Virtual Mattie(V-Mattie)是一个软件代理[19] ,可以从從研討會組織者那里收集資訊,并撰写下週研討會的公告,每週還會定期将其邮寄到持續更新的列表中,而无需人工监督。 [20] V-Mattie使用了多項前述的计算机制。
巴爾斯(Baars)的全局工作空间理论 (GWT)啟發了V-Mattie,使其演變成Conscious Mattie。Conscious Mattie有著一樣的领域和任务,在架构上納入了GWT的意识机制。 Conscious Mattie是第一个在功能上(尽管不是很明显)具有意识的软件代理。Conscious Mattie後來催生了IDA。
IDA(智能分配代理)由美国海军 [21][22][23]所開發,用于完成被稱為「人事调配军官」的人力資源任务。在每个水手的任务结束时,将會被分配到一个新的营舍。此分配过程称为分发。海軍僱傭了近300名全職的人事调配军官來執行這些新任務。 IDA的任务是透過對人事调配军官的角色的自动化来促进此过程。 IDA经过前人事调配军官的测试,并被海军接受。各种海軍机构為IDA項目提供了大約150万美元的資助。
LIDA(學習型IDA)架構最初是透過添加几种学习风格和模式[24][25][10]从IDA衍生而来的,但此后已发展成为一个更大、更通用的软件框架。 [26][27]
脚注
- Hofstadter, D. (1995). Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought. New York: Basic Books.
- Marshall, J. (2002). Metacat: A self-watching cognitive architecture for analogy-making (页面存档备份,存于). In W. D. Gray & C. D. Schunn (eds.), Proceedings of the 24th Annual Conference of the Cognitive Science Society, pp. 631-636. Mahwah, NJ: Lawrence Erlbaum Associates
- Kanerva, P. (1988). Sparse Distributed Memory (页面存档备份,存于). Cambridge MA: The MIT Press
- Rao, R. P. N., & Fuentes, O. (1998). Hierarchical Learning of Navigational Behaviors in an Autonomous Robot using a Predictive Sparse Distributed Memory (页面存档备份,存于). Machine Learning, 31, 87-113
- Drescher, G.L. (1991). Made-up minds: A Constructivist Approach to Artificial Intelligence
- Chaput, H. H., Kuipers, B., & Miikkulainen, R. (2003). Constructivist Learning: A Neural Implementation of the Schema Mechanism (页面存档备份,存于). Paper presented at the Proceedings of WSOM '03: Workshop for Self-Organizing Maps, Kitakyushu, Japan
- Maes, P. 1989. How to do the right thing. Connection Science 1:291-323
- Tyrrell, T. (1994). An Evaluation of Maes's Bottom-Up Mechanism for Behavior Selection (页面存档备份,存于). Adaptive Behavior, 2, 307-348
- Brooks, R.A. Intelligence without Representation. Artificial intelligence, 1991. Elsevier
- Franklin, S., & Patterson, F. G. J. (2006). The LIDA Architecture: Adding New Modes of Learning to an Intelligent, Autonomous, Software Agent (页面存档备份,存于) IDPT-2006 Proceedings (Integrated Design and Process Technology): Society for Design and Process Science
- Franklin, S., Ramamurthy, U., D'Mello, S., McCauley, L., Negatu, A., Silva R., & Datla, V. (2007). LIDA: A computational model of global workspace theory and developmental learning (页面存档备份,存于). In AAAI Fall Symposium on AI and Consciousness: Theoretical Foundations and Current Approaches. Arlington, VA: AAAI
- Baars, B. J. (1988). A cognitive theory of consciousness. Cambridge: Cambridge University Press
- Varela, F. J., Thompson, E., & Rosch, E. (1991). The Embodied Mind. Cambridge, Massachusetts: MIT Press
- Barsalou, L. W. 1999. Perceptual symbol systems. Behavioral and Brain Sciences 22:577–609. MA: The MIT Press
- Baddeley, A. D., & Hitch, G. J. (1974). Working memory. In G. A. Bower (Ed.), The Psychology of Learning and Motivation (pp. 47–89). New York: Academic Press
- Ericsson, K. A., and W. Kintsch. 1995. Long-term working memory. Psychological Review 102:21–245
- Glenberg, A. M. 1997. What memory is for. Behavioral and Brain Sciences 20:1–19
- Sloman, A. 1999. What Sort of Architecture is Required for a Human-like Agent? (页面存档备份,存于) In Foundations of Rational Agency, ed. M. Wooldridge, and A. Rao. Dordrecht, Netherlands: Kluwer Academic Publishers
- Franklin, S., & Graesser, A., 1997. Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents (页面存档备份,存于). Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, published as Intelligent Agents III, Springer-Verlag, 1997, 21-35
- Franklin, S., Graesser, A., Olde, B., Song, H., & Negatu, A. (1996, Nov). Virtual Mattie—an Intelligent Clerical Agent. Paper presented at the Symposium on Embodied Cognition and Action: AAAI, Cambridge, Massachusetts.
- Franklin, S., Kelemen, A., & McCauley, L. (1998). IDA: A Cognitive Agent Architecture IEEE Conf on Systems, Man and Cybernetics (pp. 2646–2651 ): IEEE Press
- Franklin, S. (2003). IDA: A Conscious Artifact? (页面存档备份,存于) Journal of Consciousness Studies, 10, 47–66
- Franklin, S., & McCauley, L. (2003). Interacting with IDA. In H. Hexmoor, C. Castelfranchi & R. Falcone (Eds.), Agent Autonomy (pp. 159–186 ). Dordrecht: Kluwer
- D'Mello, Sidney K., Ramamurthy, U., Negatu, A., & Franklin, S. (2006). A Procedural Learning Mechanism for Novel Skill Acquisition (页面存档备份,存于). In T. Kovacs & James A. R. Marshall (Eds.), Proceeding of Adaptation in Artificial and Biological Systems, AISB'06 (Vol. 1, pp. 184–185). Bristol, England: Society for the Study of Artificial Intelligence and the Simulation of Behaviour
- Franklin, S. (2005, March 21–23, 2005). Perceptual Memory and Learning: Recognizing, Categorizing, and Relating (页面存档备份,存于). Paper presented at the Symposium on Developmental Robotics: American Association for Artificial Intelligence (AAAI), Stanford University, Palo Alto CA, USA
- Franklin, S., & McCauley, L. (2004). Feelings and Emotions as Motivators and Learning Facilitators (页面存档备份,存于) Architectures for Modeling Emotion: Cross-Disciplinary Foundations, AAAI 2004 Spring Symposium Series (Vol. Technical Report SS-04-02 pp. 48–51). Stanford University, Palo Alto, California, USA: American Association for Artificial Intelligence
- Negatu, A., D'Mello, Sidney K., & Franklin, S. (2007). Cognitively Inspired Anticipation and Anticipatory Learning Mechanisms for Autonomous Agents (页面存档备份,存于). In M. V. Butz, O. Sigaud, G. Pezzulo & G. O. Baldassarre (Eds.), Proceedings of the Third Workshop on Anticipatory Behavior in Adaptive Learning Systems (ABiALS 2006) (pp. 108-127). Rome, Italy: Springer Verlag
外部链接
- LIDA architecture Cognitive Computing Research Group(页面存档备份,存于), Memphis University
- database of possible neural correlates(页面存档备份,存于) of LIDA modules and processes
- How Minds Work" tutorial(页面存档备份,存于)
- mention of LIDA in Bot shows signs of consciousness (页面存档备份,存于) by Celeste Biever, New Scientist 1 April 2011