Crossmodal learning and prediction of autobiographical episodic experiences using a sparse distributed memory

This work develops a connectionist memory model for a service robot that satisfies a number of desiderata: associativity, vagueness, approximation, robustness, distribution and parallelism. A biologically inspired and mathematically sound theory of a highly distributed and sparse memory serves as the basis for this work. The so-called sparse distributed memory (SDM), developed by P. Kanerva, corresponds roughly to a random-access memory (RAM) of a conventional computer but permits the processing of considerably larger address spaces. Complex structures are represented as binary feature vectors. The model is able to produce expectations of world states and complement partial sensory patterns of an environment based on memorised experience. Caused by objects of the world, previously learnt experiences will activate pattern sequences in the memory and claim the system's attention. In this work, the sparse distributed memory concept is mainly considered a biologically inspired and content-addressable memory structure. It is used to implement an autobiographical long-term memory for a mobile service-robot to store and retrieve episodic sensor and actuator patterns. Within the scope of this work the sparse distributed memory concept is applied to several domains of mobile service robotics, and its feasibility for the respective areas of robotics is analysed. The studied areas range from pattern matching, mobile manipulation, navigation, telemanipulation to crossmodal integration. The robot utilises properties of sparse distributed memory to detect intended actions of human teleoperators and to predict the residual motion trajectory of initiated arm or robot motions. Several examples show the model's fast and online learning capability for precoded and interactively provided motion sequences of a 6 DoF robot arm. An appropriate encoding of sensor-based information into a binary feature space is discussed and alternative coding schemes are elucidated. A transfer of the developed system to robotic subfields such as vision-based navigation is discussed. The model's performance is compared across both of these domains, manipulation and navigation. A hierarchical extension enables the memory model to link low-level sensory percepts to higher-level semantic task descriptions. This link is used to perform a classification of demonstrated telemanipulation tasks based on the robot's experience in the past. Tests are presented where different sensory patterns are combined into an integrated percept of the world. Those crossmodal percepts are used to dissolve ambiguities that may arise from unimodal perception. In dieser Arbeit wird ein konnektionistisches Gedachtnismodell fur einen Service-Roboter realisiert, das eine Riege von Desiderata erfullen soll: Assoziativitat, Unscharfe, Approximitat, Robustheit, Verteiltheit und Parallelismus. Als Grundlage dient die von P. Kanerva entwickelte und biologisch inspirierte Theorie eines hochgradig verteilten und dunn besetzten Speichers, engl. Sparse Distributed Memory (SDM). Es entspricht generell einem Speicher ahnlich dem Random-Access Memory (RAM) eines Computers wobei ein weitaus groserer Adressraum abgedeckt werden kann. Komplexe Strukturen werden als sehr lange Vektoren eines binaren Merkmalsraums auf das Gedachtnismodell abgebildet. Das Modell erzeugt Erwartungen und vervollstandigt partielle Wahrnehmungen der Umwelt mittels gespeicherter Sensordaten. Ausgelost durch Objekte der Umwelt werden zuvor gelernte Erfahrungen durch Folgen von Aktivierungsmustern im Fokus der Aufmerksamkeit des technischen Systems dargestellt. Primar wird in dieser Arbeit das Sparse Distributed Memory als eine dem menschlichen Vorbild ahnliche Gedachtnisstruktur zur autobiographischen Langzeitspeicherung von Erfahrungsmustern diskutiert. Diese Arbeit prasentiert die Ubertragung des Sparse Distributed Memory Konzepts auf verschiedenste Domanen der mobilen Service-Robotik und analysiert dessen Eignung fur die jeweiligen Bereiche. Diese Bereiche umfassen die mobile Manipulation, Navigation, Telemanipulation und die kreuzmodale Integration verschiedenartiger Sensormuster. Der Roboter nutzt die pradiktiven Eigenschaften des Modells um beispielsweise Intentionen von Teleoperatoren zu erkennen und initiierte Roboterarm-Bewegungsmuster sowie mobile Navigationsaufgaben autonom zu Ende zu fuhren. Verschiedenste Anwendungsszenarien zeigen die schnelle Lernfahigkeit von kodierten sowie interaktiven Manipulationssequenzen eines Roboterarms mit sechs Freiheitsgraden mittels einer vorwartsgerichteten, neuronalen Architektur, die das SDM darstellt. Dabei werden u.a. die Probleme der Informationsenkodierung von Sensordaten in einen binaren Merkmalsraum erortert und weitere Kodierungsmoglichkeiten untersucht. Die Ubertragung des Modells auf andere Modalitaten zur Losung von visuellen Navigationsaufgaben wird dargestellt und das Verhalten des Modells bezuglich der Manipulationsdomane verglichen. Durch eine hierarchische Erweiterung des Gedachtnismodells wird es ermoglicht, Sensorwahrnehmungen mit semantischen Konzepten hoheren Abstraktionsgrades zu verknupfen um beispielsweise Ziele einer interaktiven Telemanipulationsaufgabe fruhzeitig zu ermitteln. Es werden Untersuchungen prasentiert, die eine kreuzmodale Integration verschiedenartiger Sensormuster zu einem multimodalen Perzept der Umgebung darstellen, um Ambiguitaten unimodaler Wahrnehmungen zu kompensieren.

[1]  Chen K. Tham,et al.  Reinforcement learning of multiple tasks using a hierarchical CMAC architecture , 1995, Robotics Auton. Syst..

[2]  Marc Toussaint,et al.  Extracting Motion Primitives from Natural Handwriting Data , 2006, ICANN.

[3]  M. D’Esposito Working memory. , 2008, Handbook of clinical neurology.

[4]  H. McGurk,et al.  Hearing lips and seeing voices , 1976, Nature.

[5]  David Fowler A neural network as an instrument of prediction , 1991 .

[6]  J. Driver,et al.  Multisensory Interplay Reveals Crossmodal Influences on ‘Sensory-Specific’ Brain Regions, Neural Responses, and Judgments , 2008, Neuron.

[7]  G. Sjodin The Sparchunk code: a method to build higher-level structures in a sparsely encoded SDM , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[8]  Bernard J. Baars,et al.  A Cognitive Science Based Machine Learning Architecture , 2006, AAAI Spring Symposium: Between a Rock and a Hard Place: Cognitive Science Principles Meet AI-Hard Problems.

[9]  Alessandro Saffiotti,et al.  Fuzzy anchoring , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).

[10]  T. Hamalainen Sparse distributed memory implementations on tree shape parallel neurocomputer , 1996, Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop.

[11]  Douglas G. Danforth,et al.  An empirical investigation of sparse distributed memory using discrete speech recognition , 1990 .

[12]  G. Palm,et al.  On associative memory , 2004, Biological Cybernetics.

[13]  Josep Amat,et al.  Virtual Exoskeleton for Telemanipulation , 2000, ISER.

[14]  R. Shiffrin,et al.  Search of associative memory. , 1981 .

[15]  Rajesh P. N. Rao,et al.  Hierarchical Learning of Navigational Behaviors in an Autonomous Robot using a Predictive Sparse Distributed Memory , 1998, Machine Learning.

[16]  Norman Hendrich Mustererkennung mit neuronalen Assoziativspeichernetzen , 1996, DISKI.

[17]  Jianwei Zhang,et al.  Learning of demonstrated grasping skills by stereoscopic tracking of human head configuration , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[18]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[19]  Jan Kristoferson Some Comments on the Information Stored in Sparse Distributed Memory , 1995 .

[20]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.

[21]  Gunnar Sjodin Convergence and new operations in SDM , 2001 .

[22]  L. Squire,et al.  Preserved learning and retention of pattern-analyzing skill in amnesia: dissociation of knowing how and knowing that. , 1980, Science.

[23]  Aude Billard,et al.  Learning human arm movements by imitation: : Evaluation of a biologically inspired connectionist architecture , 2000, Robotics Auton. Syst..

[24]  Stevan Harnad,et al.  GROUNDING SYMBOLS IN THE ANALOG WORLD WITH NEURAL NETS A Hybrid Model , 1993 .

[25]  Jianwei Zhang,et al.  Sparse distributed memory for experience-based robot manipulation , 2009, 2008 IEEE International Conference on Robotics and Biomimetics.

[26]  Eric Horvitz,et al.  The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users , 1998, UAI.

[27]  P. Radford,et al.  Imitation , 2023 .

[28]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[29]  S.-S. Chen,et al.  Character recognition in a sparse distributed memory , 1991, IEEE Trans. Syst. Man Cybern..

[30]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[31]  L. Squire Memory systems of the brain: A brief history and current perspective , 2004, Neurobiology of Learning and Memory.

[32]  Shandong Wu Signature descriptions for motion trajectory representation, perception, recognition and reproduction , 2008 .

[33]  A. Paulo Coimbra,et al.  Robot navigation using a sparse distributed memory , 2008, 2008 IEEE International Conference on Robotics and Automation.

[34]  Salvatore Gaglio,et al.  Understanding dynamic scenes , 2000, Artif. Intell..

[35]  Liane Gabora,et al.  Cognitive mechanisms underlying the creative process , 2002, Creativity & Cognition.

[36]  Aluizio F. R. Araújo,et al.  Competitive and temporal Hebbian learning for production of robot trajectories , 1998, Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209).

[37]  Roland Karlsson Evaluation of a Fast Activation Mechanism for the Kanerva SDM Memory , 1995 .

[38]  Günther Görz,et al.  Kanerva's Sparse Distributed Memory: An Object-Oriented Implementation on the Connection Machine , 1995, IJCAI.

[39]  Maja J. Matarić,et al.  A framework for learning from demonstration, generalization and practice in human-robot domains , 2003 .

[40]  L. Squire,et al.  The structure and organization of memory. , 1993, Annual review of psychology.

[41]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[42]  C. Spence,et al.  Multisensory perception: Beyond modularity and convergence , 2000, Current Biology.

[43]  Jianwei Zhang,et al.  A flexible software architecture for multi-modal service robots , 2006, The Proceedings of the Multiconference on "Computational Engineering in Systems Applications".

[44]  David Chapman,et al.  What are plans for? , 1990, Robotics Auton. Syst..

[45]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[46]  Patrick Rößler,et al.  Telepräsente Bewegung und haptische Interaktion in ausgedehnten entfernten Umgebungen , 2009 .

[47]  Deborah J Serrien,et al.  Functional connectivity patterns during motor behaviour: The impact of past on present activity , 2009, Human brain mapping.

[48]  Jianwei Zhang,et al.  Robot navigation and manipulation based on a predictive associative memory , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[49]  Magnus Sahlgren,et al.  Computing with large random patterns , 2001 .

[50]  Jianwei Zhang,et al.  A smart interface-unit for the integration of pre-processed laser range measurements into robotic systems and sensor networks , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[51]  Maja J. Mataric,et al.  Performance-Derived Behavior Vocabularies: Data-Driven Acquisition of Skills from Motion , 2004, Int. J. Humanoid Robotics.

[52]  Stevan Harnad The Symbol Grounding Problem , 1999, ArXiv.

[53]  Eric R. ¬ Kandel,et al.  Neurowissenschaften : eine Einführung , 2011 .

[54]  Paul Ciprian Patic,et al.  THE BARRETTHAND GRASPER - PROGRAMMABLY FLEXIBLE PART HANDLING AND ASSEMBLY , 2006 .

[55]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[56]  Marius Usher,et al.  Chaotic Behavior of A Neural Network with Dynamical Thresholds , 1991, Int. J. Neural Syst..

[57]  Dana H. Ballard,et al.  Learning to perceive and act by trial and error , 1991, Machine Learning.

[58]  Vincent Hayward,et al.  Multi-RCCL User’s Guide , 2009 .

[59]  Peter Gärdenfors,et al.  Conceptual spaces - the geometry of thought , 2000 .

[60]  Sidney K. D'Mello,et al.  Encoding and Retrieval Efficiency of Episodic Data in a Modified Sparse Distributed Memory System , 2005 .

[61]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[62]  Dipankar Dasgupta,et al.  Using genetic algorithms for sparse distributed memory initialization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[63]  Kenji Doya,et al.  Multiple Forward Model Architecture for Sequence Processing , 2001, Sequence Learning.

[64]  Richard W. Prager Networks based on Kanerva's sparse distributed memory: results showing their strengths and limitations and a new algorithm to design the location matching layer , 1993, IEEE International Conference on Neural Networks.

[65]  Torsten Scherer,et al.  A mobile service robot for automisation of sample taking and sample management in a biotechnological pilot laboratory , 2004 .

[66]  Martin Weser,et al.  Hierarchical memory organization of multimodal robot skills for plan-based robot control , 2010 .

[67]  Danica Kragic,et al.  Motion intention recognition in robot assisted applications , 2008, Robotics Auton. Syst..

[68]  Mark T. Wallace,et al.  The development of multisensory processes , 2004, Cognitive Processing.

[69]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[70]  Klaus Landzettel,et al.  Robotics Component Verification on ISS ROKVISS - Preliminary Results for Telepresence , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[71]  Pentti Kanerva,et al.  Sparse distributed memory and related models , 1993 .

[72]  A. Baddeley Is working memory still working? , 2001, The American psychologist.

[73]  Alessandro Saffiotti,et al.  Using semantic knowledge in robotics , 2008, Robotics Auton. Syst..

[74]  A. Amedi,et al.  Functional imaging of human crossmodal identification and object recognition , 2005, Experimental Brain Research.

[75]  G. Bower,et al.  THE PSYCHOLOGY OF LEARNING AND M·OTIVATION , 2001 .

[76]  A.F.R. Araujo,et al.  Associative memory used for trajectory generation and inverse kinematics problem , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[77]  Gerhard Lakemeyer,et al.  Cognitive Robotics , 2008, Handbook of Knowledge Representation.

[78]  Mohamad H. Hassoun,et al.  Associative neural memories , 1993 .

[79]  T. Kellam,et al.  Artificial Minds , 1996, Inf. Process. Manag..

[80]  James S. Albus,et al.  Brains, behavior, and robotics , 1981 .

[81]  J. Tanji Sequential organization of multiple movements: involvement of cortical motor areas. , 2001, Annual review of neuroscience.

[82]  Jan Kristoferson Some results on activation and scaling of sparse distributed memory , 1998, Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209).

[83]  Joy Bose,et al.  Sparse Distributed Memory Using Rank-Order Neural Codes , 2007, IEEE Transactions on Neural Networks.

[84]  Charles C. Kemp,et al.  Challenges for robot manipulation in human environments [Grand Challenges of Robotics] , 2007, IEEE Robotics & Automation Magazine.

[85]  Philip A. Chou,et al.  The capacity of the Kanerva associative memory , 1989, IEEE Trans. Inf. Theory.

[86]  Richard S. Sutton,et al.  Dimensions of Reinforcement Learning , 1998 .

[87]  J. Albus A Theory of Cerebellar Function , 1971 .

[88]  Thomas B. Sheridan,et al.  Telerobotics, Automation, and Human Supervisory Control , 2003 .

[89]  D J Amit,et al.  The interaction space of neural networks with sign-constrained synapses , 1989 .

[90]  Dewen Hu,et al.  Accelerated reinforcement learning control using modified CMAC neural networks , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[91]  Becky Bunch Stream of Thought , 1968 .

[92]  Richard W. Prager,et al.  The modified Kanerva model for automatic speech recognition , 1989 .

[93]  E. Tulving,et al.  Episodic and semantic memory , 1972 .

[94]  A. Paulo Coimbra,et al.  Assessing a Sparse Distributed Memory Using Different Encoding Methods , 2009 .

[95]  Richard W. Prager,et al.  The modified Kanerva model: theory and results for real-time word recognition , 1991 .

[96]  F. Craik,et al.  Levels of Pro-cessing: A Framework for Memory Research , 1975 .

[97]  Richard L. Lewis,et al.  The mind and brain of short-term memory. , 2008, Annual review of psychology.

[98]  Bruno A Olshausen,et al.  Sparse coding of sensory inputs , 2004, Current Opinion in Neurobiology.

[99]  Samir Kouro,et al.  Unidimensional Modulation Technique for Cascaded Multilevel Converters , 2009, IEEE Transactions on Industrial Electronics.

[100]  Li Zhao,et al.  Is sparse and distributed the coding goal of simple cells? , 2004, Biological Cybernetics.

[101]  G. Lakoff,et al.  The Brain's concepts: the role of the Sensory-motor system in conceptual knowledge , 2005, Cognitive neuropsychology.

[102]  Independent Lacey,et al.  Cross-Modal Object Recognition Is Viewpoint- , 2007 .

[103]  Tsukasa Ogasawara,et al.  Indoor Navigation for a Humanoid Robot Using a View Sequence , 2009, Int. J. Robotics Res..

[104]  James S. Albus,et al.  A reference model architecture for intelligent systems design , 1993 .

[105]  Jianwei Zhang,et al.  Three-dimenisonal monocular scene reconstruction for service-robots - an application , 2007, VISAPP.

[106]  Jun Tani,et al.  On-line Imitative Interaction with a Humanoid Robot Using a Dynamic Neural Network Model of a Mirror System , 2004, Adapt. Behav..

[107]  Jianwei Zhang,et al.  EPIROME - A novel framework to investigate high-level episodic robot memory , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[108]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[109]  Jianwei Zhang,et al.  A two-arm situated artificial communicator for human-robot cooperative assembly , 2003, IEEE Trans. Ind. Electron..

[110]  A. Paulo Coimbra,et al.  AI and memory: Studies towards equipping a robot with a sparse distributed memory , 2007, 2007 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[111]  Vincent Hayward,et al.  Robot Manipulator Control under Unix RCCL: A Robot Control "C" Library , 1986 .

[112]  Doina Precup,et al.  Sparse Distributed Memories in Reinforcement Learning : Case Studies , 2004 .

[113]  John R. Anderson,et al.  The Adaptive Character of Thought , 1990 .

[114]  S. Eddy Hidden Markov models. , 1996, Current opinion in structural biology.

[115]  Masayuki Inaba,et al.  From visuo-motor self learning to early imitation-a neural architecture for humanoid learning , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[116]  Teuvo Kohonen,et al.  Content-addressable memories , 1980 .

[117]  Anthony Kulis,et al.  Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies , 2009, Scalable Comput. Pract. Exp..

[118]  Saulius Juozas Garalevicius Memory-Prediction Framework for Pattern Recognition: Performance and Suitability of the Bayesian Model of Visual Cortex , 2007, FLAIRS Conference.

[119]  Eamonn J. Keogh,et al.  Curse of Dimensionality , 2010, Encyclopedia of Machine Learning.

[120]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[121]  David Rogers,et al.  Kanerva's Sparse Distributed Memory: an Associative Memory Algorithm Well-Suited to the Connection Machine , 1989, Int. J. High Speed Comput..

[122]  D. Schacter Implicit memory: History and current status. , 1987 .

[123]  Stefan Schaal,et al.  Robot Programming by Demonstration , 2009, Springer Handbook of Robotics.

[124]  Geoffrey E. Hinton,et al.  Distributed representations and nested compositional structure , 1994 .

[125]  James L. McClelland,et al.  Parallel Distributed Processing: Explorations in the Microstructure of Cognition : Psychological and Biological Models , 1986 .

[126]  R. Atkinson,et al.  The control of short-term memory. , 1971, Scientific American.

[127]  Kuo-Chin Fan,et al.  A genetic sparse distributed memory approach to the application of handwritten character recognition , 1997, Pattern Recognit..

[128]  Jianwei Zhang,et al.  Towards an Episodic Memory for Cognitive Robots , 2008 .

[129]  Philip D. Wasserman,et al.  Advanced methods in neural computing , 1993, VNR computer library.

[130]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[131]  D. Marr A theory of cerebellar cortex , 1969, The Journal of physiology.

[132]  R.F. Reinhart,et al.  Recurrent Neural Associative Learning of Forward and Inverse Kinematics for Movement Generation of the Redundant PA-10 Robot , 2008, 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS).

[133]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[134]  Joaquin M. Fuster,et al.  Distributed Memory for Both Short and Long Term , 1998, Neurobiology of Learning and Memory.

[135]  Alessandro Saffiotti,et al.  Anchoring Symbols to Sensor Data: Preliminary Report , 2000, AAAI/IAAI.

[136]  Liane Gabora,et al.  A Day in the Life of a Meme. , 1996, Philosophica.

[137]  Monica N. Nicolescu,et al.  Understanding human intentions via Hidden Markov Models in autonomous mobile robots , 2008, 2008 3rd ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[138]  L. M. Blumenthal,et al.  Studies in geometry , 1972 .

[139]  J. Keeler Comparison Between Kanerva's SDM and Hopfield-Type Neural Networks , 1988, Cogn. Sci..

[140]  Richard F. Thompson Memory , 1992, Current Biology.

[141]  Pentti Kanerva,et al.  The Spatter Code for Encoding Concepts at Many Levels , 1994 .

[142]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[143]  S. Franklin,et al.  Running head : COGNITIVE ROBOTICS AND EXPERIMENTAL PSYCHOLOGY Computational Modeling / Cognitive Robotics Compliments Functional Modeling / Experimental Psychology , 2008 .

[144]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[145]  R. Lewontin ‘The Selfish Gene’ , 1977, Nature.

[146]  Teuvo Kohonen,et al.  Correlation Matrix Memories , 1972, IEEE Transactions on Computers.

[147]  Jianwei Zhang,et al.  Development of a smart laser range finder for an autonomous service robot , 2007, 2007 IEEE International Conference on Integration Technology.

[148]  Günther Palm,et al.  Wörterbuch der Kognitionswissenschaft , 1996 .

[149]  Doina Precup,et al.  Sparse Distributed Memories for On-Line Value-Based Reinforcement Learning , 2004, ECML.

[150]  Umesh Dwarkanath Joglekar,et al.  Learning to read aloud: A neural network approach using sparse distributed memory , 1989 .

[151]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[152]  P. Bertelson Chapter 14 Ventriloquism: A case of crossmodal perceptual grouping , 1999 .

[153]  Masayuki Inaba,et al.  View-based approach to robot navigation , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[154]  Jianwei Zhang,et al.  Natural Demonstration of Manipulation Skills for Multimodal Interactive Robots , 2007, HCI.

[155]  C. Lee Giles,et al.  Sequence learning: from recognition and prediction to sequential decision making , 2001, IEEE Intelligent Systems.

[156]  P. Suppes,et al.  REPRESENTATIONS AND MODELS IN PSYCHOLOGY , 1994 .

[157]  Uwe D. Hanebeck,et al.  Tractable probabilistic models for intention recognition based on expert knowledge , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[158]  Louis A. Jaeckel An alternative design for a sparse distributed memory , 1989 .

[159]  Jianwei Zhang,et al.  Multimodal People Tracking and Trajectory Prediction based on Learned Generalized Motion Patterns , 2006, 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.

[160]  Alessandro Saffiotti,et al.  An introduction to the anchoring problem , 2003, Robotics Auton. Syst..

[161]  L. Squire Mechanisms of memory. , 1986, Lancet.

[162]  Tim Baier-Löwenstein Lernen der Handhabung von Alltagsgegenständen im Kontext eines Service-Roboters , 2008 .

[163]  Joy Bose,et al.  A Spiking Neural Sparse Distributed Memory Implementation for Learning and Predicting Temporal Sequences , 2005, ICANN.

[164]  Gillian M. Hayes,et al.  A new approach to Kanerva's sparse distributed memory , 1997, IEEE Trans. Neural Networks.

[165]  M. Kahana Associative symmetry and memory theory , 2002, Memory & cognition.

[166]  Emilia I. Barakova,et al.  Spatial navigation based on novelty mediated autobiographical memory , 2005, IWINAC.

[167]  Frank E. Ritter,et al.  Techniques for modelling human performance in synthetic environments : A supplementary review , 1999 .

[168]  Tim A. Hely Sparse Distributed Memory , 2006 .

[169]  Alan S. Brown Why Hands Matter , 2008 .

[170]  Richard S. Sutton,et al.  Online Learning with Random Representations , 1993, ICML.

[171]  David Rogers,et al.  Predicting Weather Using a Genetic Memory: A Combination of Kanerva's Sparse Distributed Memory with Holland's Genetic Algorithms , 1989, NIPS.

[172]  Stan Franklin Perceptual Memory and Learning : Recognizing , Categorizing , and Relating , 2005 .

[173]  M. Garwicz,et al.  Anatomical and physiological foundations of cerebellar information processing , 2005, Nature Reviews Neuroscience.

[174]  H. C. LONGUET-HIGGINS,et al.  Non-Holographic Associative Memory , 1969, Nature.

[175]  Steve Temple,et al.  Sparse distributed memory using N-of-M codes , 2004, Neural Networks.

[176]  J. Hawkins,et al.  On Intelligence , 2004 .

[177]  Pentti O. A. Haikonen,et al.  The Role of Associative Processing in Cognitive Computing , 2009, Cognitive Computation.

[178]  Rajiv V. Dubey,et al.  Telemanipulation enhancement through user's motion intention recognition and fixture assistance , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[179]  Jianwei Zhang,et al.  Real-time 3D environment perception: An application for small humanoid robots , 2009, 2008 IEEE International Conference on Robotics and Biomimetics.

[180]  J. Knott The organization of behavior: A neuropsychological theory , 1951 .

[181]  Alexandre Bouchard-Côté School Sparse Distributed Memories in a Bounded Metric State Space : Some Theoretical and Empirical Results , 2004 .

[182]  Sompolinsky,et al.  Willshaw model: Associative memory with sparse coding and low firing rates. , 1990, Physical review. A, Atomic, molecular, and optical physics.