On the Interactions Between Top-Down Anticipation and Bottom-Up Regression

This paper discusses the importance of anticipation and regression in modeling cognitive behavior. The meanings of these cognitive functions are explained by describing our proposed neural network model which has been implemented on a set of cognitive robotics experiments. The reviews of these experiments suggest that the essences of embodied cognition may reside in the phenomena of the break-down between the top-down anticipation and the bottom-up regression and in its recovery process.

• Publication year

  2007

• Venue

  Frontiers in Neurorobotics

• Publication date

  2007-10-08

• Fields of study

  Medicine, Computer Science, Psychology

• Identifiers
  DOI 10.3389/neuro.12.002.2007PMID 18958273PMCID 2533585
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Internal simulation of perception: a minimal neuro-robotic model

  2005cited by this paper
• Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication

  2004cited by this paper
• On-line Imitative Interaction with a Humanoid Robot Using a Dynamic Neural Network Model of a Mirror System

  2004cited by this paper
• Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB

  2004cited by this paper
• The Dynamical Systems Accounts for Phenomenology of Immanent Time: An Interpretation by Revisiting a Robotics Synthetic Study

  2004cited by this paper
• A hierarchical neural-network model for control and learning of voluntary movement

  2004cited by this paper
• Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

  2003cited by this paper
• Intelligence with representation

  2003cited by this paper
• Self-organization of behavioral primitives as multiple attractor dynamics: a robot experiment

  2002cited by this paper
• Imitation as a dual-route process featuring prediction and learning components: A biologically plaus

  2002cited by this paper
• Cambrian Intelligence: The Early History of the New AI

  1999cited by this paper
• Multiple paired forward and inverse models for motor control

  1998cited by this paper
• Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems

  1998cited by this paper
• Hierarchical Reinforcement Learning of Low-Dimensional Subgoals and High-Dimensional Trajectories

  1998cited by this paper
• An Interpretation of the "Self" From the Dynamical Systems Perspective: A Constructivist Approach

  1998cited by this paper
• Model-based learning for mobile robot navigation from the dynamical systems perspective

  1996cited by this paper
• A dynamical systems perspective on agent-environment interaction

  1996cited by this paper
• A Menu of Designs for Reinforcement Learning Over Time

  1995cited by this paper
• Feudal Reinforcement Learning

  1992cited by this paper
• Intelligence without Representation

  1991cited by this paper
• The Induction of Dynamical Recognizers

  1991cited by this paper
• The Symbol Grounding Problem

  1990cited by this paper
• Finding Structure in Time

  1990cited by this paper
• Attractor dynamics and parallelism in a connectionist sequential machine

  1990cited by this paper
• Memorizing oscillatory patterns in the analog neuron network

  1989cited by this paper
• Learning internal representations by error propagation

  1986influential reference
• Perceptual Structures and Distributed Motor Control

  1981cited by this paper

• Neural representations unobserved—or: a dilemma for the cognitive neuroscience revolution

  2023cites this paper
• Predictive processing and anti-representationalism

  2021cites this paper
• The brain and its time: intrinsic neural timescales are key for input processing

  2021cites this paper
• The brain and its time: intrinsic neural timescales are key for input processing

  2021cites this paper
• The role of robotics and AI in technologically mediated human evolution: a constructive proposal

  2019cites this paper
• Neurorobotics—A Thriving Community and a Promising Pathway Toward Intelligent Cognitive Robots

  2018cites this paper
• Anticipation of digital patterns

  2017cites this paper
• A Neural Architecture for Performing Actual and Mentally Simulated Movements During Self-Intended and Observed Bimanual Arm Reaching Movements

  2015cites this paper
• Embodied Prediction

  2015cites this paper
• Self-Organization and Compositionality in Cognitive Brains : A Neuro-Robotics Study

  2014cites this paper
• Self-Organization and Compositionality in Cognitive Brains: A Neurorobotics Study

  2014cites this paper
• A hexapod walker using a heterarchical architecture for action selection

  2013cites this paper
• The many faces of precision (Replies to commentaries on “Whatever next? Neural prediction, situated agents, and the future of cognitive science”)

  2013influential citation
• Selective exploration exploiting skills in hierarchical reinforcement learning framework

  2013cites this paper
• Walknet, a bio-inspired controller for hexapod walking

  2013cites this paper
• Razvoj i primjena konceptualne metafore u jeziku suvremene znanosti: konceptualizacija prostora, vremena i stanja

  2012cites this paper
• From hardware and software to kernels and envelopes: a concept shift for robotics, developmental psychology, and brain sciences

  2011cites this paper
• Supervised learning of internal models for autonomous goal-oriented robot navigation using Reservoir Computing

  2010cites this paper
• Contrôle moteur par le cervelet et interface Cerveau-Machine pour commander un doigt robotique

  2010cites this paper
• Epigenetic Robotics Architecture (ERA)

  2010cites this paper
• Stable kernels and fluid body envelopes

  2009cites this paper
• Recognizing Sequences of Sequences

  2009cites this paper
• Integration of Gravitational Torques in Cerebellar Pathways Allows for the Dynamic Inverse Computation of Vertical Pointing Movements of a Robot Arm

  2009cites this paper
• Direct Control of an Active Tactile Sensor Using Echo State Networks

  2009cites this paper
• How and Why the Brain Lays the Foundations for a Conscious Self

  2008cites this paper
• Why and How to Avoid Representation

  2008cites this paper
• Cars, Compositionality, and Consciousness

  2008cites this paper
• Open Peer Commentaries

  2008cites this paper
• The Mind Is Not In the Brain

  year unknowncites this paper
• Paladyn Journal of Behavioral Robotics a Formalism for Learning from Demonstration *

  year unknowncites this paper