• Corpus ID: 17055857

Simulating Mirror Neurons

@inproceedings{Derosier2014SimulatingMN,
  title={Simulating Mirror Neurons},
  author={K. Derosier and Jackie Kay},
  year={2014}
}
Mirror neurons are motor cortical neurons found in primates and thought to be important for imitative learning. Multiple attempts have been made to model mirror neurons in a developmental robotics context. In this paper, we implement a system based on the article Towards a robotic model of the mirror neuron system by Rebrová, Pecháč and Farkaš [5]. Their system emphasizes biological plausibility by using a bidirectional learning algorithm to connect motor and visual modules in a manner inspired… 

Figures and Tables from this paper

References

SHOWING 1-8 OF 8 REFERENCES
Towards a robotic model of the mirror neuron system
TLDR
A multi-layer connectionist model of action understanding circuitry and mirror neurons, emphasizing the bidirectional activation flow between visual and motor areas is presented, inspired by a supervised, biologically plausible GeneRec algorithm.
The mirror-neuron system.
TLDR
A neurophysiological mechanism appears to play a fundamental role in both action understanding and imitation, and those properties specific to the human mirror-neuron system that might explain the human capacity to learn by imitation are stressed.
Single-Neuron Responses in Humans during Execution and Observation of Actions
Hierarchical attentive multiple models for execution and recognition of actions
Developmental Perception of the Self and Action
TLDR
A developmental framework for action-driven perception in anthropomorphic robots that develops the agent's perception of its own body and actions and embedded minimal knowledge into the robot's cognitive system in the form of motor synergies and actions to allow motor exploration.
Bidirectional Activation-based Neural Network Learning Algorithm
TLDR
A bidirectional activation-based learning algorithm (BAL), inspired by O'Reilly's supervised Generalized Recirculation (GeneRec) algorithm, that has been designed as a biologically plausible alternative to standard error backpropagation.
Biologically Plausible Error-Driven Learning Using Local Activation Differences: The Generalized Recirculation Algorithm
TLDR
All known fully general error-driven learning algorithms that use local activation-based variables in deterministic networks can be considered variations of the GeneRec algorithm (and indirectly, of the backpropagation algorithm).
Merge SOM for temporal data