The interactivist-constructivist (IC) approach offers an attractive framework for the development of intelligent robots. However, we still lack genuinely intelligent robots, capable of representing the world, in the IC sense. Here we argue that the reason for this situation is the lack of learning mechanisms that would allow the components of the robotic controller to learn constructively while they direct the robot’s action in accordance to its value system. We also suggest that spike-timing-dependent plasticity (STDP) may be such a learning mechanism that operates in the brain.
Pitti A., Alirezaei H. & Kuniyoshi Y. (2009) Cross-modal and scale-free action representations through enaction. Neural Networks 22(2): 144–154. https://cepa.info/7603
Embodied action representation and action understanding are the first steps to understand what it means to communicate. We present a biologically plausible mechanism to the representation and the recognition of actions in a neural network with spiking neurons based on the learning mechanism of spike-timing-dependent plasticity (STDP). We show how grasping is represented through the multimodal integration between the vision and tactile maps across multiple temporal scales. The network evolves into a small-world organization with scale-free dynamics promoting efficient inter-modal binding of the neural assemblies with accurate timing. Finally, it acquires the qualitative properties of the mirror neuron system to trigger an observed action performed by someone else.