Limits...
Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics.

Burms J, Caluwaerts K, Dambre J - Front Neurorobot (2015)

Bottom Line: Our results demonstrate the universal applicability of reward-modulated Hebbian learning.Furthermore, they demonstrate the robustness of systems trained with the learning rule.This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

View Article: PubMed Central - PubMed

Affiliation: Computing Systems Laboratory (Reservoir Team), Electronics and Information Systems Department (ELIS), Ghent University , Ghent , Belgium.

ABSTRACT
In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

No MeSH data available.


Related in: MedlinePlus

Evaluation of a network trained for the 3-bit decoder task under the influence of input noise. The noise amplitude increased from left to right. The eight possible inputs are shown from top to bottom. The gray area indicates 1 SD around the observations for each of the different state trajectories (thick lines). The red crosses indicate the target observations at the end of the trial.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4538293&req=5

Figure 10: Evaluation of a network trained for the 3-bit decoder task under the influence of input noise. The noise amplitude increased from left to right. The eight possible inputs are shown from top to bottom. The gray area indicates 1 SD around the observations for each of the different state trajectories (thick lines). The red crosses indicate the target observations at the end of the trial.

Mentions: Although the network was trained without any noise on the input signals, the resulting behavior is robust against such noise. In Figure 10, we show the behavior of the network when input noise is present. This plot was generated by first applying k-means clustering on the trajectories and then estimating the variance of each centroid. Shown are the various centroids and the SD of each. We see that the network is robust against high amounts of noise on the input data (σ up to 0.5), as the original trajectories are maintained.


Reward-Modulated Hebbian Plasticity as Leverage for Partially Embodied Control in Compliant Robotics.

Burms J, Caluwaerts K, Dambre J - Front Neurorobot (2015)

Evaluation of a network trained for the 3-bit decoder task under the influence of input noise. The noise amplitude increased from left to right. The eight possible inputs are shown from top to bottom. The gray area indicates 1 SD around the observations for each of the different state trajectories (thick lines). The red crosses indicate the target observations at the end of the trial.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4538293&req=5

Figure 10: Evaluation of a network trained for the 3-bit decoder task under the influence of input noise. The noise amplitude increased from left to right. The eight possible inputs are shown from top to bottom. The gray area indicates 1 SD around the observations for each of the different state trajectories (thick lines). The red crosses indicate the target observations at the end of the trial.
Mentions: Although the network was trained without any noise on the input signals, the resulting behavior is robust against such noise. In Figure 10, we show the behavior of the network when input noise is present. This plot was generated by first applying k-means clustering on the trajectories and then estimating the variance of each centroid. Shown are the various centroids and the SD of each. We see that the network is robust against high amounts of noise on the input data (σ up to 0.5), as the original trajectories are maintained.

Bottom Line: Our results demonstrate the universal applicability of reward-modulated Hebbian learning.Furthermore, they demonstrate the robustness of systems trained with the learning rule.This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

View Article: PubMed Central - PubMed

Affiliation: Computing Systems Laboratory (Reservoir Team), Electronics and Information Systems Department (ELIS), Ghent University , Ghent , Belgium.

ABSTRACT
In embodied computation (or morphological computation), part of the complexity of motor control is offloaded to the body dynamics. We demonstrate that a simple Hebbian-like learning rule can be used to train systems with (partial) embodiment, and can be extended outside of the scope of traditional neural networks. To this end, we apply the learning rule to optimize the connection weights of recurrent neural networks with different topologies and for various tasks. We then apply this learning rule to a simulated compliant tensegrity robot by optimizing static feedback controllers that directly exploit the dynamics of the robot body. This leads to partially embodied controllers, i.e., hybrid controllers that naturally integrate the computations that are performed by the robot body into a neural network architecture. Our results demonstrate the universal applicability of reward-modulated Hebbian learning. Furthermore, they demonstrate the robustness of systems trained with the learning rule. This study strengthens our belief that compliant robots should or can be seen as computational units, instead of dumb hardware that needs a complex controller. This link between compliant robotics and neural networks is also the main reason for our search for simple universal learning rules for both neural networks and robotics.

No MeSH data available.


Related in: MedlinePlus