Sparse Restricted Boltzmann Machines as a Model of the Mirror Neuron System
I will defend a two-fold hypothesis. First (1), Restricted Boltzmann Machines (RBM) can successfully emulate the human Mirror Neuron System (MNS), by using association. This supports the association hypothesis, which states that Mirror Neurons are a by-product of associating perception with motor codes. Second (2), Sparse Coding is an necessity for Mirror Neurons to emerge from association learning. Methods: I simulated a dataset with three actions and two goals. Each stimuli has five features; three to indicate the actions, two to indicate the goal. I trained Sparse RBMs of various sparsities and sizes to model the MNS. Conclusion 1: RBMs prove to be successful in emulating various aspects of MNS behavior. This includes action execution, observation, imitation, goal inference, dealing with missing values (i.e. in the dark) and handling multiple modalities (i.e. integrate vision and proprioception). The performance, strength and certainty of responses of the model in different circumstances is similar to data from experiments. Conclusion 2: The Mirror Units that emerge are only dependent on the Sparse Coding. They are robust to network size, although size tends to diminish strength of the response. The units are capable of representing one or more causes (i.e. a single action, goal, or both). The optimal sparsity turns out to be , where is the number of distinctions the Unit needs to make. While Mirror Units emerge, association learning was insufficient to create two distinct populations , as found in the brain. This might be solved with the addition of classification learning. Keywords: Restricted Boltzmann Machines, Mirror Neuron System, Sparse Coding, Associative Memory.
Faculteit der Sociale Wetenschappen