Reward-Dependent and Locally Modulated Hebbian Rule

In pattern classification tasks, the convolutional network has been widely used to detect the features and the error backpropagation with gradient descent (BPGD) algorithm has been used to train the network. However, the plasticity of the synapse between neurons often depends on the potential of the pre- and postsysnaptic membrane and the local concentration of neuromodulators such as dopamine. In this paper, we proposed the reward-dependent and locally modulated (RDLM) Hebbian rule to train a multi-layer network to perform the image classification tasks. We found that by introducing local modulation, the reward-dependent Hebbian rule can successfully train multi-layer networks. We have shown that the performance of our method on the MNIST and Fashion MNIST datasets can compete with the traditional BPGD algorithm. In conclusion, we proposed a biologically plausible learning rule that can compete with traditional BPGD in image classification tasks. The method can potentially be used to train the network with complex architecture for complex tasks.