Mohammad Modiri

Mohammad Modiri

The brain is a nonlinear and highly Recurrent Neural Network (RNN). This RNN is surprisingly plastic and supports our astonishing ability to learn and execute complex tasks. However, learning is incredibly complicated due to the brain's nonlinear nature and the obscurity of mechanisms for determining the contribution of each synapse to the output error. This issue is known as the Credit Assignment Problem (CAP) and is a fundamental challenge in neuroscience and Artificial Intelligence (AI). Nevertheless, in the current understanding of cognitive neuroscience, it is widely accepted that a feedback loop systems play an essential role in synaptic plasticity. With this as inspiration, we propose a computational model by combining Neural Networks (NN) and nonlinear optimal control theory. The proposed framework involves a new NN-based actor-critic method which is used to simulate the error feedback loop systems and projections on the NN's synaptic plasticity so as to ensure that the output error is minimized.

Mohammad Modiri

The brain can learn to execute a wide variety of tasks quickly and efficiently. Nevertheless, most of the mechanisms that enable us to learn are unclear or incredibly complicated. Recently, considerable efforts have been made in neuroscience and artificial intelligence to understand and model the structure and mechanisms behind the amazing learning capability of the brain. However, in the current understanding of cognitive neuroscience, it is widely accepted that synaptic plasticity plays an essential role in our amazing learning capability. This mechanism is also known as the Credit Assignment Problem (CAP) and is a fundamental challenge in neuroscience and Artificial Intelligence (AI). The observations of neuroscientists clearly confirm the role of two important mechanisms including the error feedback system and unsupervised learning in synaptic plasticity. With this inspiration, a new learning rule is proposed via the fusion of reinforcement learning (RL) and unsupervised learning (UL). In the proposed computational model, the nonlinear optimal control theory is used to resemble the error feedback loop systems and project the output error to neurons membrane potential (neurons state), and an unsupervised learning rule based on neurons membrane potential or neurons activity are utilized to simulate synaptic plasticity dynamics to ensure that the output error is minimized.