12/28/2023 0 Comments Racket ball![]() In biological networks, all learning mechanisms may complement one another, accelerating the learning capabilities of animals. Our model shows that learning mechanisms involving different neural circuits produce similar performance in sensory-motor tasks. We used our models to dissect the circuit architectures and learning rules most effective for learning. Here we demonstrate that our biologically-plausible learning rules were effective in training spiking neuronal network models to solve problems in dynamic environments. Model-generated actions updated the environment and triggered reward or punishment signals that adjusted synaptic weights so that the models could learn which actions led to reward. Two populations of motor neurons generated commands to move the racket up or down. Motor populations received inputs from visual and association areas representing the dorsal pathway. Neuronal association areas encoded spatial relationships between objects in the visual scene. Neurons in the early visual area relayed information encoding object location and motion direction across the network. Our models included visual areas encoding game inputs and relaying the information to motor areas, which used this information to learn to move the racket to hit the ball. We also developed a new biologically-inspired learning rule that significantly enhanced performance, while reducing training time. We systematically investigated how different architectures and circuit-motifs (feed-forward, recurrent, feedback) contributed to learning and performance. Here we developed visual/motor spiking neuronal network models and trained them to play a virtual racket-ball game using several reinforcement learning algorithms inspired by the dopaminergic reward system. The models using these learning rules are often treated as black boxes, with little analysis on circuit architectures and learning mechanisms supporting optimal performance. ![]() Most of these models have not been tested in dynamic visual environments where models must make predictions on future states and adjust their behavior accordingly. Recent models of spiking neuronal networks have been trained to perform behaviors in static environments using a variety of learning rules, with varying degrees of biological realism.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |