"...Here, for the first time, we show that (Reinforcement Learning) RL can be used efficiently to train a spiking neural network (SNN) to perform object recognition in natural images without using an external classifier. We used a feedforward convolutional SNN and a temporal coding scheme where the most strongly activated neurons fire first, while less activated ones fire later, or not at all. In the highest layers, each neuron was assigned to an object category, and it was assumed that the stimulus category was the category of the first neuron to fire. ..."
Model Type: Realistic Network
Cell Type(s): Abstract integrate-and-fire neuron
Model Concept(s): Reward-modulated STDP; STDP; Winner-take-all; Reinforcement Learning; Temporal Coding; Vision
Simulation Environment: C#
Implementer(s): Mozafari, Milad [milad.mozafari at ut.ac.ir]
References:
Mozafari M, Kheradpisheh SR, Masquelier T, Nowzari-Dalini A, Ganjtabesh M. (2018). First-Spike-Based Visual Categorization Using Reward-Modulated STDP IEEE Transactions on Neural Networks and Learning Systems.