First-Spike-Based Visual Categorization Using Reward-Modulated STDP

@article{Mozafari2018FirstSpikeBasedVC,
  title={First-Spike-Based Visual Categorization Using Reward-Modulated STDP},
  author={Milad Mozafari and Saeed Reza Kheradpisheh and Timoth{\'e}e Masquelier and Abbas Nowzari-Dalini and Mohammad Ganjtabesh},
  journal={IEEE Transactions on Neural Networks and Learning Systems},
  year={2018},
  volume={29},
  pages={6178-6190}
}
Reinforcement learning (RL) has recently regained popularity with major achievements such as beating the European game of Go champion. Here, for the first time, we show that 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… CONTINUE READING
Tweets
This paper has been referenced on Twitter 30 times. VIEW TWEETS

Citations

Publications citing this paper.
SHOWING 1-10 OF 10 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 85 REFERENCES

Similar Papers

Loading similar papers…