An asymmetric ternary spiking neuron with a trainable negative threshold improves deep spiking Q-network scores on six of seven Atari games, but the theoretical explanation and the headline performance metric are not rigorous.
Spiking neural networks.J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Performance of Spike-based Deep Q-Learning using Ternary Neurons
An asymmetric ternary spiking neuron with a trainable negative threshold improves deep spiking Q-network scores on six of seven Atari games, but the theoretical explanation and the headline performance metric are not rigorous.