机构:
Shahid Beheshti Univ, Fac Math Sci, Dept Comp & Data Sci, Tehran 1983969411, IranShahid Beheshti Univ, Fac Math Sci, Dept Comp & Data Sci, Tehran 1983969411, Iran
Kheradpisheh, Saeed Reza
[1
]
Mirsadeghi, Maryam
论文数: 0引用数: 0
h-index: 0
机构:
Amirkabir Univ Technol, Dept Elect Engn, Tehran 158754413, IranShahid Beheshti Univ, Fac Math Sci, Dept Comp & Data Sci, Tehran 1983969411, Iran
Mirsadeghi, Maryam
[2
]
Masquelier, Timothee
论文数: 0引用数: 0
h-index: 0
机构:
Univ Toulouse 3, Ctr Natl Rech Sci, CerCo UMR 5549, F-31062 Toulouse, FranceShahid Beheshti Univ, Fac Math Sci, Dept Comp & Data Sci, Tehran 1983969411, Iran
Masquelier, Timothee
[3
]
机构:
[1] Shahid Beheshti Univ, Fac Math Sci, Dept Comp & Data Sci, Tehran 1983969411, Iran
[2] Amirkabir Univ Technol, Dept Elect Engn, Tehran 158754413, Iran
[3] Univ Toulouse 3, Ctr Natl Rech Sci, CerCo UMR 5549, F-31062 Toulouse, France
We propose a new learning algorithm to train spiking neural networks (SNN) using conventional artificial neural networks (ANN) as proxy. We couple two SNN and ANN networks, respectively, made of integrate-and-fire (IF) and ReLU neurons with the same network architectures and shared synaptic weights. The forward passes of the two networks are totally independent. By assuming IF neuron with rate-coding as an approximation of ReLU, we backpropagate the error of the SNN in the proxy ANN to update the shared weights, simply by replacing the ANN final output with that of the SNN. We applied the proposed proxy learning to deep convolutional SNNs and evaluated it on two benchmarked datasets of Fashion-MNIST and Cifar10 with 94.56% and 93.11% classification accuracy, respectively. The proposed networks could outperform other deep SNNs trained with tandem learning, surrogate gradient learning, or converted from deep ANNs. Converted SNNs require long simulation times to reach reasonable accuracies while our proxy learning leads to efficient SNNs with much smaller simulation times. The source codes of the proposed method are publicly available at https://github.com/SRKH/ProxyLearning.
引用
收藏
页码:70769 / 70778
页数:10
相关论文
共 52 条
[51]
Zhou S., 2019, Temporal-coded deep spiking neural network with easy training and robust performance