Variational probability flow for biologically plausible training of deep neural networks

Zuozhu Liu, Tony Q.S. Quek, Shaowei Lin

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

The quest for biologically plausible deep learning is driven, not just by the desire to explain experimentally-observed properties of biological neural networks, but also by the hope of discovering more efficient methods for training artificial networks. In this paper, we propose a new algorithm named Variational Probably Flow (VPF), an extension of minimum probability flow for training binary Deep Boltzmann Machines (DBMs). We show that weight updates in VPF are local, depending only on the states and firing rates of the adjacent neurons. Unlike contrastive divergence, there is no need for Gibbs confabulations; and unlike backpropagation, alternating feedforward and feedback phases are not required. Moreover, the learning algorithm is effective for training DBMs with intra-layer connections between the hidden nodes. Experiments with MNIST and Fashion MNIST demonstrate that VPF learns reasonable features quickly, reconstructs corrupted images more accurately, and generates samples with a high estimated log-likelihood. Lastly, we note that, interestingly, if an asymmetric version of VPF exists, the weight updates directly explain experimental results in Spike-Timing-Dependent Plasticity (STDP).

原文English
主出版物標題32nd AAAI Conference on Artificial Intelligence, AAAI 2018
發行者AAAI Press
頁面3698-3705
頁數8
ISBN(電子)9781577358008
出版狀態Published - 2018
事件32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
持續時間: 2018 2月 22018 2月 7

出版系列

名字32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Conference

Conference32nd AAAI Conference on Artificial Intelligence, AAAI 2018
國家/地區United States
城市New Orleans
期間18-02-0218-02-07

All Science Journal Classification (ASJC) codes

  • 人工智慧

指紋

深入研究「Variational probability flow for biologically plausible training of deep neural networks」主題。共同形成了獨特的指紋。

引用此