黃海平(中山大學物理學院副教授)

黃海平(中山大學物理學院副教授)

黃海平,男,博士,中山大學物理學院副教授。

基本介紹

  • 中文名:黃海平
  • 畢業院校:中國科學院理論物理研究所
  • 學位/學歷:博士
  • 專業方向:神經計算的統計物理學
  • 任職院校:中山大學
人物經歷,學科方向,學術成果,承擔課題,代表論著,榮譽獲獎,主要兼職,

人物經歷

2018.03- 中山大學百人計畫副教授
2014.08-2018.03 日本理化學研究所研究科學家(Research Scientist)
2012.08-2014.08 日本學術振興會外國人特別研究員(JSPS postdoctoral fellow)
2011.08-2012.08 香港科技大學訪問學者(Visiting Scholar)
2006.09-2011.07 中國科學院理論物理研究所博士生
2002.09-2006.06 中山大學理工學院物理學專業本科生

學科方向

理論物理學科:神經計算的統計物理學,具體的研究方向-
a. 無序系統的統計物理: 複本理論, 空腔方法, 物理啟發的訊息傳遞算法,描述非線性動力學的動力學平均場理論;
b. 神經網路的理論和計算模型: 監督學習神經網路,受限玻爾茲曼機的平均場理論, 深度無監督學習, 循環神經網路的平均場理論及其神經科學原理; 生物神經網路的相變理論。

學術成果

承擔課題

(1) 中山大學百人計畫青年學術骨幹啟動經費(2018-2019)
(2) 國家青年科學基金項目:神經網路無監督學習的相關統計物理研究 (2019-2021)

代表論著

[1] H. Huang,Role of zero synapses in unsupervised feature learning,2018J. Phys. A: Math. Theor.5108LT01. Published as aLETTER.
[2]H. Huang, Statistical mechanics of unsupervised feature learning in arestricted Boltzmann machine with binary synapses, J. Stat. Mech. (2017) 053302. Recommended inQuora.
[3]H. Huang, Theory of population coupling and applications to describe high order correlations in large populations of interacting neurons, J. Stat. Mech. (2017)033501.
[4]H. Huang* and T. Toyoizumi, Clustering of neural codewords revealed by afirst-order phase transition, Phys. Rev. E 93, 062416 (2016). Selected as one of the most interesting and intriguing arXiv papers from the past week byMIT Technology Review.
[5]H. Huang* and T. Toyoizumi, Unsupervised feature learning from finite data by message passing: discontinuous versus continuous phase transition, Phys. Rev. E94, 062310 (2016).
[6]H. Huang, Effects of hidden nodes on network structure inference, J. Phys. A: Math. Theor. 48 355002 (2015).
[7]H. Huang* and T. Toyoizumi, Advanced mean field theory of the restricted Boltzmann machine, Phys. Rev. E 91, 050101(R) (2015). Published as aRapidCommunication.
[8]H. Huang* and Y. Kabashima, Origin of the computational hardness forlearning with binary synapses, Phys. Rev. E 90, 052813 (2014).Solved a long standing problem—why is a binary perceptron hard to learn
[9]H. Huang* and Y. Kabashima, Dynamics of asymmetric kinetic Ising systems revisited. J. Stat. Mech.: Theory Exp. P05020 (2014).
[10]H. Huang*, K. Y. Michael Wong and Y. Kabashima, Entropy landscape ofsolutions in the binary perceptron problem, J. Phys. A: Math. Theor. 46 375002 (2013). Selected in theResearch Highlightssection of J. Phys. A.
[11]H. Huang, Sparse Hopfield network reconstruction with L1 regularization. Eur. Phys. J. B 86, 484 (2013).
[12]H. Huang*, and Y. Kabashima, Adaptive Thouless-Anderson-Palmer approach to inverse Ising problems with quenched random fields. Phys. Rev. E 87, 062129 (2013).
[13]H. Huang* and H. Zhou, Counting solutions from finite samplings. Phys. Rev. E 85, 026118 (2012).
[14]H. Huang* and H. Zhou, Combined local search strategy for learning in networks of binary synapses. Europhysics Letters 96, 58003 (2011).

榮譽獲獎

2012年,日本學術振興會外國人特別研究員(JSPS 博士後)
2017年,日本理化學研究所傑出研究獎

主要兼職

Physical Review Letters, Physical Review X, Scientific Reports, Physical Review E, Journal of Statistical Mechanics: Theory and Experiment, Journal of Physics A: Mathematical and Theoretical, Neural Networks, Eur. J. Phys. B, Physica A, Neurocomputing, PloS Comput Bio, Network Neuroscience 等十餘種國際專業雜誌的審稿人。

相關詞條

熱門詞條

聯絡我們