[1]Ising,E.Beitrag zur Theorie des Ferromagnetismus. Z. Physik, 1925, 31: 253-258 .
[2] 黄海平, 统计物理、无序系统与神经网络, 科学，2022，74：40-44
[3] 黄海平，神经网络的统计力学(英文版)，高等教育出版社，2021.
[4] Brice Huang, Capacity threshold for the Ising perceptron, arXiv：2404.18902.
[5] H. Huang, K. M. Wong and Y. Kabashima, Entropy landscape of solutions in the binary perceptron problem, Journal of Physics A: Mathematical and Theoretical, 2013, 46(37):375002; H.Huang andY. Kabashima, Origin of the computational hardness for learning with binary synapses, Physical Review E, 2014, 90(5):052813.
[6] W. Perkins and C. Xu, Frozen 1-rsb structure of the symmetric ising perceptron, Random Structures & Algorithms, 2024, 64(4):856.
[7] E. Abbe, S. Li and A. Sly, Proof of the contiguity conjecture and lognormal limit for the symmetric perceptron, In 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS), pp. 327-338.
[8] C. Baldassi, A. Ingrosso, C. Lucibello, L. Saglietti and R. Zecchina, Subdominant dense clusters allow for simple learning and high computational performance in neural networks with discrete synapses, Physical review letters, 2015, 115(12):128101.
[9] E. Abbe, S. Li and A. Sly, Binary perceptron: efficient algorithms can find solutions in a rare well- connected cluster, In 2022 Proceedings of the 54th Annual ACM SIGACT Symposium on Theory of Computing, pp. 860-873.
[10] Tianqi Hou and Haiping Huang. Statistical physics of unsupervised learning with prior knowledge in neural networks. Phys. Rev. Lett., 2020, 124:248302
[11] Gabriel Raya and Lca Ambrogioni. Spontaneous symmetry breaking in generative diffusion models. In A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine, editors, Advances in Neural Information Processing Systems, volume 36, pages 66377-66389. Curran Associates, Inc., 2023; Z. Y and H. Huang, Nonequilbrium physics of generative diffusion models, arXiv: 2405.11932.
[12] Junbin Qiu and Haiping Huang. An optimization-based equilibrium measure describes non- equilibrium steady state dynamics: application to edge of chaos. arXiv:2401.10009.
[13] Daniel Toker, Ioannis Pappas, Janna D Lendner, Joel Frohlich, Diego M Mateos, Suresh Muthukumaraswamy, Robin Carhart-Harris, Michelle Paff, Paul M Vespa, Martin M Monti, et al. Consciousness is supported by near- critical slow cortical electrodynamics. Proceedings of the National Academy of Sciences, 2022, 119(7):e2024455119.
[14] Sebastien Bubeck, Varun Chandrasekaran, Ronen Eldan, John A. Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, YuanFang Li, Scott M. Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang. Sparks ofartificial general intelligence: Early experiments with gpt-4. arXiv:2303.12712.
[15] Yuhao Li, Ruoran Bai, and Haiping Huang, Spin glass model of in-context learning, arXiv: 2408.02288.
