User Tools

Site Tools


publication:arxivwork

My latest work published in arXiv.org:

  1. Hui Jiang, “A Latent Space Theory for Emergent Abilities in Large Language Models,” arXiv:2304.09960.
  2. Behnam Asadi, Hui Jiang, “On Approximation Capabilities of ReLU Activation and Softmax Output Layer in Neural Networks,” arXiv:2002.04060.
  3. Y. Lin, K. Ahmadi, H. Jiang, “Bandlimiting Neural Networks Against Adversarial Attacks,” arXiv:1905.12797.
  4. H. Jiang, “Why Learning of Large-Scale Neural Networks Behaves Like Convex Optimization”, arXiv:1903.02140.
  5. H. Jiang, “A New Perspective on Machine Learning: How to do Perfect Supervised Learning”, arXiv:1901.02046.
  6. Q. Liu, H. Jiang, Z. Ling, X. Zhu, S. Wei, Y. Hu, “Combing Context and Commonsense Knowledge Through Neural Networks for Solving Winograd Schema Problems,” arXiv:1611.04146.
  7. D. Liu, W. Lin, S. Zhang, S. Wei, H. Jiang, “Neural Networks Models for Entity Discovery and Linking,” arXiv:1611.03558.
  8. R. Soltani, H. Jiang, “Higher Order Recurrent Neural Networks,” arXiv:1605.00064.
  9. Q. Liu, Z. Ling, H. Jiang, Y. Hu, “Part-of-Speech Relevance Weights for Learning Word Embeddings,arXiv:1603.07695.
  10. D. J. Im, C. D. Kim, H. Jiang, R. Memisevic, “Generating images with recurrent adversarial networks,”arXiv:1602.05110.
publication/arxivwork.txt · Last modified: 2023/04/24 17:19 by hj

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki