“第十八章 深度学习前沿”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
第4行: 第4行:
 
*[[教学参考-18|教学参考]]
 
*[[教学参考-18|教学参考]]
 
*[http://aigraph.cslt.org/courses/18/course-18.pptx 课件]
 
*[http://aigraph.cslt.org/courses/18/course-18.pptx 课件]
*小清爱提问:什么是词向量[]
+
*小清爱提问:什么是词向量[http://aigraph.cslt.org/ai100/AI100-119-什么是词向量.pdf]
*小清爱提问:什么是序列到序列模型[]
+
*小清爱提问:什么是序列到序列模型[http://aigraph.cslt.org/ai100/AI100-120-什么是序列到序列模型.pdf]
*小清爱提问:什么是注意力机制[]
+
*小清爱提问:什么是注意力机制[http://aigraph.cslt.org/ai100/AI100-121-什么是注意力机制.pdf]
*小清爱提问:什么是自监督学习[]
+
*小清爱提问:什么是自监督学习[http://aigraph.cslt.org/ai100/AI100-122-什么是自监督学习.pdf]
*小清爱提问:什么是对抗生成网络[]
+
*小清爱提问:什么是对抗生成网络[http://aigraph.cslt.org/ai100/AI100-123-什么是对抗生成网络.pdf]
*小清爱提问:什么是变分自编码器[]
+
*小清爱提问:什么是变分自编码器[http://aigraph.cslt.org/ai100/AI100-124-什么是变分自编码器.pdf]
  
 
==扩展阅读==
 
==扩展阅读==
  
*AI100问:什么是残差网络[]
+
*AI100问:什么是残差网络[http://aigraph.cslt.org/ai100/AI-100-118-什么是残差网络.pdf]
*AI100问:什么是词向量[]
+
*AI100问:什么是词向量[http://aigraph.cslt.org/ai100/AI100-119-什么是词向量.pdf]
*AI100问:什么是序列到序列模型[]
+
*AI100问:什么是序列到序列模型[http://aigraph.cslt.org/ai100/AI100-120-什么是序列到序列模型.pdf]
*AI100问:什么是注意力机制[]
+
*AI100问:什么是注意力机制[http://aigraph.cslt.org/ai100/AI100-121-什么是注意力机制.pdf]
*AI100问:什么是自监督学习[]
+
*AI100问:什么是自监督学习[http://aigraph.cslt.org/ai100/AI100-122-什么是自监督学习.pdf]
*AI100问:什么是对抗生成网络[]
+
*AI100问:什么是对抗生成网络[http://aigraph.cslt.org/ai100/AI100-123-什么是对抗生成网络.pdf]
*AI100问:什么是变分自编码器[]
+
*AI100问:什么是变分自编码器[http://aigraph.cslt.org/ai100/AI100-124-什么是变分自编码器.pdf]
 +
 
  
 
==视频展示==
 
==视频展示==

2022年8月7日 (日) 11:32的版本


教学资料

  • 教学参考
  • 课件
  • 小清爱提问:什么是词向量[1]
  • 小清爱提问:什么是序列到序列模型[2]
  • 小清爱提问:什么是注意力机制[3]
  • 小清爱提问:什么是自监督学习[4]
  • 小清爱提问:什么是对抗生成网络[5]
  • 小清爱提问:什么是变分自编码器[6]

扩展阅读

  • AI100问:什么是残差网络[7]
  • AI100问:什么是词向量[8]
  • AI100问:什么是序列到序列模型[9]
  • AI100问:什么是注意力机制[10]
  • AI100问:什么是自监督学习[11]
  • AI100问:什么是对抗生成网络[12]
  • AI100问:什么是变分自编码器[13]


视频展示

演示链接

  • Word Embedding [14]
  • WebVectors: Word Embedding Online [15]


开发者资源


高级读者

  • He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.[18]
  • Bengio Y, Ducharme R, Vincent P. A neural probabilistic language model[J]. Advances in neural information processing systems, 2000, 13. [19]
  • Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[J]. arXiv preprint arXiv:1301.3781, 2013. [20]
  • Schroff F, Kalenichenko D, Philbin J. Facenet: A unified embedding for face recognition and clustering[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 815-823. [21]
  • Li C, Ma X, Jiang B, et al. Deep speaker: an end-to-end neural speaker embedding system[J]. arXiv preprint arXiv:1705.02304, 2017. [22]
  • Lin Y, Liu Z, Sun M, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Twenty-ninth AAAI conference on artificial intelligence. 2015. [23]
  • Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[J]. Advances in neural information processing systems, 2014, 27. [24]
  • Liu Y, Liu D, Lv J, et al. Generating Chinese poetry from images via concrete and abstract information[C]//2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020: 1-8. [25]
  • Sun D, Ren T, Li C, et al. Learning to write stylized chinese characters by reading a handful of examples[J]. arXiv preprint arXiv:1712.06424, 2017. [26]
  • Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:1409.0473, 2014. [27]
  • Xu K, Ba J, Kiros R, et al. Show, attend and tell: Neural image caption generation with visual attention[C]//International conference on machine learning. PMLR, 2015: 2048-2057. [28]
  • Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30. [29]
  • Liu X, Zhang F, Hou Z, et al. Self-supervised learning: Generative or contrastive[J]. IEEE Transactions on Knowledge and Data Engineering, 2021. [30]
  • Schneider S, Baevski A, Collobert R, et al. wav2vec: Unsupervised pre-training for speech recognition[J]. arXiv preprint arXiv:1904.05862, 2019. [31]
  • Noroozi M, Favaro P. Unsupervised learning of visual representations by solving jigsaw puzzles[C]//European conference on computer vision. Springer, Cham, 2016: 69-84. [32]
  • Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018. [33]
  • Brown T, Mann B, Ryder N, et al. Language models are few-shot learners[J]. Advances in neural information processing systems, 2020, 33: 1877-1901. [34]
  • Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners[J]. OpenAI blog, 2019, 1(8): 9.[]
  • Ethayarajh K. How contextual are contextualized word representations? comparing the geometry of BERT, ELMo, and GPT-2 embeddings[J]. arXiv preprint arXiv:1909.00512, 2019. [35]
  • Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[J]. Advances in neural information processing systems, 2014, 27. [36]
  • Kingma D P, Welling M. Auto-encoding variational bayes[J]. arXiv preprint arXiv:1312.6114, 2013. [37]
  • 王东,机器学习导论,第三章,神经模型,2021,清华大学出版社 [38]
  • Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning [39]