Advanced Topics for self-study and Presentation

The presentations will be organized into two afternoon sessions: 1-5pm on Nov 25 (Friday) @HNE 037 and 1-5pm on Nov 30 (Wednesday) @LAS3033 .

Each person will make a 20-25 min presentation (including Q&A). To save time, you need to email your PPT to a session chair (to be named) before 10am that day (otherwise, your mark will be deducted).

Nov 25: all presentations NOT related to deep learning. Feng Wei fwei@cse.yorku.ca will coordinate the session. Email him your slides by 10am Nov 25. The presentation will take place from 1pm @HNE 037 in the following order:

1. Chao Wang
2. Yifan Li
3. Eunkyung Park
4. Leihan Chen
5. Feng Wei
6. Po Wu
7. Yangguang Li

Nov 30: all presentations related to deep learning. Chao Wang chwang@cse.yorku.ca will coordinate the session. Email him your slides by 10am Nov 30. The presentation will take place from 1pm @LAS3033 in the following order:

1. Matthew Tesfaldet
2. Mahdieh Abbaszadegan
3. Hemanth Pidaparthy
4. Jack Wu
5. Gong Cheng
6. Hao Li
7. Meng Jia

• Hemanth Pidaparthy: RNNs/LSTMs for Image Captioning
  1. Show and Tell: A Neural Image Caption Generator
  2. Visualizing and Understanding Recurrent Neural Networks
• Yifan Li: HMMs
  1. L. R. Rabiner and B. H. Juang, An Introduction to Hidden Markov Models
  2. L. R. Rabiner, A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition
• Matthew Tesfaldet: CNNs basics
  1. Hubel, D. H.; Wiesel, T. N. (1968-03-01). “Receptive fields and functional architecture of monkey striate cortex”
  2. LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey (2015). ”Deep learning”
  3. Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E. “ImageNet Classification with Deep Convolutional Neural Networks”
  4. LeCun, Yann; Léon Bottou; Yoshua Bengio; Patrick Haffner (1998). ”Gradient-based learning applied to document recognition”
• Leihan Chen: An overview of inference algorithm in undirected graphical model
  1. Tappen, M.F. and Freeman, W.T., 2003, October. Comparison of graph cuts with belief propagation for stereo, using identical MRF parameters. In Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on (pp. 900-906). IEEE.
  2. Kohli, P. and Torr, P.H., 2009. Robust higher order potentials for enforcing label consistency. International Journal of Computer Vision, 82(3), pp.302-324.
  3. Koltun, V., 2011. Efficient inference in fully connected crfs with gaussian edge potentials. Adv. Neural Inf. Process. Syst.
• Chao Wang: Budgeted SGD for multi-class SVMs
  1. Breaking the Curse of Kernelization: Budgeted Stochastic Gradient Descent for Large-Scale SVM Training
  2. Ensembles of Budgeted Kernel Support Vector Machines for Parallel Large Scale Learning
• Feng Wei: PageRank and Personalized PageRank
  1. Page, Lawrence, et al. “The PageRank citation ranking: bringing order to the web,” 1999.
  2. Alhelbawy, Ayman, and Robert J. Gaizauskas. “Graph Ranking for Collective Named Entity Disambiguation.” ACL. 2014.
  3. Pershina, Maria, Yifan He, and Ralph Grishman. “Personalized Page Rank for named entity disambiguation.” Proc. 2015 Annual Conference of the North American Chapter of the ACL, NAACL HLT. Vol. 14. 2015.
• Jack Wu: Language Understanding using RNNs and GRUs
  1. Rudolf Kadlec, Martin Schmid, Ondrej Bajgar & Jan Kleindienst, “Text Understanding with the Attention Sum Reader Network,” arXiv:1603.01547.
  2. Danqi Chen and Jason Bolton and Christopher D. Manning, “A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task,” arXiv:1606.02858.
• Hao Li: Reinforcement Learning: basics
  1. Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng, “End-to-End Reinforcement Learning of Dialogue Agents for Information Access,” arXiv:1609.00777.
  2. Jiwei Li, Will Monroe, Alan Ritter, Michel Galley, Jianfeng Gao, Dan Jurafsky, “Deep Reinforcement Learning for Dialogue Generation”, arXiv:1606.01541.
• Eunkyung Park: Latent Dirichlet Allocation and topic models
  1. David M. Blei, Andrew Y. Ng, Michael I. Jordan, “Latent Dirichlet Allocation”, Journal of Machine Learning Research 3 (2003) 993-1022.
  2. Matthew A. Taddy, “On Estimation and Selection for Topic Models,” Proceedings of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS) 2012.
• Meng Jia: Adversarial Networks
  1. Generative Adversarial Nets
  2. Conditional Generative Adversarial Nets
  3. Generating Videos with Scene Dynamics
  4. Generating images with recurrent adversarial networks
• Mahdieh Abbaszadegan: RNNs basics (BPTT/RTRL/EKF, etc..)
  1. A tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the "echo state network" approach
  2. A guide to recurrent neural networks and backpropagation
  3. Simple recurrent network trained by RTRL and Extended Kalman Filter Algorithm
• Po Wu: Metric Learning
  1. Distance Metric Learning: A Comprehensive Survey
  2. Large Scale Metric Learning from Equivalence Constraints
  3. Person Re-identification by Local Maximal Occurrence Representation and Metric Learning
• Gong Cheng: Sparse Auto-encoder
  1. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, A book chapter (Auto-Encoder) from Deep Learning, 14.1-14.3 pp 502-509.
  2. Andrew Ng, Sparse Auto-encoder
• Yangguang Li: ensemble learning
  1. Ensemble learning
  2. Ensemble Methods in Machine Learning
  3. Using coding-based ensemble learning to improve software defect prediction