9:00-9:10 Opening remarks
9:10-9:50 Invited talk: Andrew Ng (Stanford University), Title: Deep Learning and Unsupervised Feature Learning [slides]
9:50-10:30 Invited talk: Xuedong Huang (Microsoft Research), Title: Intent, Knowledge, and Multisensory via Machine Learning

10:30–11:00 coffee break

11:00-11:40 Invited talk: John Platt (Microsoft Research), Title: Hints and Allegations: Learning Hard Classification Problems through applying Invariances
11:40-12:10 Poster session

12:10-1:30 lunch break

1:30-2:10 Invited talk: Pedro Domingos (U. Washington), Title: Sum-Product Networks: A New Deep Architecture [slides]
2:10-2:50 Invited talk: Fei-Fei Li (Stanford University), Title: Object Bank: A high-level image representation for complex scene understanding
2:50-3:30 Invited talk: Steven Greenberg (Silicon Speech), Title: Biological Foundations of Speech and Visual Information Processing by Humans and Machines

3:30-4:00 coffee break (and poster session)

4:00-5:30 Panel discussion


  • Deep Convex Networks for Image and Speech Classification, Li Deng and Dong Yu. [extended abstract]
  • Discriminative Learning of Feature Functions of Generative Type in Speech Translation, Xiaodong He and Li Deng. [extended abstract]
  • Large-Scale Online Incremental Feature Learning with Denoising Autoencoders, Guanyu Zhou and Honglak Lee.
  • LASSO Model Adaptation for Automatic Speech Recognition, Jinyu Li, Ming Yuan, and Chin-Hui Lee. [extended abstract]
  • Sparse, Distributed, and Convolutional Training of Image Features for Object Recognition, Kihyuk Sohn, Dae Yon Jung, Honglak Lee, and Alfred Hero III.
  • Towards High-Accuracy Low-Cost Noisy Robust Speech Recognition Exploiting Structured Model, Jinyu Li, Li Deng, Dong Yu, and Yifan Gong. [extended abstract]
  • Unsupervised learning of low-level audio features for music similarity estimation, Christian Osendorfer, Jan Schluter, Jurgen Schmidhuber, Patrick van der Smagt. [extended abstract]