Block Seminar Machine Learning for Natural Language Processing (Summer 2019)

Lecturer:  Dietrich Klakow

Location:  to be announced

Time: block course in the fall break 2019

Application for participation: 

Please register here until May 1st.

Unordered List of Topics:

  1. Generating multiple objects at spatially distinct locations ( link to paper )
  2. h-detach: Modifying the LSTM Gradient Towards Better Optimization ( link to paper )
  3. Compositional attention networks for machine reasoning ( link to paper
  4. The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision ( link to paper
  5. Raven: A dataset for relational and analogical visual reasoning ( link to paper )
  6. Adaptive Input Representations for Neural Language Modeling ( link to paper )
  7. Understanding Grounded Language Learning Agents (link to paper )
  8. Mining for meaning: from vision to language through multiple network consensus (link to paper )
  9. On the Spectral Bias of Neural Networks (link to paper )
  10. Machine Learning Topological Invariants with Neural Networks (link to paper )
  11. Unsupervised discovery of demixed, low-dimensional neural dynamics across multiple timescales through tensor components analysis (link to paper )
  12. Stronger generalization bounds for deep nets via a compression approach (link to paper )
  13. Linear algebraic structure of word senses, with applications to polysemy ( link to paper )
  14. Gated orthogonal recurrent units: On learning to forget ( link to paper )
  15. A man field view of the landscape of a two-layer neural network (link to paper )
  16. Entropy and mutual information in models of deep neural networks (link to paper )
  17. … more to come …. (link to paper )