7:00 – 6:30 ASRC

• Get mileage from Porsche!
• Start conference spreadsheet – locations, deadlines, domain, etc
  • CHIIR
  • IUI
  • Journalism Conference
  • Simulation Conference
• Meeting with Don at 4:30
  • Meta Particles -> meta organism = flock
  • Homotopy type theory
  • Christelle Viauroux
• Continuing review of Novelty Learning via Collaborative Proximity Filtering
  • A Painless Q-Learning Tutorial
  • The problem with the paper is that the authors do not consider that they are really identifying two different populations of users rather than the behavior changes in a single population. I think that if the paper addressed this possibility, it could contribute much more.
• Visualizing Data using t-SNE
• Simultaneous Discovery of Common and Discriminative Topics via Joint Nonnegative Matrix Factorization
• An Interactive Visual Testbed System for Dimension Reduction and Clustering of Large-scale High-dimensional Data

• Orthogonality and orthography: introducing measured distance into semanticspace

• Utopian: User-driven topic modeling based on interactive nonnegative matrix factorization

• From frequency to meaning: Vector space models of semantics

• Taste Over Time: The Temporal Dynamics of User Preferences.

• GA Tech – Jigsaw

6:30 – 3:00 ASRC

• Notes from Aaron to discuss today:

  • http://karpathy.github.io/2015/05/21/rnn-effectiveness/?branch_used=true Great article on RNN. Sample code available too.

  • Slider based decisions for clustering topic models where we weight similarity contributions individually, including entities (who the document is about via NLP extraction), BOW comparison, TF-IDF LS comparison, etc. The clusters change based off the combined contribution of each vector of attractors.
• Starting review of Novelty Learning via Collaborative Proximity Filtering
  • Gotta read this!!!  Taste Over Time – the Temporal Dynamics of User Preferences
  • and Mixtape – Direction-based Navigation in Large Media Collections
  • MAchine Learning for LanguagE Toolkit (MALLET)
• LingPipe is tool kit for processing text using computational linguistics. LingPipe is used to do tasks like:
  • Find the names of people, organizations or locations in news
  • Automatically classify Twitter search results into categories
  • Suggest correct spellings of queries
• GATE is open source software capable of solving almost any text processing problem
• Semantic Vectors creates semantic WordSpace models from free natural language text. Such models are designed to represent words and documents in terms of underlying concepts. They can be used for many semantic (concept-aware) matching tasks such as automatic thesaurus generation, knowledge representation, and concept matching.
• LSA-based essay grading – could be good for document classification/spam detection

6:45 – 3:00 ASRC

• Nervous enough about the election to move 1/3 of my retirement into long term treasuries.
• Writing up review of Topic-Relevance Map – Visualization for Improving Search Result Comprehension for IUI 2017. Done!
• Got similarity distance working on retrieved documents using a config file

7:00 – 3:00 ASRC

• Continuing to review Topic-Relevance Map – Visualization for Improving Search Result Comprehension for IUI 2017. I think parts of this are effectively plagiarized. Need to talk to someone about this
• How Google Shapes the News You See About the Candidates
• The Linear Algebra Behind Search Engines Online tutorial from 2005, which means there’s a chance I can follow. Loo
• Matrices, Vector Spaces, and Information Retrieval. Good examples. Looks readable. More on this later.
• Jaegul Choo
  • Weakly supervised nonnegative matrix factorization for user-driven clustering
  • L-EnsNMF: Boosted Local Topic Discovery via Ensemble of Nonnegative Matrix Factorization
  • Simultaneous discovery of common and discriminative topics via joint nonnegative matrix factorization
  • DemographicVis: Analyzing demographic information based on user generated content
  • Nonnegative matrix factorization for interactive topic modeling and document clustering
  • And so on. Need to spend some time looking at this.
• A human-machine collaborative system for identifying rumors on twitter

7:00 – 4:00 ASRC

• Reviewing Topic-Relevance Map – Visualization for Improving Search Result Comprehension for IUI 2017
• This looks important: Directing exploratory search: reinforcement learning from user interactions with keywords
• More (work) proposal writing. Done with first draft.

7:00 – 5:00 ASRC

• Playing around with using dissertation to search from. Interesting and different results for non–and-equalized docs and single counts.
  • baseline: information model behavior agent result pattern search system between
  • equalized docs: information search behavior design system result source document provide
  • single counts: information result provide system between search process example behavior
  • equalized + single: information result provide between search system process approach design
• Finishing survey and sending out – done!
• Tested the new CSE
• Back to Vector space models of semantics
• Worked on proposal with Aaron.