Skip to content

Latest commit

 

History

History
81 lines (67 loc) · 5.2 KB

aitasks.md

File metadata and controls

81 lines (67 loc) · 5.2 KB
Raw

AI@20 class projects task list：

Most important: Work hard and have fun!

Task1(AutoDriving)：

Task2(ReDoPaper):

Task3(arXivAPP)：

  • About：arXiv dataset and metadata of 1.7M+ scholarly papers across STEM
  • Dataset URL:https://www.kaggle.com/Cornell-University/arxiv
  • Task: Build AI applications upon arXiv dataset, including but not limited to Question/Answering,Knowledge Graph, Visualizaion, Recommendation, Survey systems.

Task4(SWI)：

Task5(AIBooks)：

  • 1: Prolog Programming for Artificial Intelligence (Ivan Bratko)
  • 2: The Art of Prolog, Second Edition (Leon Sterling)
  • 3: Artificial Intelligence Machine Learning and Deep Learning
  • 4: Algorithms for Optimization
  • 5: Analysis and Geometry on Graphs and Manifolds
  • 6: Graphs, Networks and Algorithms
  • 7: Genetic Programming Theory and Practice
  • 8: Industrial Machine Learning Using Artificial Intelligence as a Transformational Disruptor
  • 9: Optimization for Machine Learning
  • 10: Unsupervised Learning in Space and Time
  • URL:https://pan.baidu.com/s/1Qi6DfnXr-cxzKcT-dcRJvA (CODE:bb4j)
  • Task: Translate one of the books and extract source code files for the book examples. Formulas should be in source format and thus be reproducible.

Task6(miniWatson)：

  • About：Watson is a famous IBM NLP project of Question/Answering for open domains.
  • Reference URL:http://brenocon.com/watson_special_issue/
  • Task: Build a miniWatson for specific domains: Computer Science, Mathmatics, ..., or your perfered domain.

Task7(AIWriter):

  • Task: Build an AI Writer that can pass turing-test.
  • Task tips: Collect as many as possible computer science research papers, extract different paper sections (abstract, introduction, model, experiment, discussion, conclusion etc.) from papers. Construct a huge sentence bank from the extracted paper sections contents. Build n-gram models for sentences (instead of words). Build sentence similarity measures to help find simlar sentences. Given an input sentence and section tag (for example: 'abstract' or 'introduction'), generate the whole section with simlar following sentences. The generated sections (for example: 'abstract' or 'introduction') should pass turing-test.

Task8(ResearchGraph):

  • Task: Build knowledge graph from given research papers.
  • Task tips: Collect as many as possible computer science research papers, extract different paper sections (abstract, introduction, model, experiment, discussion, conclusion etc.) from papers. Identify important concepts entities and relations from the extracted paper sections contents. Build knowledge graphs with the entities and relations. Build a visualization system for the KG to give interactive demonstrations.

Task9(HumanEye):

  • Task: Generate text knowledge from visual contents (images or video).
  • Task tips: Collect as much as possible visual contents (images or videos). Build a generative model (human eye) from visual contents (images or videos). The gererator should pass turing-test.

Task10(Brainstorm):

  • Task: Generate thought paths from any concept pairs.
  • Task tips: Simulate human brain's functionalities. Given any concept pairs, generate a sequence of thoughts to connect the concept pairs. The thought path should be reasonable and should form a story that can pass turing-test.

Task11(NewsRec):

  • Task: Content-based news recommendation.
  • URL: https://github.com/microsoft/recommenders
  • Task tips: Reimplement canonical news recommendation algorithms. Build an improved model out of the existing models.

Any suggestions are welcome, current tasks may be updated and new tasks may be added in the future.