In Journals:

• Feature Selection vs Theory Reformulation: a Study of Genetic Refinement of Knowledge-based Neural Networks
  Burns, B. and Danyluk A.
  Machine Learning, 38:1/2, pp. 89-108, 2000.

• Problem Definition, Data Cleaning, and Evaluation: A Classifier Learning Case Study
  Provost, F. and Danyluk A.
  Informatica, 23, pp. 123-136, 1999.

In Refereed Proceedings:

• Why Structural Recursion Should Be Taught before Arrays in CS1
  Bruce, K., Danyluk, A., and Murtagh, T.
  Proceedings of the ACM SIGCSE Symposium, 2005.

• Event-driven Programming is Simple Enough for CS1
  Bruce, K., Danyluk, A., and Murtagh, T.
  The Sixth Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE), pp. 1-4, 2001.

• A library to support a graphics-based object-first approach to CS1
  Bruce, K., Danyluk, A., and Murtagh, T.
  Proceedings of the ACM SIGCSE Symposium, pp. 6-10, 2001.

• Small Disjuncts in Action: Learning to Diagnose Errors in the Local Loop of the Telephone Network
  Proceedings of the Tenth International Conference on Machine Learning, Morgan Kaufmann, pp. 81-88, 1993.
  * without figures

In Refereed Workshops:

• Off-Topic Detection in Conversational Telephone Speech
  Stewart, R., Danyluk, A., and Liu, Y.
  Proceedings of the Workshop on Analyzing Conversations in Text and Speech at HLT-NAACL, 2006.

• Event-Driven Programming Facilitates Learning Standard Programming Concepts
  OOPSLA '04 Educators Symposium, 2004.

• Using Robotics to Motivate Learning in an AI Course Aimed at Non-Majors
  AAAI 2004 Spring Symposium on Accessible Hands-on Artificial Itelligence and Robotics Education, 2004.

• Theory refinement through knowledge-based feature set selection
  Burns, B. and Danyluk A.
  Proceedings of the Fourth International Workshop on Multistrategy Learning, Esposito, Michalski, & Saitta (eds), pp. 53-63, 1998.

Technical Reports:

• Predicting the Future: AI Approaches to Time-Series Problems, Papers from the 1998 Workshop
  AAAI Press Technical Report WS-98-07.
  Predicting the Future: AI Approaches to Time-Series Problems: a Workshop Report
  Danyluk A., Fawcett, T., and Provost, F.
  AI Magazine, 20:1, p. 124.

• Learning from Bad Data
  Provost, F. and Danyluk, A.
  in Working Notes for Applying Machine Learning in Practice: A Workshop at the Twelfth International Machine Learning Conference, (Technical Report AIC-95-023) Washington, DC: Naval Research Laboratory, Navy Center for Applied Research in Artificial Intelligence, Aha, D. and Riddle P. (eds), pp. 27-33, 1995.

Talks:

• Machine Learning meets the Real World: Successes and new research directions
  Danyluk A.
  Invited Technical Presentation at GHC 2002, The Grace Hopper Celebration of Women in Computing, October 2002.

• Artificial Intelligence
  Danyluk A.
  Future Problem Solvers, Williamstown Elementary School, February 2004.