Machine Learning for Mathematical Software
Session at the 2018 International Congress on Mathematical Software
University of Notre Dame, South Bend, Indiana, USA. 26th July 2018.
The session Machine Learning for Mathematical Software took place at ICMS 2018 (ICMS Session Page).
There were 8 talks:

Erika Abraham  Heuristics in SMT Solving: To Learn or not to Learn?
Slides pdf

Yihe Dong  NLPbased Detection of Mathematical Subject Classification.
Slides Mathematica Notebook

Matthew England  Machine Learning for Mathematical Software.
Slides pdf

Stephen A. Forrest  Integration of Deep Learning in Maple.
Slides pdf

Jonathan Gryak  Solving Algorithmic Problems in Algebraic Structures via Machine Learning.
Slides pdf

Munehiro Kobayashi  Ordering of Subformulas for Efficient Quantifier Elimination over Real Closed Field.
Slides pdf

Thomas Sturm  Machine Learning for Reduce/Redlog? Some Ideas and Numbers for Discussion.
Slides pdf

Josef Urban  A Brief Overview of Machine Learning for Automated Reasoning.
Slides pdf
The session considered the use of Machine Learning in: multiple real QE procedures (England, Kobayashi, Sturm), computer algebra systems / graph theory (Forrest), SMT solvers (Abraham), mathematical knowledge management (Dong), group theory (Gryak) and theorem proving (Urban).
The session was organised by Matthew England, as a kick off to EPSRC Project EP/R019622/1, Embedding Machine Learning within Quantifier Elimination Procedures.