Skip to content

Professor Peter A FlachMSc(Twente), PhD(Tilburg)

Professor of Artificial Intelligence

Peter Flach

Professor Peter A FlachMSc(Twente), PhD(Tilburg)

Professor of Artificial Intelligence

Member of

Research interests

Data-intensive computing and analytics; 
Mining complex and highly structured data; 
Evaluation, calibration and reuse of machine learning models; 
Feature construction and subgroup discovery in data streams; 
Intelligent reasoning, artificial intelligence. 

View research connections

Postal address:
Merchant Venturers Building
Woodland Road
Clifton
Bristol
United Kingdom

Selected research outputs

  1. Published
  2. Published

    Beta calibration: a well-founded and easily implemented improvement on logistic calibration for binary classifiers

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. Published

    SPHERE: A sensor platform for healthcare in a residential environment

    Research output: Chapter in Book/Report/Conference proceedingChapter in a book

  4. Published

    BDL.NET: Bayesian dictionary learning in Infer.NET

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  5. Published
  6. Published
  7. Published
  8. Published

    ROC Analysis

    Research output: Chapter in Book/Report/Conference proceedingEntry for encyclopedia/dictionary

  9. Published

    Background check: a general technique to build more reliable and versatile classifiers

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  10. Published

    Fast unsupervised online drift detection using incremental Kolmogorov-Smirnov test

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  11. Published

    Classifier Calibration

    Research output: Chapter in Book/Report/Conference proceedingEntry for encyclopedia/dictionary

  12. Published

    Cost-sensitive boosting algorithms: Do we really need them?

    Research output: Contribution to journalArticle

  13. Published

    On the Need for Structure Modelling in Sequence Prediction

    Research output: Contribution to journalArticle

  14. Published

    The SPHERE Challenge: Activity Recognition with Multimodal Sensor Data

    Research output: Contribution to journalArticle

  15. Published
  16. Published

    Machine learning to assist risk of bias assessments in systematic reviews

    Research output: Contribution to journalArticle

  17. Published
  18. Published

    Precision-Recall-Gain Curves: PR Analysis Done Right

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  19. Published

    Reliability Maps: A Tool to Enhance Probability Estimates and Improve Classification Accuracy (Best paper award)

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  20. Published
  21. Published

View all (203) »

Selected research projects

  1. REFrAMe

    Project: Funded ProjectResearch project

  2. SPHERE (EPSRC IRC)

    Project: Funded ProjectResearch project

  3. IEU Theme 2

    Project: Funded ProjectResearch project

  4. Generating value from smart electricity meter data

    Project: Funded ProjectResearch project

View all (11) »

Selected awards and activities

  1. ECML-PKDD 2014 Best paper award

    Activity: AwardsPrize (including medals and awards)

  2. Machine Learning

    Activity: Editorial work or peer review of publicationsEditorial activity

View all (2) »