Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Regression conformal prediction with random forests

- U. Johansson, Henrik Boström, Tuve Löfström, Henrik Linusson
- Computer Science, Mathematics
- Machine Learning
- 1 October 2014

Regression conformal prediction produces prediction intervals that are valid, i.e., the probability of excluding the correct target value is bounded by a predefined confidence level. The most… Expand

On the Calibration of Aggregated Conformal Predictors

- Henrik Linusson, U. Norinder, Henrik Boström, U. Johansson, Tuve Löfström
- Computer Science, Mathematics
- COPA
- 31 May 2017

Conformal prediction is a learning framework that produces models that associate with each of their predictions a measure of statistically valid confidence. These models are typically constructed o… Expand

Evolved decision trees as conformal predictors

- Ulf Johansson, Rikard König, Tuve Löfström, Henrik Boström
- Computer Science
- IEEE Congress on Evolutionary Computation
- 20 June 2013

In conformal prediction, predictive models output sets of predictions with a bound on the error rate. In classification, this translates to that the probability of excluding the correct class is… Expand

Accelerating difficulty estimation for conformal regression forests

- Henrik Boström, Henrik Linusson, Tuve Löfström, U. Johansson
- Computer Science, Mathematics
- Annals of Mathematics and Artificial Intelligence
- 1 March 2017

The conformal prediction framework allows for specifying the probability of making incorrect predictions by a user-provided confidence level. In addition to a learning algorithm, the framework… Expand

Effective utilization of data in inductive conformal prediction using ensembles of neural networks

- Tuve Löfström, Ulf Johansson, Henrik Boström
- Computer Science
- The International Joint Conference on Neural…
- 1 August 2013

Conformal prediction is a new framework producing region predictions with a guaranteed error rate. Inductive conformal prediction (ICP) was designed to significantly reduce the computational cost… Expand

Efficiency Comparison of Unstable Transductive and Inductive Conformal Classifiers

- Henrik Linusson, U. Johansson, Henrik Boström, Tuve Löfström
- Computer Science
- AIAI Workshops
- 19 September 2014

In the conformal prediction literature, it appears axiomatic that transductive conformal classifiers possess a higher predictive efficiency than inductive conformal classifiers, however, this depends… Expand

The Importance of Diversity in Neural Network Ensembles - An Empirical Investigation

- U. Johansson, Tuve Löfström, L. Niklasson
- Computer Science
- International Joint Conference on Neural Networks
- 29 October 2007

When designing ensembles, it is almost an axiom that the base classifiers must be diverse in order for the ensemble to generalize well. Unfortunately, there is no clear definition of the key term… Expand

Interpretable regression trees using conformal prediction

- Ulf Johansson, Henrik Linusson, Tuve Löfström, Henrik Boström
- Computer Science
- Expert Syst. Appl.
- 1 May 2018

A key property of conformal predictors is that they are valid, i.e., their error rate on novel data is bounded by a preset level of confidence. For regression, this is achieved by turning the point… Expand

Model-agnostic nonconformity functions for conformal classification

- U. Johansson, Henrik Linusson, Tuve Löfström, Henrik Boström
- Computer Science
- International Joint Conference on Neural Networks…
- 1 May 2017

A conformai predictor outputs prediction regions, for classification label sets. The key property of all conformai predictors is that they are valid, i.e., their error rate on novel data is bounded… Expand

Overproduce-and-select: The grim reality

- U. Johansson, Tuve Löfström, Henrik Boström
- Computer Science
- IEEE Symposium on Computational Intelligence and…
- 16 April 2013

Overproduce-and-select (OPAS) is a frequently used paradigm for building ensembles. In static OPAS, a large number of base classifiers are trained, before a subset of the available models is selected… Expand