Special Session on Explainability of Learning Machines @IJCNN2017 http://gesture.chalearn.org/ijcnn17_explainability_of_learning_machines Research progress in machine learning and pattern recognition has led to a variety of modeling techniques with (almost) human-like performance in a variety of tasks. A clear example of this type of models are neural networks, whose deep variants dominate the arenas of computer vision and natural language processing among other fields. Although this type of models have obtained astounding results in a variety of tasks (e.g., face recognition with facenet), they are limited in their explainability and interpretability, i.e., in general, users cannot say too much about: ● ●
What is the rationale behind the decision made? (explainability) What in the model structure explains its functioning? (interpretability)
We organize a special session on explainable machine learning. This session aims at compiling the latest efforts and research advances from the scientific community in enhancing traditional machine learning algorithms with explainability capabilities at both the learning and decision stages. Likewise the special session targets novel methodologies and algorithms implementing explanatory mechanisms.
Topics and guidelines ● ● ● ● ●
Explainability of all aspects of machine learning techniques for classification, regression, clustering, feature selection & extraction, ensemble learning, deep learning, etc. Generation of explanations from the outputs of traditional learning machines. Explainability of learned (trained) models for specific tasks. Training, learning procedures leading to explainable models. Natural language explanations of decisions taken by learning machines.
Please prepare and submit your paper according to the guidelines in: http://www.ijcnn.org/paper-submission
Please make sure to select the special session on Explainability and Machine Learning
Important dates: November 15th : SS submission deadline January 20th: Decision notification February 20th: Camera ready submission Organizers: Isabelle Guyon, ChaLearn, Berkeley, USA, Université Paris Saclay,
[email protected] Hugo Jair Escalante, INAOE, Mexico, ChaLearn,
[email protected] Sergio Escalera, Computer Vision Center (UAB) and University of Barcelona,
[email protected] Evelyne Viegas, Microsoft Research,
[email protected]