2.2k citations
- Brown UniversityUS17 papers
- Allen InstituteUS16 papers
- University of WashingtonUS9 papers
- Institut du CerveauFR8 papers
- Sorbonne UniversitéFR7 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR7 papers
- Chongqing Normal UniversityCN6 papers
- East China Normal UniversityCN6 papers
- Shanxi UniversityCN6 papers
- University of CalgaryCA6 papers
- California Institute of TechnologyUS5 papers
- Harvard UniversityUS5 papers
8 papers · 1 filter
Attention for Causal Relationship Discovery from Biological Neural Dynamics
Ziyu Lu, Anika Tabassum, Shruti Kulkarni +4
This paper explores the potential of the transformer models for learning Granger causality in networks with complex nonlinear dynamics at every node, as in neurobiological and biop…
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
Thomas Fel, Victor Boutin, Mazda Moayeri +5
In recent years, concept-based approaches have emerged as some of the most promising explainability methods to help us interpret the decisions of Artificial Neural Networks (ANNs).…
Learning Functional Transduction
Mathieu Chalvidal, Thomas Serre, Rufin VanRullen
Research in machine learning has polarized into two general approaches for regression tasks: Transductive methods construct estimates directly from available data but are usually p…
Mitigating Bias in Calibration Error Estimation
Rebecca Roelofs, Nicholas Cain, Jonathon Shlens +1
For an AI system to be reliable, the confidence it expresses in its decisions must match its accuracy. To assess the degree of match, examples are typically binned by confidence an…
How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks
Thomas Fel, David Vigouroux, Rémi Cadène +1
A plethora of methods have been proposed to explain how deep neural networks reach their decisions but comparatively, little effort has been made to ensure that the explanations pr…
Mixture Representation Learning with Coupled Autoencoders
Yeganeh M. Marghi, Rohan Gala, Uygar Sümbül
Jointly identifying a mixture of discrete and continuous factors of variability without supervision is a key problem in unraveling complex phenomena. Variational inference has emer…