PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Finale Doshi‐Velez

5 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Towards A Rigorous Science of Interpretable Machine Learning

    2017 · arXiv (Cornell University)

    As machine learning systems become ubiquitous, there has been a surge of interest in interpretable machine learning: systems that provide explanation for their outputs. These explanations are often used to qualitatively assess other criteria such …

  2. Prior matters: simple and general methods for evaluating and improving topic quality in topic modeling

    2017 · arXiv (Cornell University)

    Latent Dirichlet Allocation (LDA) models trained without stopword removal often produce topics with high posterior probabilities on uninformative words, obscuring the underlying corpus content. Even when canonical stopwords are manually removed, uninformative words common in …

  3. Failure Modes of Variational Autoencoders and Their Effects on\n Downstream Tasks

    2020 · arXiv (Cornell University)

    Variational Auto-encoders (VAEs) are deep generative latent variable models\nthat are widely used for a number of downstream tasks. While it has been\ndemonstrated that VAE training can suffer from a number of pathologies,\nexisting literature lacks characterizations …

  4. Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

    2018 · arXiv (Cornell University)

    As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing uncertainty over the parameters of …

  5. Discovering User Types: Mapping User Traits by Task-Specific Behaviors in Reinforcement Learning

    2023 · arXiv (Cornell University)

    When assisting human users in reinforcement learning (RL), we can represent users as RL agents and study key parameters, called \emph{user traits}, to inform intervention design. We study the relationship between user behaviors (policy classes) …