Search Results for author:
Found 31 papers, 13 papers with code
Shapley Sets: Feature Attribution via Recursive Function Decomposition
Despite their ubiquitous use, Shapley value feature attributions can be misleading due to feature interaction in both model and data.
MIDI-Draw: Sketching to Control Melody Generation
We describe a proof-of-principle implementation of a system for drawing melodies that abstracts away from a note-level input representation via melodic contours.
When the Ground Truth is not True: Modelling Human Biases in Temporal Annotations
Here we propose a method to model human biases on temporal annotations and argue for the use of soft labels.
FAT Forensics: A Python Toolbox for Implementing and Deploying Fairness, Accountability and Transparency Algorithms in Predictive Systems
Predictive systems, in particular machine learning algorithms, can take important, and sometimes legally binding, decisions about our everyday life.
What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components
Explainability techniques for data-driven predictive models based on artificial intelligence and machine learning algorithms allow us to better understand the operation of such systems and help to hold them accountable.
Simply Logical -- Intelligent Reasoning by Example (Fully Interactive Online Edition)
"Simply Logical -- Intelligent Reasoning by Example" by Peter Flach was first published by John Wiley in 1994.
The Weak Supervision Landscape
In this paper we propose a framework for categorising weak supervision settings with the aim of: (1) helping the dataset owner or annotator navigate through the available options within weak supervision when prescribing an annotation process, and (2) describing existing annotations for a dataset to machine learning practitioners so that we allow them to understand the implications for the learning process.
Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence
This approach allows us to define explainability as (logical) reasoning applied to transparent insights (into, possibly black-box, predictive systems) interpreted under background knowledge and placed within a specific context -- a process that engenders understanding in a selected group of explainees.
BIG-bench Machine Learning
Explainable artificial intelligence
+3
Classifier Calibration: A survey on how to assess and improve predicted class probabilities
This paper provides both an introduction to and a detailed overview of the principles and practice of classifier calibration.
Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning
Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments.
Model-based Reinforcement Learning
reinforcement-learning
+1
You Only Write Thrice: Creating Documents, Computational Notebooks and Presentations From a Single Source
We offer a proof-of-concept workflow that composes Jupyter Book (an online document), Jupyter Notebook (a computational narrative) and reveal. js slides from a single markdown source file.
Continual Density Ratio Estimation in an Online Setting
To the best of our knowledge, there is no existing method that can evaluate generative models in continual learning without storing samples from the original distribution.
Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control
In this paper we investigate the use of model-based reinforcement learning to assist people with Type 1 Diabetes with insulin dose decisions.
Discriminative Representation Loss (DRL): A More Efficient Approach than Gradient Re-Projection in Continual Learning
The use of episodic memories in continual learning has been shown to be effective in terms of alleviating catastrophic forgetting.
Interpretable Representations in Explainable AI: From Theory to Practice
Interpretable representations are the backbone of many explainers that target black-box predictive systems based on artificial intelligence and machine learning algorithms.
Semi-Discriminative Representation Loss for Online Continual Learning
The use of episodic memory in continual learning has demonstrated effectiveness for alleviating catastrophic forgetting.
LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
Explainable machine learning provides tools to better understand predictive models and their decisions, but many such methods are limited to producing insights with respect to a single class.
One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency
We address this challenge in this paper by discussing the promises of Interactive Machine Learning for improved transparency of black-box systems using the example of contrastive explanations -- a state-of-the-art approach to Interpretable Machine Learning.
Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
When used as a Work Sheet, our taxonomy can guide the development of new explainability approaches by aiding in their critical evaluation along the five proposed dimensions.
Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration
Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence.
bLIMEy: Surrogate Prediction Explanations Beyond LIME
Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are model-agnostic and are post-hoc (i. e., can be retrofitted).
Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence.
Continual Density Ratio Estimation (CDRE): A new method for evaluating generative models in continual learning
We propose a new method Continual Density Ratio Estimation (CDRE), which can estimate density ratios between a target distribution of real samples and a distribution of samples generated by a model while the model is changing over time and the data of the target distribution is not available after a certain time point.
FACE: Feasible and Actionable Counterfactual Explanations
First, a counterfactual example generated by the state-of-the-art systems is not necessarily representative of the underlying data distribution, and may therefore prescribe unachievable goals(e. g., an unsuccessful life insurance applicant with severe disability may be advised to do more sports).
FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
Today, artificial intelligence systems driven by machine learning algorithms can be in a position to take important, and sometimes legally binding, decisions about our everyday lives.
HyperStream: a Workflow Engine for Streaming Data
This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabilities.
Distribution Calibration for Regression
We are concerned with obtaining well-calibrated output distributions from regression models.
$β^3$-IRT: A New Item Response Model and its Applications
Item Response Theory (IRT) aims to assess latent abilities of respondents based on the correctness of their answers in aptitude test items with different difficulty levels.
Non-Parametric Calibration of Probabilistic Regression
The task of calibration is to retrospectively adjust the outputs from a machine learning model to provide better probability estimates on the target variable.
Probabilistic Sensor Fusion for Ambient Assisted Living
There is a widely-accepted need to revise current forms of health-care provision, with particular interest in sensing systems in the home.
Precision-Recall-Gain Curves: PR Analysis Done Right
Precision-Recall analysis abounds in applications of binary classification where true negatives do not add value and hence should not affect assessment of the classifier's performance.
