Search Results for author: Raul Santos-Rodriguez

Found 28 papers, 6 papers with code

Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL

no code implementations8 Sep 2022 Taku Yamagata, Ahmed Khalil, Raul Santos-Rodriguez

In this paper, we propose Q-learning Decision Transformer (QDT) that addresses the shortcomings of DT by leveraging the benefit of Dynamic Programming (Q-learning).

Offline RL Q-Learning

What and How of Machine Learning Transparency: Building Bespoke Explainability Tools with Interoperable Algorithmic Components

no code implementations8 Sep 2022 Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez, Peter Flach

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.

Explanation Generation

The Weak Supervision Landscape

no code implementations30 Mar 2022 Rafael Poyiadzi, Daniel Bacaicoa-Barber, Jesus Cid-Sueiro, Miquel Perello-Nieto, Peter Flach, Raul Santos-Rodriguez

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.

BIG-bench Machine Learning Navigate

Classifier Calibration: How to assess and improve predicted class probabilities: a survey

no code implementations20 Dec 2021 Telmo Silva Filho, Hao Song, Miquel Perello-Nieto, Raul Santos-Rodriguez, Meelis Kull, Peter Flach

This paper provides both an introduction to and a detailed overview of the principles and practice of classifier calibration.

Decision Making

Uncertainty Quantification of Surrogate Explanations: an Ordinal Consensus Approach

no code implementations17 Nov 2021 Jonas Schulz, Rafael Poyiadzi, Raul Santos-Rodriguez

To this end, we produce estimates of the uncertainty of a given explanation by measuring the ordinal consensus amongst a set of diverse bootstrapped surrogate explainers.

Reinforcement Learning with Feedback from Multiple Humans with Diverse Skills

no code implementations16 Nov 2021 Taku Yamagata, Ryan McConville, Raul Santos-Rodriguez

We empirically show that our approach can accurately learn the reliability of each trainer correctly and use it to maximise the information gained from the multiple trainers' feedback, even if some of the sources are adversarial.

reinforcement-learning

OPERAnet: A Multimodal Activity Recognition Dataset Acquired from Radio Frequency and Vision-based Sensors

1 code implementation8 Oct 2021 Mohammud J. Bocus, Wenda Li, Shelly Vishwakarma, Roget Kou, Chong Tang, Karl Woodbridge, Ian Craddock, Ryan McConville, Raul Santos-Rodriguez, Kevin Chetty, Robert Piechocki

This dataset can be exploited to advance WiFi and vision-based HAR, for example, using pattern recognition, skeletal representation, deep learning algorithms or other novel approaches to accurately recognize human activities.

Human Activity Recognition Multimodal Activity Recognition

Understanding surrogate explanations: the interplay between complexity, fidelity and coverage

no code implementations9 Jul 2021 Rafael Poyiadzi, Xavier Renard, Thibault Laugel, Raul Santos-Rodriguez, Marcin Detyniecki

This paper analyses the fundamental ingredients behind surrogate explanations to provide a better understanding of their inner workings.

On the overlooked issue of defining explanation objectives for local-surrogate explainers

no code implementations10 Jun 2021 Rafael Poyiadzi, Xavier Renard, Thibault Laugel, Raul Santos-Rodriguez, Marcin Detyniecki

In this work we review the similarities and differences amongst multiple methods, with a particular focus on what information they extract from the model, as this has large impact on the output: the explanation.

On the relation between statistical learning and perceptual distances

no code implementations ICLR 2022 Alexander Hepburn, Valero Laparra, Raul Santos-Rodriguez, Johannes Ballé, Jesús Malo

Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function.

BIG-bench Machine Learning Perceptual Distance

Self-Supervised WiFi-Based Activity Recognition

no code implementations19 Apr 2021 Hok-Shing Lau, Ryan McConville, Mohammud J. Bocus, Robert J. Piechocki, Raul Santos-Rodriguez

Traditional approaches to activity recognition involve the use of wearable sensors or cameras in order to recognise human activities.

Activity Recognition Contrastive Learning +1

Self-play Learning Strategies for Resource Assignment in Open-RAN Networks

no code implementations3 Mar 2021 Xiaoyang Wang, Jonathan D Thomas, Robert J Piechocki, Shipra Kapoor, Raul Santos-Rodriguez, Arjun Parekh

Open Radio Access Network (ORAN) is being developed with an aim to democratise access and lower the cost of future mobile data networks, supporting network services with various QoS requirements, such as massive IoT and URLLC.

Edge-computing Management

Hypothesis Testing for Class-Conditional Label Noise

no code implementations3 Mar 2021 Rafael Poyiadzi, Weisong Yang, Niall Twomey, Raul Santos-Rodriguez

Differently, in this paper we assume we have access to a set of anchor points whose true posterior is approximately 1/2.

Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception

no code implementations22 Feb 2021 Alexander Hepburn, Raul Santos-Rodriguez

We generate explanations for images in the Imagenet-C dataset and demonstrate how using a perceptual distances in the surrogate explainer creates more coherent explanations for the distorted and reference images.

Image Classification

bLIMEy: Surrogate Prediction Explanations Beyond LIME

1 code implementation29 Oct 2019 Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez, Peter Flach

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).

Explainable artificial intelligence

PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance

no code implementations28 Oct 2019 Alexander Hepburn, Valero Laparra, Jesús Malo, Ryan McConville, Raul Santos-Rodriguez

Traditionally, the vision community has devised algorithms to estimate the distance between an original image and images that have been subject to perturbations.

Perceptual Distance

FACE: Feasible and Actionable Counterfactual Explanations

1 code implementation20 Sep 2019 Rafael Poyiadzi, Kacper Sokol, Raul Santos-Rodriguez, Tijl De Bie, Peter Flach

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

3 code implementations11 Sep 2019 Kacper Sokol, Raul Santos-Rodriguez, Peter Flach

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.

BIG-bench Machine Learning Fairness

N2D: (Not Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding

4 code implementations16 Aug 2019 Ryan McConville, Raul Santos-Rodriguez, Robert J. Piechocki, Ian Craddock

We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is best able to find the most clusterable manifold in the embedding, suggesting local manifold learning on an autoencoded embedding is effective for discovering higher quality discovering clusters.

Deep Clustering Image Clustering +2

Enforcing Perceptual Consistency on Generative Adversarial Networks by Using the Normalised Laplacian Pyramid Distance

no code implementations9 Aug 2019 Alexander Hepburn, Valero Laparra, Ryan McConville, Raul Santos-Rodriguez

While an important part of the evaluation of the generated images usually involves visual inspection, the inclusion of human perception as a factor in the training process is often overlooked.

Image Segmentation Image-to-Image Translation +2

Label Propagation for Learning with Label Proportions

no code implementations24 Oct 2018 Rafael Poyiadzi, Raul Santos-Rodriguez, Niall Twomey

Learning with Label Proportions (LLP) is the problem of recovering the underlying true labels given a dataset when the data is presented in the form of bags.

Informative Data Projections: A Framework and Two Examples

no code implementations27 Nov 2015 Tijl De Bie, Jefrey Lijffijt, Raul Santos-Rodriguez, Bo Kang

Methods for Projection Pursuit aim to facilitate the visual exploration of high-dimensional data by identifying interesting low-dimensional projections.

Meta-song evaluation for chord recognition

no code implementations TBD 2011 Yizhao Ni, Matt Mcvicar, Raul Santos-Rodriguez, Tijl De Bie

We present a new approach to evaluate chord recognition systems on songs which do not have full annotations.

Chord Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.