Related papers: TSInterpret: A unified framework for time series i…
As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI…
Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream applications, the learned representations often lack…
Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g.,…
Explaining deep learning models operating on time series data is crucial in various applications of interest which require interpretable and transparent insights from time series signals. In this work, we investigate this problem from an…
The ability to interpret decisions taken by Machine Learning (ML) models is fundamental to encourage trust and reliability in different practical applications. Recent interpretation strategies focus on human understanding of the underlying…
Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historical-value models. Yet, despite the attractive properties of time-index models, such as being able to…
We study the use of a time series encoder to learn representations that are useful on data set types with which it has not been trained on. The encoder is formed of a convolutional neural network whose temporal output is summarized by a…
Advanced machine learning models have recently achieved high predictive accuracy for weather and climate prediction. However, these complex models often lack inherent transparency and interpretability, acting as "black boxes" that impede…
Deep learning models have achieved state-of-the-art performance in many classification tasks. However, most of them cannot provide an interpretation for their classification results. Machine learning models that are interpretable are…
We introduce a temporal feature encoding architecture called Time Series Representation Model (TSRM) for multivariate time series forecasting and imputation. The architecture is structured around CNN-based representation layers, each…
Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently, partially…
In the era of increasingly complex AI models for time series forecasting, progress is often measured by marginal improvements on benchmark leaderboards. However, this approach suffers from a fundamental flaw: standard evaluation metrics…
The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…
Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel…
Despite the popularisation of machine learning models, more often than not, they still operate as black boxes with no insight into what is happening inside the model. There exist a few methods that allow to visualise and explain why a model…
We provide a novel notion of what it means to be interpretable, looking past the usual association with human understanding. Our key insight is that interpretability is not an absolute concept and so we define it relative to a target model,…
In this paper, we investigate the distillation of time series reasoning capabilities into small, instruction-tuned language models as a step toward building interpretable time series foundation models. Leveraging a synthetic dataset of…
Over the past decade, adaptive video streaming technology has witnessed significant advancements, particularly driven by the rapid evolution of deep learning techniques. However, the black-box nature of deep learning algorithms presents…
Evaluating time series attribution methods is difficult because real-world datasets rarely provide ground truth for which time points drive a prediction. A common workaround is to generate synthetic data where class-discriminating features…
Artificial Intelligence models are becoming increasingly more powerful and accurate, supporting or even replacing humans' decision making. But with increased power and accuracy also comes higher complexity, making it hard for users to…