Related papers: Model-Agnostic Interpretation Framework in Machine…
Data-driven models are central to scientific discovery. In efforts to achieve state-of-the-art model accuracy, researchers are employing increasingly complex machine learning algorithms that often outperform simple regressions in…
Deep learning is becoming increasingly adopted in business and industry due to its ability to transform large quantities of data into high-performing models. These models, however, are generally regarded as black boxes, which, in spite of…
Deep learning models are favored in many research and industry areas and have reached the accuracy of approximating or even surpassing human level. However they've long been considered by researchers as black-box models for their…
One of the desired key properties of deep learning models is the ability to generalise to unseen samples. When provided with new samples that are (perceptually) similar to one or more training samples, deep learning models are expected to…
The challenge of creating interpretable models has been taken up by two main research communities: ML researchers primarily focused on lower-level explainability methods that suit the needs of engineers, and HCI researchers who have more…
The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…
Sophisticated machine learning (ML) models to inform trading in the financial sector create problems of interpretability and risk management. Seemingly robust forecasting models may behave erroneously in out of distribution settings. In…
Modern statistical learning techniques have often emphasized prediction performance over interpretability, giving rise to "black box" models that may be difficult to understand, and to generalize to other settings. We conceptually divide a…
Model interpretability is a key challenge that has yet to align with the advancements observed in contemporary state-of-the-art deep learning models. In particular, deep learning aided vision tasks require interpretability, in order for…
As the discipline has evolved, research in machine learning has been focused more and more on creating more powerful neural networks, without regard for the interpretability of these networks. Such "black-box models" yield state-of-the-art…
As artificial intelligence is increasingly affecting all parts of society and life, there is growing recognition that human interpretability of machine learning models is important. It is often argued that accuracy or other similar…
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…
Modern data analytics underpinned by machine learning techniques has become a key enabler to the automation of data-led decision making. As an important branch of state-of-the-art data analytics, business process predictions are also faced…
The proliferation of machine learning (ML) has drawn unprecedented interest in the study of various multimedia contents such as text, image, audio and video, among others. Consequently, understanding and learning ML-based representations…
The ubiquity of machine learning based predictive models in modern society naturally leads people to ask how trustworthy those models are? In predictive modeling, it is quite common to induce a trade-off between accuracy and…
The last decade witnessed an ever-increasing stream of successes in Machine Learning (ML). These successes offer clear evidence that ML is bound to become pervasive in a wide range of practical uses, including many that directly affect…
Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpretation, that explains the model's decision process on that…
This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…
Interpretability is a pressing issue for machine learning. Common approaches to interpretable machine learning constrain interactions between features of the input, rendering the effects of those features on a model's output comprehensible…
Human Activity Recognition using time-series data from wearable sensors poses unique challenges due to complex temporal dependencies, sensor noise, placement variability, and diverse human behaviors. These factors, combined with the…