相关论文: Mapping chemical performance on molecular structur…

With the advancement of technology for artificial intelligence (AI) based solutions and analytics compute engines, machine learning (ML) models are getting more complex day by day. Most of these models are generally used as a black box…

While the uptake of data-driven approaches for materials science and chemistry is at an exciting, early stage, to realise the true potential of machine learning models for successful scientific discovery, they must have qualities beyond…

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific…

We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE. CLE gives an faithful and interpretable explanation to the prediction, by approximating the model locally using an…

The task here is to predict the toxicological activity of chemical compounds based on the Tox21 dataset, a benchmark in computational toxicology. After a domain-specific overview of chemical toxicity, we discuss current computational…

Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes. We will unravel these black boxes and will demonstrate approaches to understand the learned representations…

Molecular property prediction is a crucial task that guides the design of new compounds, including drugs and materials. While explainable artificial intelligence methods aim to scrutinize model predictions by identifying influential…

As machine learning becomes an important part of many real world applications affecting human lives, new requirements, besides high predictive accuracy, become important. One important requirement is transparency, which has been associated…

Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in…

Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation…

Providing explainable molecular property predictions is critical for many scientific domains, such as drug discovery and material science. Though transformer-based language models have shown great potential in accurate molecular property…

Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most accurate models often hinders their safe use. Thus, there is a…

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system. A large number of interpreting methods focus on identifying explanatory input features, which generally fall into two main…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable. An explanation can appear plausible to humans but fail to…

The simulation of intrinsic contributions to molecular properties holds the potential to allow for chemistry to be directly inferred from changes to electronic structures at the atomic level. In the present study, we demonstrate how such…

Explainability techniques are crucial in gaining insights into the reasons behind the predictions of deep learning models, which have not yet been applied to chemical language models. We propose an explainable AI technique that attributes…

The integration of machine learning (ML) into chemistry offers transformative potential in the design of molecules with targeted properties. However, the focus has often been on creating highly efficient predictive models, sometimes at the…