26 papers · ranked by Valyu relevance
Rikab Gambhir, Luisa Lucie-Smith, Jesse Thaler
We review the concepts of interpretability and explainability as they apply to machine learning in physics. We define interpretability as concerning the structural transparency of a model (the ability to understand or approximate its inner workings) and explainability as concerning the scientific content of a model…
Tim Räz
The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to…
Mohammad Ennab, Hamid Mcheick, Jae-Ho Han
The lack of interpretability in artificial intelligence models (i.e., deep learning, machine learning, and rules-based) is an obstacle to their widespread adoption in the healthcare domain. The absence of understandability and transparency frequently leads to (i) inadequate accountability and (ii) a consequent…
Mara Graziani, Lidia Dutkiewicz, Davide Calvaresi, José Pereira Amorim + 12 more
'José Pereira Amorim' 'Katerina Yordanova' 'Mor Vered' 'Rahul Nair' 'Pedro Henriques Abreu' 'Tobias Blanke' 'Valeria Pulignano' 'John O. Prior' 'Lode Lauwaert' 'Wessel Reijers' 'Adrien Depeursinge' 'Vincent Andrearczyk' 'Henning Müller'] Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to…
Ted L. Chang, Hongjing Xia, Sonya Mahajan, Rohit Mahajan + 5 more
We developed an inherently interpretable multilevel Bayesian framework for representing variation in regression coefficients that mimics the piecewise linearity of ReLU-activated deep neural networks. We used the framework to formulate a survival model for using medical claims to predict hospital readmission and death…
Conor Rowan, Alireza Doostan
In the context of scientific machine learning (SciML), the "black box" nature of models involving neural networks makes researchers uneasy. Though neural networks trained on large data sets have been successfully used to describe and predict many physical phenomena, there is a sense that, unlike traditional scientific…
Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu + 4 more
'Jiang Bian' 'Dejing Dou'] Abstract Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction results of deep models. In recent years…
Giulia Capitoli, Marco S. Nobile, Emma L. Ambags, Vincenzo L’Imperio + 2 more
'Michele Provenzano' 'Pietro Liò'] Background The need for transparency and interpretability is a fundamental theme to be addressed by Artificial Intelligence (AI) research, especially in high-risk applications such as healthcare. In this work, we propose Fuzzy Sets in Probability Trees (FPT), a novel method that…
Oded Rotem, Tamar Schwartz, Ron Maor, Yishay Tauber + 5 more
The success of deep learning in identifying complex patterns exceeding human intuition comes at the cost of interpretability. Non-linear entanglement of image features makes deep learning a “black box” lacking human meaningful explanations for the models’ decision. We present DISCOVER, a generative model designed to…
Mehrshad Sadria, Anita Layton, Gary D. Bader
For predictive computational models to be considered reliable in crucial areas such as biology and medicine, it is essential for them to be accurate, robust, and interpretable. A sufficiently robust model should not have its output affected significantly by a slight change in the input. Also, these models should be…
Chao Min, Guoyong Liao, Guoquan Wen, Yingjun Li + 1 more
To address the issues of stability and fidelity in interpretable learning, a novel interpretable methodology, ensemble interpretation, is presented in this paper which integrates multi-perspective explanation of various interpretation methods. On one hand, we define a unified paradigm to describe the common mechanism…
Piyush Borole, Tongjie Wang, Antonio Vergari, Ajitha Rajan
Survival analysis refers to statistical procedures used to analyze data that focuses on the time until an event occurs, such as death in cancer patients. Traditionally, the linear Cox Proportional Hazards (CPH) model is widely used due to its inherent interpretability. CPH model help identify key disease-associated…
Matteo Rizzo, Alberto Veneri, Matteo Marcuzzo, Alessandro Zangari + 4 more
Explainable Artificial Intelligence, or XAI, is a vibrant research topic in the artificial intelligence community. It is raising growing interest across methods and domains, especially those involving high-stakes decision-making, such as the biomedical sector. Much has been written about the subject, yet XAI still…
Marina Dubova, Suyog Chandramouli, Gerd Gigerenzer, Peter Grünwald + 11 more
'William Holmes' 'Tania Lombrozo' 'Marco Marelli' 'Sebastian Musslick' 'Bruno Nicenboim' 'Lauren N. Ross' 'Richard Shiffrin' 'Martha White' 'Eric-Jan Wagenmakers' 'Paul-Christian Bürkner' 'Sabina J. Sloman'] The preference for simple explanations, known as the parsimony principle, has long guided the development of…
Benjamin Leblanc, Pascal Germain
Interpretability and explainability have gained more and more attention in the field of machine learning as they are crucial when it comes to high-stakes decisions and troubleshooting. Since both provide information about predictors and their decision process, they are often seen as two independent means for one single…
Haomiao Wang, Julien Aligon, Julien May, Emmanuel Doumard + 6 more
Although the benefits of machine learning (ML) are undeniable in health-care, explainability plays a vital role in improving transparency and understanding the most decisive and persuasive variables for prediction. The challenge is to identify explanations that make sense to the biomedical expert. This work proposes…
Gerd Gigerenzer
Psychological artificial intelligence (AI) applies insights from psychology to design computer algorithms. Its core domain is decision-making under uncertainty, that is, ill-defined situations that can change in unexpected ways rather than well-defined, stable problems, such as chess and Go. Psychological theories…
Authors not listed
Explainability methods in machine learning-driven research are increasingly being used, but it remains challenging to assess their reliability without deeply investigating the specific problem at hand. In this work, we present a Python-based Workflow for Interpretability Scoring using matched molecular Pairs (WISP).…
Authors not listed
Traditional and non-classical machine learning models for solid-state structure prediction have predominantly relied on compositional features (derived from properties of constituent elements) to predict the existence of structure and its properties. However, the lack of structural information can be a source of…
Marta S. Lemanczyk, Jakub M. Bartoszewicz, Bernhard Y. Renard
Post-hoc interpretability methods are commonly used to understand decisions of genomic deep learning models and reveal new biological insights. However, interactions between sequence regions (e.g. regulatory elements) impact the learning process as well as interpretability methods that are sensitive to dependencies…
Authors not listed
Machine learning holds significant promise for accelerating biomarker discovery in clinical proteomics, yet its real-world impact remains limited by widespread methodological pitfalls and unrealistic expectations. In this perspective, we critically examine the integration of machine learning into clinical proteomics…
Authors not listed
While metallodrugs have been known for decades, developing new effective formulations still remains a challenge, underscoring the need for new tools to assist identification of potent metal-containing anticancer agents. In this work, we developed a straightforward data-driven approach to predict cytotoxicity of metal…
Ping Yang, E. Adrian Henle, Cory M. Simon, Xiaoli Fern
Pesticides benefit agriculture by increasing crop yield, quality, and security. However, pesticides may inadvertently harm bees, which are valuable as pollinators. Thus, candidate pesticides in development pipelines must be assessed for toxicity to bees. Leveraging a data set of 382 molecules with toxicity labels from…
Friedrich Hastedt, Rowan M. Bailey, Klaus Hellgardt, Sophia N. Yaliraki + 2 more
Machine learning models for chemical retrosynthesis have attracted substantial interest in recent years. Unaddressed challenges, particularly the absence of robust evaluation metrics for performance comparison, and the lack of black-box interpretability, obscure model limitations and impede progress in the field. We…
Yuanqi Du, Xian Liu, Shengchao Liu, Jieyu Zhang + 1 more
Discovering meaningful molecules in the vast combinatorial chemical space has been a longstanding challenge in many fields from materials science to drug discovery. Recent advances in machine learning, especially generative models, have made remarkable progress and demonstrate considerable promise for automated…
Authors not listed
Supervised deep learning has become a standard approach to deliver competitive predictive tools that allow relating the structure of molecules and their physicochemical features to properties such as binding to protein targets, performance as electronic materials, and reactivity. However, efforts to understand how…