Results 51 to 60 of about 66,762 (195)

A Semiparametric Approach to Interpretable Machine Learning

CoRR, 2020
Black box models in machine learning have demonstrated excellent predictive performance in complex problems and high-dimensional settings. However, their lack of transparency and interpretability restrict the applicability of such models in critical decision-making processes.
Numair Sani, Jaron J. R. Lee, Razieh Nabi, Ilya Shpitser   +3 more
openaire   +2 more sources

Transparency challenges in policy evaluation with causal machine learning: improving usability and accountability

Data & Policy
Causal machine learning tools are beginning to see use in real-world policy evaluation tasks to flexibly estimate treatment effects. One issue with these methods is that the machine learning models used are generally black boxes, that is, there is no ...
Patrick Rehill, Nicholas Biddle
doaj   +1 more source

Interpretable machine learning for Kronecker coefficients

Advances in Theoretical and Mathematical Physics
We analyze the saliency of neural networks and employ interpretable machine learning models to predict whether the Kronecker coefficients of the symmetric group are zero or not. Our models use triples of partitions as input features, as well as b-loadings derived from the principal component of an embedding that captures the differences between ...
Giorgi Butbaia, Kyu-Hwan Lee, Fabian Ruehle   +2 more
openaire   +2 more sources

Interpretable molecular encodings and representations for machine learning tasks

Computational and Structural Biotechnology Journal
Molecular encodings and their usage in machine learning models have demonstrated significant breakthroughs in biomedical applications, particularly in the classification of peptides and proteins.
Moritz Weckbecker, Aleksandar Anžel, Zewen Yang, Georges Hattab   +3 more
doaj   +1 more source

Ensemble Interpretation: A Unified Method for Interpretable Machine Learning

CoRR, 2023
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 of different interpretation methods,
Chao Min, Guoyong Liao, Guoquan Wen, Yingjun Li, Xing Guo   +4 more
openaire   +2 more sources

Replication data for: Kernel Regularized Least Squares: Reducing Misspecification Bias with a Flexible and Interpretable Machine Learning Approach

, 2013
Code and data to replicate Figures and Tables in " Kernel Regularized Least Squares: Reducing Misspecification Bias with a Flexible and Interpretable Machine Learning Approach.
Hainmueller, Jens and Hazlett, Chad
core   +1 more source

Causality Learning: A New Perspective for Interpretable Machine Learning [PDF]

, 2022
Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc.
Wang, X, Duong, TD, Liu, S, Xu, G, Li, Q
core  

A Non-Invasive Interpretable Diagnosis of Melanoma Skin Cancer Using Deep Learning and Ensemble Stacking of Machine Learning Models

, 2022
A skin lesion is a portion of skin that observes abnormal growth compared to other areas of the skin. The ISIC 2018 lesion dataset has seven classes.
Nazir, Amril, Md. Mahfuzur Rahman, Shorfuzzaman, Mohammad, Iftiaz A. Alfi, Amril Nazir, Mohammad Shorfuzzaman, Rahman, Mahfuzur, Alfi, Iftiaz A.   +7 more
core   +1 more source

Interpretable Machine Learning for TabPFN

The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes. The TabPFN model, a special case of PFNs for tabular data, is able to achieve state-of-the-art performance on a variety of classification tasks while producing posterior predictive distributions in mere seconds by in-context ...
David Rundel, Julius Kobialka, Constantin von Crailsheim, Matthias Feurer 0001, Thomas Nagler, David Rügamer   +5 more
openaire   +2 more sources

Machine learning interpretability meets TLS fingerprinting

Soft Computing, 2023
Protecting users' privacy over the Internet is of great importance; however, it becomes harder and harder to maintain due to the increasing complexity of network protocols and components. Therefore, investigating and understanding how data is leaked from the information transmission platforms and protocols can lead us to a more secure environment.
Mahdi Jafari Siavoshani, Amirhossein Khajehpour, Amirmohammad Ziaei, Amir Ali Gatmiri, Ali Taheri   +4 more
openaire   +2 more sources