English
Related papers

Related papers: Inducing Interpretable Voting Classifiers without …

200 papers

Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…

Machine Learning · Computer Science 2022-02-22 Marco Bertolini , Djork-Arné Clevert , Floriane Montanari

Deep neural classifiers have recently found tremendous success in data-driven control systems. However, existing models suffer from a trade-off between accuracy and adversarial robustness. This limitation must be overcome in the control of…

Machine Learning · Computer Science 2024-06-05 Yatong Bai , Brendon G. Anderson , Somayeh Sojoudi

Interpretability of deep reinforcement learning systems could assist operators with understanding how they interact with their environment. Vector quantization methods -- also called codebook methods -- discretize a neural network's latent…

Artificial Intelligence · Computer Science 2024-07-30 Kenneth Eaton , Jonathan Balloch , Julia Kim , Mark Riedl

System combination is an important technique for combining the hypotheses of different machine translation systems to improve translation performance. Although early statistical approaches to system combination have been proven effective in…

Computation and Language · Computer Science 2020-07-15 Xuancheng Huang , Jiacheng Zhang , Zhixing Tan , Derek F. Wong , Huanbo Luan , Jingfang Xu , Maosong Sun , Yang Liu

There is an increased interest in solving complex constrained problems where part of the input is not given as facts but received as raw sensor data such as images or speech. We will use "visual sudoku" as a prototype problem, where the…

Machine Learning · Computer Science 2020-03-25 Maxime Mulamba , Jayanta Mandi , Rocsildes Canoy , Tias Guns

To understand how well a large language model captures certain semantic or syntactic features, researchers typically apply probing classifiers. However, the accuracy of these classifiers is critical for the correct interpretation of the…

Computation and Language · Computer Science 2023-12-19 Sergey A. Saltykov

A new game-theoretic approach for combining multiple classifiers is proposed. A short introduction in Game Theory and coalitions illustrate the way any collective decision scheme can be viewed as a competitive game of coalitions that are…

Computer Science and Game Theory · Computer Science 2015-02-10 Harris V. Georgiou

To date, there has been no formal study of the statistical cost of interpretability in machine learning. As such, the discourse around potential trade-offs is often informal and misconceptions abound. In this work, we aim to initiate a…

Machine Learning · Computer Science 2020-10-29 Gintare Karolina Dziugaite , Shai Ben-David , Daniel M. Roy

Despite huge advances, LLMs still lack convenient and reliable methods to quantify the uncertainty in their responses, making them difficult to trust in high-stakes applications. One of the simplest approaches to eliciting more accurate…

Artificial Intelligence · Computer Science 2025-10-07 Aparna Nair-Kanneganti , Trevor J. Chan , Shir Goldfinger , Emily Mackay , Brian Anthony , Alison Pouch

Reinforcement learning techniques achieved human-level performance in several tasks in the last decade. However, in recent years, the need for interpretability emerged: we want to be able to understand how a system works and the reasons…

Machine Learning · Computer Science 2023-01-13 Leonardo Lucio Custode , Giovanni Iacca

Deep neural networks are behind many of the recent successes in machine learning applications. However, these models can produce overconfident decisions while encountering out-of-distribution (OOD) examples or making a wrong prediction.…

Machine Learning · Computer Science 2021-06-24 Navid Kardan , Ankit Sharma , Kenneth O. Stanley

We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time. The predictive power of such models can heavily depend on the structure of…

Machine Learning · Statistics 2017-03-06 Yacine Jernite , Anna Choromanska , David Sontag

Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality. In this paper, we propose a knowledge distillation based decision trees extension, dubbed rectified…

Machine Learning · Computer Science 2020-08-24 Yiming Li , Jiawang Bai , Jiawei Li , Xue Yang , Yong Jiang , Shu-Tao Xia

Decision trees are popular classification models, providing high accuracy and intuitive explanations. However, as the tree size grows the model interpretability deteriorates. Traditional tree-induction algorithms, such as C4.5 and CART,…

Machine Learning · Computer Science 2022-11-29 Guangyi Zhang , Aristides Gionis

We propose a novel approach for using unsupervised boosting to create an ensemble of generative models, where models are trained in sequence to correct earlier mistakes. Our meta-algorithmic framework can leverage any existing base learner…

Machine Learning · Computer Science 2017-12-25 Aditya Grover , Stefano Ermon

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Tree ensembles, such as random forests and boosted trees, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we present a method to make a…

Machine Learning · Statistics 2017-03-01 Satoshi Hara , Kohei Hayashi

We propose a procedure for automated implicit inductive theorem proving for equational specifications made of rewrite rules with conditions and constraints. The constraints are interpreted over constructor terms (representing data values),…

Logic in Computer Science · Computer Science 2008-12-01 Adel Bouhoula , Florent Jacquemard

Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…

Machine Learning · Computer Science 2023-06-21 Abhinav Kumar , Chenhao Tan , Amit Sharma

Recommendation algorithms that incorporate techniques from deep learning are becoming increasingly popular. Due to the structure of the data coming from recommendation domains (i.e., one-hot-encoded vectors of item preferences), these…

Machine Learning · Computer Science 2017-06-14 Joan Serrà , Alexandros Karatzoglou