English
Related papers

Related papers: Interpretable neural networks based on continuous-…

200 papers

Interpretable representations are the backbone of many explainers that target black-box predictive systems based on artificial intelligence and machine learning algorithms. They translate the low-level data representation necessary for good…

Machine Learning · Computer Science 2024-04-29 Kacper Sokol , Peter Flach

Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of…

Machine Learning · Computer Science 2021-09-29 Fenglei Fan , Jinjun Xiong , Mengzhou Li , Ge Wang

The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on…

Machine Learning · Computer Science 2026-03-05 Elena Golimblevskaia , Aakriti Jain , Bruno Puri , Ammar Ibrahim , Wojciech Samek , Sebastian Lapuschkin

Machine learning methods can be a valuable aid in the scientific process, but they need to face challenging settings where data come from inhomogeneous experimental conditions. Recent meta-learning methods have made significant progress in…

Machine Learning · Computer Science 2024-03-21 Matthieu Blanke , Marc Lelarge

The ability of deep learning (DL) to improve the practice of medicine and its clinical outcomes faces a looming obstacle: model interpretation. Without description of how outputs are generated, a collaborating physician can neither resolve…

Machine Learning · Computer Science 2020-06-30 Christopher Snyder , Sriram Vishwanath

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

Computation and Language · Computer Science 2026-03-31 Yibo Yang

Recent advancements in post-hoc and inherently interpretable methods have markedly enhanced the explanations of black box classifier models. These methods operate either through post-analysis or by integrating concept learning during model…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Bor-Shiun Wang , Chien-Yi Wang , Wei-Chen Chiu

While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making…

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for…

Machine Learning · Computer Science 2022-05-25 Ben Zhang , Zhetong Dong , Junsong Zhang , Hongwei Lin

Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque "black boxes". The difficulty of interpreting the…

Machine Learning · Statistics 2020-01-22 Enguerrand Horel , Virgile Mison , Tao Xiong , Kay Giesecke , Lidia Mangu

Multimodal learning aims to enhance perceptual and decision-making capabilities by integrating information from diverse sources. However, classical deep learning approaches face a critical trade-off between the high accuracy of black-box…

Quantum Physics · Physics 2026-01-14 Yu Wu , Qianli Zhou , Jie Geng , Xinyang Deng , Wen Jiang

We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-20 David Bau , Bolei Zhou , Aditya Khosla , Aude Oliva , Antonio Torralba

In recent years, Deep Reinforcement Learning has made impressive advances in solving several important benchmark problems for sequential decision making. Many control applications use a generic multilayer perceptron (MLP) for non-vision…

Machine Learning · Computer Science 2020-03-13 Mario Srouji , Jian Zhang , Ruslan Salakhutdinov

Deep neural networks (DNNs) are known as black-box models. In other words, it is difficult to interpret the internal state of the model. Improving the interpretability of DNNs is one of the hot research topics. However, at present, the…

Machine Learning · Computer Science 2019-09-17 Masanari Kimura , Masayuki Tanaka

Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction. We…

Computer Vision and Pattern Recognition · Computer Science 2019-04-18 Sadaf Gulshad , Jan Hendrik Metzen , Arnold Smeulders , Zeynep Akata

Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences…

Machine Learning · Statistics 2016-11-30 Hakan Bilen , Andrea Vedaldi

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not…

Artificial Intelligence · Computer Science 2022-01-26 Mohan Sridharan , Tiago Mota

While deep neural networks have led to major advances in image recognition, language translation, data mining, and game playing, there are well-known limits to the paradigm such as lack of explainability, difficulty of incorporating prior…

Artificial Intelligence · Computer Science 2023-02-24 Paulo Shakarian , Gerardo I. Simari

The interpretability of machine learning, particularly for deep neural networks, is crucial for decision making in real-world applications. One approach is replacing the un-interpretable machine learning model with a surrogate model, which…

Machine Learning · Statistics 2020-07-22 Keiichi Kisamori , Keisuke Yamazaki , Yuto Komori , Hiroshi Tokieda

In this work, we propose a simple but effective method to interpret black-box machine learning models globally. That is, we use a compact binary tree, the interpretation tree, to explicitly represent the most important decision rules that…

Machine Learning · Computer Science 2018-05-24 Chengliang Yang , Anand Rangarajan , Sanjay Ranka