English
Related papers

Related papers: From Black-Box to White-Box: Control-Theoretic Neu…

200 papers

Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems. Research on opening black-box DNN can be broadly categorized into post-hoc methods and…

Machine Learning · Computer Science 2021-06-25 Sandareka Wickramanayake , Wynne Hsu , Mong Li Lee

We introduce techniques for exploring the functionality of a neural network and extracting simple, human-readable approximations to its performance. By performing gradient ascent on the input space of the network, we are able to produce…

High Energy Physics - Phenomenology · Physics 2018-04-26 Thomas Roxlo , Matthew Reece

Deep neural networks (DNNs) have been shown to outperform traditional machine learning algorithms in a broad variety of application domains due to their effectiveness in modeling complex problems and handling high-dimensional datasets. Many…

Deep neural networks achieve outstanding results in a large variety of tasks, often outperforming human experts. However, a known limitation of current neural architectures is the poor accessibility to understand and interpret the network…

Computer Vision and Pattern Recognition · Computer Science 2022-03-08 Nicola Garau , Niccolò Bisagno , Zeno Sambugaro , Nicola Conci

The rapid evolution of machine learning (ML) has led to the widespread adoption of complex "black box" models, such as deep neural networks and ensemble methods. These models exhibit exceptional predictive performance, making them…

Machine Learning · Computer Science 2025-03-28 Moncef Garouani , Josiane Mothe , Ayah Barhrhouj , Julien Aligon

Neural networks are complex functions of both their inputs and parameters. Much prior work in deep learning theory analyzes the distribution of network outputs at a fixed a set of inputs (e.g. a training dataset) over random initializations…

Disordered Systems and Neural Networks · Physics 2025-04-08 Mike Winer , Boris Hanin

While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…

Machine Learning · Computer Science 2025-07-09 Sofiia Chorna , Kateryna Tarelkina , Eloïse Berthier , Gianni Franchi

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

The lack of interpretability and transparency are preventing economists from using advanced tools like neural networks in their empirical research. In this paper, we propose a class of interpretable neural network models that can achieve…

Econometrics · Economics 2020-12-01 Yucheng Yang , Zhong Zheng , Weinan E

The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack…

Computer Vision and Pattern Recognition · Computer Science 2018-06-27 Bolei Zhou , David Bau , Aude Oliva , Antonio Torralba

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance…

Computer Vision and Pattern Recognition · Computer Science 2018-02-08 Quanshi Zhang , Song-Chun Zhu

Deep neural networks (DNN) are black box algorithms. They are trained using a gradient descent back propagation technique which trains weights in each layer for the sole goal of minimizing training error. Hence, the resulting weights cannot…

Machine Learning · Computer Science 2018-11-05 Daniel Goldfarb

Neural networks are often regarded as "black boxes" due to their complex functions and numerous parameters, which poses significant challenges for interpretability. This study addresses these challenges by introducing methods to enhance the…

Machine Learning · Statistics 2024-09-26 Mohamad Yamen AL Mohamad , Hossein Bevrani , Ali Akbar Haydari

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Machine Learning · Computer Science 2026-04-03 Lingjing Kong , Shaoan Xie , Guangyi Chen , Yuewen Sun , Xiangchen Song , Eric P. Xing , Kun Zhang

Network control theory has recently emerged as a promising approach for understanding brain function and dynamics. By operationalizing notions of control theory for brain networks, it offers a fundamental explanation for how brain dynamics…

Quantitative Methods · Quantitative Biology 2020-03-20 Shikuang Deng , Shi Gu

Deep neural networks are vulnerable to adversarial attacks and hard to interpret because of their black-box nature. The recently proposed invertible network is able to accurately reconstruct the inputs to a layer from its outputs, thus has…

Machine Learning · Computer Science 2019-10-16 Juntang Zhuang , Nicha C. Dvornek , Xiaoxiao Li , Junlin Yang , James S. Duncan

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.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon

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

Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…

Computation and Language · Computer Science 2024-04-04 Josh Magnus Ludan , Qing Lyu , Yue Yang , Liam Dugan , Mark Yatskar , Chris Callison-Burch

Recent advances in deep learning have led to increasingly complex models with deeper layers and more parameters, reducing interpretability and making their decisions harder to understand. While many methods explain black-box reasoning, most…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Nuoye Xiong , Anqi Dong , Ning Wang , Cong Hua , Guangming Zhu , Lin Mei , Peiyi Shen , Liang Zhang