English
Related papers

Related papers: Coloring black boxes: visualization of neural netw…

200 papers

Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with…

Machine Learning · Computer Science 2020-12-09 Udo Schlegel , Daniela Oelke , Daniel A. Keim , Mennatallah El-Assady

The recent success of brain-inspired deep neural networks (DNNs) in solving complex, high-level visual tasks has led to rising expectations for their potential to match the human visual system. However, DNNs exhibit idiosyncrasies that…

Neurons and Cognition · Quantitative Biology 2019-05-08 Chihye Han , Wonjun Yoon , Gihyun Kwon , Seungkyu Nam , Daeshik Kim

In recent years, machine learning (ML) has become a key enabling technology for the sciences and industry. Especially through improvements in methodology, the availability of large databases and increased computational power, today's ML…

Artificial Intelligence · Computer Science 2019-09-27 Wojciech Samek , Klaus-Robert Müller

Accurate uncertainty quantification is a critical challenge in machine learning. While neural networks are highly versatile and capable of learning complex patterns, they often lack interpretability due to their ``black box'' nature. On the…

Machine Learning · Computer Science 2025-11-18 Pragatheeswaran Vipulananthan , Kamal Premaratne , Dilip Sarkar , Manohar N. Murthi

Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger…

Computer Vision and Pattern Recognition · Computer Science 2014-12-30 Wei Yu , Kuiyuan Yang , Yalong Bai , Hongxun Yao , Yong Rui

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

The black-box nature of neural networks limits model decision interpretability, in particular for high-dimensional inputs in computer vision and for dense pixel prediction tasks like segmentation. To address this, prior work combines neural…

Computer Vision and Pattern Recognition · Computer Science 2020-06-15 Alvin Wan , Daniel Ho , Younjin Song , Henk Tillman , Sarah Adel Bargal , Joseph E. Gonzalez

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…

Prediction and explanation are key objects in supervised machine learning, where predictive models are known as black boxes and explanatory models are known as glass boxes. Explanation provides the necessary and sufficient information to…

Methodology · Statistics 2018-07-31 Caleb Deen Bastian , Herschel Rabitz

Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging. We explore the central prevailing themes of this emerging area and present a taxonomy…

Image and Video Processing · Electrical Eng. & Systems 2020-05-14 Gregory Ongie , Ajil Jalal , Christopher A. Metzler , Richard G. Baraniuk , Alexandros G. Dimakis , Rebecca Willett

For many evaluation metrics commonly used as benchmarks for unconditional image generation, trivially memorizing the training set attains a better score than models which are considered state-of-the-art; we consider this problematic. We…

Machine Learning · Computer Science 2020-01-14 Ishaan Gulrajani , Colin Raffel , Luke Metz

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-24 Diego Gragnaniello , Francesco Marra , Giovanni Poggi , Luisa Verdoliva

Brain imaging of mental health, neurodevelopmental and learning disorders has coupled with machine learning to identify patients based only on their brain activation, and ultimately identify features that generalize from smaller samples of…

Image and Video Processing · Electrical Eng. & Systems 2020-07-21 Laura Tomaz Da Silva , Nathalia Bianchini Esper , Duncan D. Ruiz , Felipe Meneguzzi , Augusto Buchweitz

In recent years convolutional neural networks (CNN) have shown striking progress in various tasks. However, despite the high performance, the training and prediction process remains to be a black box, leaving it a mystery to extract what…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Haoyue Dai

Despite the great success of Convolutional Neural Networks (CNNs) in Computer Vision and Natural Language Processing, the working mechanism behind CNNs is still under extensive discussions and research. Driven by a strong demand for the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Jingyi Shen , Han-Wei Shen

The impressive results of modern neural networks partly come from their non linear behaviour. Unfortunately, this property makes it very difficult to apply formal verification tools, even if we restrict ourselves to networks with a…

Artificial Intelligence · Computer Science 2021-05-18 Julien Girard-Satabin , Aymeric Varasse , Marc Schoenauer , Guillaume Charpiat , Zakaria Chihani

Neural Networks are the state of the art for many tasks in the computer vision domain, including Writer Identification (WI) and Writer Verification (WV). The transparency of these "black box" systems is important for improvements of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Viktoria Pundy , Marco Peer , Florian Kleber

Factorization machines and polynomial networks are supervised polynomial models based on an efficient low-rank decomposition. We extend these models to the multi-output setting, i.e., for learning vector-valued functions, with application…

Machine Learning · Statistics 2017-11-07 Mathieu Blondel , Vlad Niculae , Takuma Otsuka , Naonori Ueda

Deep learning models often function as black boxes, providing no straightforward reasoning for their predictions. This is particularly true for computer vision models, which process tensors of pixel values to generate outcomes in tasks such…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Sachin Karmani , Thanushon Sivakaran , Gaurav Prasad , Mehmet Ali , Wenbo Yang , Sheyang Tang

We use graphical methods to probe neural nets that classify images. Plots of t-SNE outputs at successive layers in a network reveal increasingly organized arrangement of the data points. They can also reveal how a network can diminish or…

Machine Learning · Computer Science 2021-07-28 Christopher R. Hoyt , Art B. Owen
‹ Prev 1 8 9 10 Next ›