English
Related papers

Related papers: Interpreting Deep Classifier by Visual Distillatio…

200 papers

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization --…

Machine Learning · Statistics 2026-05-08 Joseph H. Rudoler , Kevin Tan , Giles Hooker , Konrad P. Kording

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Machine Learning · Computer Science 2019-10-08 Yulong Wang , Xiaolin Hu , Hang Su

The lack of interpretability and trust is a much-criticised feature of deep neural networks. In fully connected nets, the signalling between inner layers is scrambled because backpropagation training does not require perceptrons to be…

Signal Processing · Electrical Eng. & Systems 2021-01-28 Jake L. Amey , Jake Keeley , Tajwar Choudhury , Ilya Kuprov

Neural networks have emerged as powerful tools across various applications, yet their decision-making process often remains opaque, leading to them being perceived as "black boxes." This opacity raises concerns about their interpretability…

Machine Learning · Computer Science 2024-11-27 Pirzada Suhail , Amit Sethi

Network clustering requires making many decisions manually, such as the number of groups and a statistical model to be used. Even after filtering using an information criterion or regularizing with a nonparametric framework, we are commonly…

Social and Information Networks · Computer Science 2019-06-05 Chihiro Noguchi , Tatsuro Kawamoto

In this paper, we contend that a natural objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a low-dimensional Gaussian mixture supported on incoherent subspaces. The…

Machine Learning · Computer Science 2024-09-09 Yaodong Yu , Sam Buchanan , Druv Pai , Tianzhe Chu , Ziyang Wu , Shengbang Tong , Hao Bai , Yuexiang Zhai , Benjamin D. Haeffele , Yi Ma

Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Changbin Li , Kangshuo Li , Yuzhe Ou , Lance M. Kaplan , Audun Jøsang , Jin-Hee Cho , Dong Hyun Jeong , Feng Chen

Sum-Product Networks (SPNs) are recently introduced deep tractable probabilistic models by which several kinds of inference queries can be answered exactly and in a tractable time. Up to now, they have been largely used as black box density…

Machine Learning · Computer Science 2018-08-27 Antonio Vergari , Nicola Di Mauro , Floriana Esposito

We characterize a prevalent weakness of deep neural networks (DNNs)---overthinking---which occurs when a DNN can reach correct predictions before its final layer. Overthinking is computationally wasteful, and it can also be destructive…

Machine Learning · Computer Science 2019-05-10 Yigitcan Kaya , Sanghyun Hong , Tudor Dumitras

We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Neehar Kondapaneni , Markus Marks , Oisin Mac Aodha , Pietro Perona

While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…

Computer Vision and Pattern Recognition · Computer Science 2017-10-27 Zhi Zhang , Guanghan Ning , Zhihai He

Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have provided insights to understanding the generalizability in…

Machine Learning · Computer Science 2020-05-12 Jingling Li , Yanchao Sun , Jiahao Su , Taiji Suzuki , Furong Huang

Deep learning is a type of machine learning that adapts a deep hierarchy of concepts. Deep learning classifiers link the most basic version of concepts at the input layer to the most abstract version of concepts at the output layer, also…

Machine Learning · Computer Science 2021-07-20 Sara Hajj Ibrahim , Mohamed Nassar

Deep Convolutional Neural Networks (CNNs) have been one of the most influential recent developments in computer vision, particularly for categorization. There is an increasing demand for explainable AI as these systems are deployed in the…

Computer Vision and Pattern Recognition · Computer Science 2018-11-21 Tian Xu , Jiayu Zhan , Oliver G. B. Garrod , Philip H. S. Torr , Song-Chun Zhu , Robin A. A. Ince , Philippe G. Schyns

A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space. This approach assumes that the…

Machine Learning · Computer Science 2024-06-06 Dan Friedman , Andrew Lampinen , Lucas Dixon , Danqi Chen , Asma Ghandeharioun

It is well observed that in deep learning and computer vision literature, visual data are always represented in a manually designed coding scheme (eg., RGB images are represented as integers ranging from 0 to 255 for each channel) when they…

Machine Learning · Computer Science 2020-09-18 Xiang Deng , Zhongfei , Zhang

Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous way of adding supervision to the last layer of the network…

Computer Vision and Pattern Recognition · Computer Science 2019-06-05 Dawei Sun , Anbang Yao , Aojun Zhou , Hao Zhao

Supervised training of deep neural networks for classification typically relies on hard targets, which promote overconfidence and can limit calibration, generalization, and robustness. Self-distillation methods aim to mitigate this by…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Anton Adelöw , Matteo Gamba , Atsuto Maki

Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation literature remains…

Computer Vision and Pattern Recognition · Computer Science 2022-02-11 Shuxuan Guo , Jose M. Alvarez , Mathieu Salzmann

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