English
Related papers

Related papers: The Linear Centroids Hypothesis: Features as Direc…

200 papers

The Linear Representation Hypothesis (LRH) states that neural networks learn to encode concepts as directions in activation space, and a strong version of the LRH states that models learn only such encodings. In this paper, we present a…

Machine Learning · Computer Science 2024-08-21 Róbert Csordás , Christopher Potts , Christopher D. Manning , Atticus Geiger

Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this…

Machine Learning · Computer Science 2025-11-17 Peng Wang , Xiao Li , Can Yaras , Zhihui Zhu , Laura Balzano , Wei Hu , Qing Qu

Deep neural networks for image classification typically consists of a convolutional feature extractor followed by a fully connected classifier network. The predicted and the ground truth labels are represented as one hot vectors. Such a…

Computer Vision and Pattern Recognition · Computer Science 2018-08-22 Soham Saha , Girish Varma , C. V. Jawahar

Convolutional neural networks (CNNs) learn abstract features to perform object classification, but understanding these features remains challenging due to difficult-to-interpret results or high computational costs. We propose an automatic…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Maren H. Wehrheim , Pamela Osuna-Vargas , Matthias Kaschube

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the…

Machine Learning · Computer Science 2020-04-30 Xiao Zhang , Dongrui Wu

Our proposed framework attempts to break the trade-off between performance and explainability by introducing an explainable-by-design convolutional neural network (CNN) based on the lateral inhibition mechanism. The ExplaiNet model consists…

Machine Learning · Computer Science 2024-11-04 Pantelis I. Kaplanoglou , Konstantinos Diamantaras

Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures and structures. In this paper we establish some analysis for…

Machine Learning · Computer Science 2024-01-03 Jianfei Li , Han Feng , Ding-Xuan Zhou

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

We introduce Deep Linear Discriminant Analysis (DeepLDA) which learns linearly separable latent representations in an end-to-end fashion. Classic LDA extracts features which preserve class separability and is used for dimensionality…

Machine Learning · Computer Science 2016-02-18 Matthias Dorfer , Rainer Kelz , Gerhard Widmer

We introduce a mathematical framework for the linear representation hypothesis (LRH), which asserts that intermediate layers of language models store features linearly. We separate the hypothesis into two claims: linear representation…

Machine Learning · Computer Science 2026-02-13 Nikhil Garg , Jon Kleinberg , Kenny Peng

It has been hypothesized that neural networks with similar architectures trained on similar data learn shared representations relevant to the learning task. We build on this idea by extending the conceptual framework where representations…

Machine Learning · Computer Science 2025-06-06 Femi Bello , Anubrata Das , Fanzhi Zeng , Fangcong Yin , Liu Leqi

While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics.…

Computer Vision and Pattern Recognition · Computer Science 2018-05-29 Mengnan Du , Ninghao Liu , Qingquan Song , Xia Hu

Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully-connected layer of the CNN (FC-features) exhibit rich…

Computer Vision and Pattern Recognition · Computer Science 2017-04-05 Sheng Guo , Weilin Huang , Limin Wang , Yu Qiao

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within…

Neural and Evolutionary Computing · Computer Science 2018-01-30 Dario Garcia-Gasulla , Ferran Parés , Armand Vilalta , Jonatan Moreno , Eduard Ayguadé , Jesús Labarta , Ulises Cortés , Toyotaro Suzumura

The task of lane detection has garnered considerable attention in the field of autonomous driving due to its complexity. Lanes can present difficulties for detection, as they can be narrow, fragmented, and often obscured by heavy traffic.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-10 Jia-Qi Zhang , Hao-Bin Duan , Jun-Long Chen , Ariel Shamir , Miao Wang

Deep Learning (DL) has attracted a lot of attention for its ability to reach state-of-the-art performance in many machine learning tasks. The core principle of DL methods consists in training composite architectures in an end-to-end…

Machine Learning · Computer Science 2020-11-17 Carlos Lassance , Vincent Gripon , Antonio Ortega

High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circuits to structured semantic directions that align with human-interpretable concepts. While…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Bowei Tian , Xuntao Lyu , Meng Liu , Hongyi Wang , Ang Li

Classical work on line segment detection is knowledge-based; it uses carefully designed geometric priors using either image gradients, pixel groupings, or Hough transform variants. Instead, current deep learning methods do away with all…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Yancong Lin , Silvia L. Pintea , Jan C. van Gemert

It is well established that training deep neural networks gives useful representations that capture essential features of the inputs. However, these representations are poorly understood in theory and practice. In the context of supervised…

Machine Learning · Computer Science 2021-03-12 Nishanth Dikkala , Gal Kaplun , Rina Panigrahy
‹ Prev 1 2 3 10 Next ›