English
Related papers

Related papers: A technical note on bilinear layers for interpreta…

200 papers

One of the central questions in the theory of deep learning is to understand how neural networks learn hierarchical features. The ability of deep networks to extract salient features is crucial to both their outstanding generalization…

Machine Learning · Computer Science 2025-04-03 Eshaan Nichani , Alex Damian , Jason D. Lee

Multi-Layer Perceptrons (MLPs) make powerful functional representations for sampling and reconstruction problems involving low-dimensional signals like images,shapes and light fields. Recent works have significantly improved their ability…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Ishit Mehta , Michaël Gharbi , Connelly Barnes , Eli Shechtman , Ravi Ramamoorthi , Manmohan Chandraker

We study the use of binary activated neural networks as interpretable and explainable predictors in the context of regression tasks on tabular data; more specifically, we provide guarantees on their expressiveness, present an approach based…

Machine Learning · Computer Science 2024-06-11 Benjamin Leblanc , Pascal Germain

Today, it is more important than ever before for users to have trust in the models they use. As Machine Learning models fall under increased regulatory scrutiny and begin to see more applications in high-stakes situations, it becomes…

Machine Learning · Computer Science 2020-12-03 William Knauth

Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop…

Machine Learning · Computer Science 2019-11-19 Lawrence Phillips , Garrett Goh , Nathan Hodas

Understanding how information is represented in neural networks is a fundamental challenge in both neuroscience and artificial intelligence. Despite their nonlinear architectures, recent evidence suggests that neural networks encode…

Machine Learning · Computer Science 2025-03-04 David Klindt , Charles O'Neill , Patrik Reizinger , Harald Maurer , Nina Miolane

Layer normalization (LN) is a ubiquitous technique in deep learning but our theoretical understanding to it remains elusive. This paper investigates a new theoretical direction for LN, regarding to its nonlinearity and representation…

Machine Learning · Computer Science 2024-06-04 Yunhao Ni , Yuxin Guo , Junlong Jia , Lei Huang

Traditional neural networks have an impressive classification performance, but what they learn cannot be inspected, verified or extracted. Neural Logic Networks on the other hand have an interpretable structure that enables them to learn a…

Machine Learning · Computer Science 2026-01-26 Vincent Perreault , Katsumi Inoue , Richard Labib , Alain Hertz

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle…

Machine Learning · Computer Science 2019-01-24 Quanshi Zhang , Yu Yang , Ying Nian Wu

In this paper, we described and developed a framework for Multilayer Perceptron (MLP) to work on low level image processing, where MLP will be used to perform image super-resolution. Meanwhile, MLP are trained with different types of images…

Computer Vision and Pattern Recognition · Computer Science 2012-12-24 Kah Keong Chua , Yong Haur Tay

Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems, e.g., image classification, natural language processing or human action recognition. Although these methods…

Machine Learning · Computer Science 2017-11-15 Grégoire Montavon , Sebastian Bach , Alexander Binder , Wojciech Samek , Klaus-Robert Müller

In recent years, many interpretability methods have been proposed to help interpret the internal states of Transformer-models, at different levels of precision and complexity. Here, to analyze encoder-decoder Transformers, we propose a…

Computation and Language · Computer Science 2024-04-04 Anna Langedijk , Hosein Mohebbi , Gabriele Sarti , Willem Zuidema , Jaap Jumelet

Implicit Neural Representations (INRs) have emerged as a paradigm in knowledge representation, offering exceptional flexibility and performance across a diverse range of applications. INRs leverage multilayer perceptrons (MLPs) to model…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Amer Essakine , Yanqi Cheng , Chun-Wun Cheng , Lipei Zhang , Zhongying Deng , Lei Zhu , Carola-Bibiane Schönlieb , Angelica I Aviles-Rivero

The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have emerged about the…

Computation and Language · Computer Science 2019-09-26 Shikhar Vashishth , Shyam Upadhyay , Gaurav Singh Tomar , Manaal Faruqui

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a principled notion of interpretability to formally compare…

Artificial Intelligence · Computer Science 2020-11-16 Pablo Barceló , Mikaël Monet , Jorge Pérez , Bernardo Subercaseaux

The approximation capability of ANNs and their RNN instantiations, is strongly correlated with the number of parameters packed into these networks. However, the complexity barrier for human understanding, is arguably related to the number…

Neural and Evolutionary Computing · Computer Science 2023-03-10 Julian Lemmel , Radu Grosu

We introduce combinatorial interpretability, a methodology for understanding neural computation by analyzing the combinatorial structures in the sign-based categorization of a network's weights and biases. We demonstrate its power through…

Machine Learning · Computer Science 2025-05-07 Micah Adler , Dan Alistarh , Nir Shavit

Convolutional networks are large linear systems divided into layers and connected by non-linear units. These units are the "articulations" that allow the network to adapt to the input. To understand how a network manages to solve a problem…

Computer Vision and Pattern Recognition · Computer Science 2019-11-15 Pablo Navarrete Michelini , Hanwen Liu , Yunhua Lu , Xingqun Jiang

Mechanistic Interpretability aims to reverse engineer the algorithms implemented by neural networks by studying their weights and activations. An obstacle to reverse engineering neural networks is that many of the parameters inside a…

In deep learning, Multi-Layer Perceptrons (MLPs) have once again garnered attention from researchers. This paper introduces MC-MLP, a general MLP-like backbone for computer vision that is composed of a series of fully-connected (FC) layers.…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Zhimin Zhu , Jianguo Zhao , Tong Mu , Yuliang Yang , Mengyu Zhu
‹ Prev 1 3 4 5 6 7 10 Next ›