English
Related papers

Related papers: Understanding intermediate layers using linear cla…

200 papers

Despite strong empirical performance for image classification, deep neural networks are often regarded as ``black boxes'' and they are difficult to interpret. On the other hand, sparse convolutional models, which assume that a signal can be…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Xili Dai , Mingyang Li , Pengyuan Zhai , Shengbang Tong , Xingjian Gao , Shao-Lun Huang , Zhihui Zhu , Chong You , Yi Ma

In recent years we see a rapidly growing line of research which shows learnability of various models via common neural network algorithms. Yet, besides a very few outliers, these results show learnability of models that can be learned using…

Machine Learning · Computer Science 2020-07-06 Amit Daniely , Eran Malach

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 2024-11-28 Pirzada Suhail , Hao Tang , Amit Sethi

Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the hard no-margin regime and make the computation identifiable…

Machine Learning · Computer Science 2026-04-20 Patrick Lutz , Themistoklis Haris , Arjun Chandra , Aditya Gangrade , Venkatesh Saligrama

We propose a probe for the analysis of deep learning architectures that is based on machine learning and approximation theoretical principles. Given a deep learning architecture and a training set, during or after training, the Sparsity…

Machine Learning · Computer Science 2021-05-17 Ido Ben-Shaul , Shai Dekel

One of the pursued objectives of deep learning is to provide tools that learn abstract representations of reality from the observation of multiple contextual situations. More precisely, one wishes to extract disentangled representations…

Machine Learning · Computer Science 2023-10-24 Pierre Colombo , Nathan Noiry , Guillaume Staerman , Pablo Piantanida

In recent years, deep neural networks (DNNs) have known an important rise in popularity. However, although they are state-of-the-art in many machine learning challenges, they still suffer from several limitations. For example, DNNs require…

Machine Learning · Computer Science 2021-10-11 Carlos Lassance , Myriam Bontonou , Mounia Hamidouche , Bastien Pasdeloup , Lucas Drumetz , Vincent Gripon

This work introduces the notion of intermediate concepts based on levels structure to aid explainability for black-box models. The levels structure is a hierarchical structure in which each level corresponds to features of a dataset (i.e.,…

Machine Learning · Computer Science 2023-06-05 Minal Suresh Patil , Kary Främling

With the substantial performance of neural networks in sensitive fields increases the need for interpretable deep learning models. Major challenge is to uncover the multiscale and distributed representation hidden inside the basket mappings…

Computer Vision and Pattern Recognition · Computer Science 2022-11-10 Piduguralla Manaswini , Jignesh S. Bhatt

Recent data-driven approaches to scene interpretation predominantly pose inference as an end-to-end black-box mapping, commonly performed by a Convolutional Neural Network (CNN). However, decades of work on perceptual organization in both…

Computer Vision and Pattern Recognition · Computer Science 2018-07-23 Chi Li , M. Zeeshan Zia , Quoc-Huy Tran , Xiang Yu , Gregory D. Hager , Manmohan Chandraker

Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployment. In this paper, we propose a framework to analyse and…

Machine Learning · Computer Science 2026-05-21 Divij Khaitan , Subhashis Banerjee

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…

Machine Learning · Computer Science 2024-03-19 Yihao Xue , Eric Gan , Jiayi Ni , Siddharth Joshi , Baharan Mirzasoleiman

The empirical success of deep learning is often attributed to deep networks' ability to exploit hierarchical structure in data, constructing increasingly complex features across layers. Yet despite substantial progress in deep learning…

Machine Learning · Computer Science 2026-01-28 Yunwei Ren , Yatin Dandi , Florent Krzakala , Jason D. Lee

Deep neural networks can empirically perform efficient hierarchical learning, in which the layers learn useful representations of the data. However, how they make use of the intermediate representations are not explained by recent theories…

Machine Learning · Computer Science 2021-03-08 Minshuo Chen , Yu Bai , Jason D. Lee , Tuo Zhao , Huan Wang , Caiming Xiong , Richard Socher

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Paul Gavrikov , Janis Keuper

The task of quantifying the inherent uncertainty associated with neural network predictions is a key challenge in artificial intelligence. Bayesian neural networks (BNNs) and deep ensembles are among the most prominent approaches to tackle…

Machine Learning · Computer Science 2025-05-23 Valentin Villecroze , Yixin Wang , Gabriel Loaiza-Ganem

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high…

Machine Learning · Computer Science 2020-06-09 Murat Sensoy , Lance Kaplan , Federico Cerutti , Maryam Saleki

In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand…

Machine Learning · Computer Science 2026-03-06 Difan Jiao , Di Wang , Lijie Hu

Large NLP models have recently shown impressive performance in language understanding tasks, typically evaluated by their fine-tuned performance. Alternatively, probing has received increasing attention as being a lightweight method for…

Computation and Language · Computer Science 2022-10-17 Zining Zhu , Soroosh Shahtalebi , Frank Rudzicz

The deep neural networks (DNNs) have achieved great success in learning complex patterns with strong predictive power, but they are often thought of as "black box" models without a sufficient level of transparency and interpretability. It…

Machine Learning · Computer Science 2020-11-10 Agus Sudjianto , William Knauth , Rahul Singh , Zebin Yang , Aijun Zhang