English
Related papers

Related papers: How Important Is a Neuron?

200 papers

Linear classifier probes are frequently utilized to better understand how neural networks function. Researchers have approached the problem of determining unit importance in neural networks by probing their learned, internal…

Machine Learning · Computer Science 2022-11-09 Lucas Hayne , Abhijit Suresh , Hunar Jain , Rahul Kumar , R. McKell Carter

Detecting when a neural sequence model does "interesting" computation is an open problem. The next token prediction loss is a poor indicator: Low loss can stem from trivially predictable sequences that are uninteresting, while high loss may…

Machine Learning · Computer Science 2025-03-18 Vincent Herrmann , Róbert Csordás , Jürgen Schmidhuber

Theoretical and empirical evidence indicates that the depth of neural networks is crucial for their success. However, training becomes more difficult as depth increases, and training of very deep networks remains an open problem. Here we…

Machine Learning · Computer Science 2015-11-24 Rupesh Kumar Srivastava , Klaus Greff , Jürgen Schmidhuber

Deep learning has arguably achieved tremendous success in recent years. In simple words, deep learning uses the composition of many nonlinear functions to model the complex dependency between input features and labels. While neural networks…

Machine Learning · Statistics 2019-04-16 Jianqing Fan , Cong Ma , Yiqiao Zhong

One of the most effective methods of channel pruning is to trim on the basis of the importance of each neuron. However, measuring the importance of each neuron is an NP-hard problem. Previous works have proposed to trim by considering the…

Machine Learning · Computer Science 2021-12-07 Bilan Lai , Haoran Xiang , Furao Shen

We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (word importance), we find that these deep networks often…

Computation and Language · Computer Science 2018-05-16 Pramod Kaushik Mudrakarta , Ankur Taly , Mukund Sundararajan , Kedar Dhamdhere

Multilayer networks have seen a resurgence under the umbrella of deep learning. Current deep learning algorithms train the layers of the network sequentially, improving algorithmic performance as well as providing some regularization. We…

Machine Learning · Computer Science 2016-02-22 Ke Wu , Malik Magdon-Ismail

Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute test-time predictions either to input features (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Aziz Bacha , Thomas George

Although deep learning models perform remarkably well across a range of tasks such as language translation and object recognition, it remains unclear what high-level logic, if any, they follow. Understanding this logic may lead to more…

Databases · Computer Science 2019-01-08 Thibault Sellam , Kevin Lin , Ian Yiran Huang , Yiru Chen , Michelle Yang , Carl Vondrick , Eugene Wu

Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information…

Machine Learning · Computer Science 2025-07-22 Yiding Song

Deep neural networks use multiple layers of functions to map an object represented by an input vector progressively to different representations, and with sufficient training, eventually to a single score for each class that is the output…

Machine Learning · Computer Science 2022-09-02 Tin Kam Ho

Recent work has shown that deep neural networks are highly sensitive to tiny perturbations of input images, giving rise to adversarial examples. Though this property is usually considered a weakness of learned models, we explore whether it…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Jiren Zhu , Russell Kaplan , Justin Johnson , Li Fei-Fei

We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation…

Machine Learning · Computer Science 2018-11-27 Chih-Kuan Yeh , Joon Sik Kim , Ian E. H. Yen , Pradeep Ravikumar

Convolutional neural networks (CNNs) in recent years have made a dramatic impact in science, technology and industry, yet the theoretical mechanism of CNN architecture design remains surprisingly vague. The CNN neurons, including its…

Machine Learning · Computer Science 2019-07-16 Kamil Adamczewski , Mijung Park

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Computer Vision and Pattern Recognition · Computer Science 2017-03-31 Yinpeng Dong , Hang Su , Jun Zhu , Bo Zhang

It is commonly believed that the hidden layers of deep neural networks (DNNs) attempt to extract informative features for learning tasks. In this paper, we formalize this intuition by showing that the features extracted by DNN coincide with…

Information Theory · Computer Science 2019-05-17 Shao-Lun Huang , Xiangxiang Xu , Lizhong Zheng , Gregory W. Wornell

Systematic relations between multiple objects that occur in various fields can be represented as networks. Real-world networks typically exhibit complex topologies whose structural properties are key factors in characterizing and further…

Physics and Society · Physics 2021-04-09 Yoshihisa Tanaka , Ryosuke Kojima , Shoichi Ishida , Fumiyoshi Yamashita , Yasushi Okuno

Deep neural networks are a key component of behavior prediction and motion generation for self-driving cars. One of their main drawbacks is a lack of transparency: they should provide easy to interpret rationales for what triggers certain…

Computer Vision and Pattern Recognition · Computer Science 2020-05-12 Jinkyu Kim , Mayank Bansal

The \emph{receptive fields} of deep learning classification models determine the regions of the input data that have the most significance for providing correct decisions. The primary way to learn such receptive fields is to train the…

Machine Learning · Computer Science 2020-07-06 Ehsan Yaghoubi , Diana Borza , Aruna Kumar , Hugo Proença

Deep learning has achieved impressive prediction accuracies in a variety of scientific and industrial domains. However, the nested non-linear feature of deep learning makes the learning highly non-transparent, i.e., it is still unknown how…

Machine Learning · Computer Science 2020-10-26 Chan Li , Haiping Huang