English
Related papers

Related papers: SAFR: Neuron Redistribution for Interpretability

200 papers

Training a unified multilingual model promotes knowledge transfer but inevitably introduces negative interference. Language-specific modeling methods show promise in reducing interference. However, they often rely on heuristics to…

Computation and Language · Computer Science 2024-04-18 Shaomu Tan , Di Wu , Christof Monz

As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity. One commonly used type of explainer is post hoc feature…

Machine Learning · Computer Science 2023-03-24 Avi Schwarzschild , Max Cembalest , Karthik Rao , Keegan Hines , John Dickerson

Compressed sensing MRI is a classic inverse problem in the field of computational imaging, accelerating the MR imaging by measuring less k-space data. The deep neural network models provide the stronger representation ability and faster…

Computer Vision and Pattern Recognition · Computer Science 2018-04-05 Zhiwen Fan , Liyan Sun , Xinghao Ding , Yue Huang , Congbo Cai , John Paisley

Implicit neural representations have recently been extended to represent convolutional neural network weights via neural representation for neural networks, offering promising parameter compression benefits. However, standard multi-layer…

Machine Learning · Computer Science 2025-09-10 Qihu Xie , Yuan Li , Yi Kang

Deep Recurrent Neural Networks (RNN) is increasingly used in decision-making with temporal sequences. However, understanding how RNN models produce final predictions remains a major challenge. Existing work on interpreting RNN models for…

Machine Learning · Computer Science 2020-08-25 Chuan Wang , Xumeng Wang , Kwan-Liu Ma

Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in NLP actually engage on time series data remains unexplored. The persistent…

Machine Learning · Computer Science 2026-05-07 Alper Yıldırım

Extrapolation -- the ability to make inferences that go beyond the scope of one's experiences -- is a hallmark of human intelligence. By contrast, the generalization exhibited by contemporary neural network algorithms is largely limited to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Taylor W. Webb , Zachary Dulberg , Steven M. Frankland , Alexander A. Petrov , Randall C. O'Reilly , Jonathan D. Cohen

In traditional software programs, it is easy to trace program logic from variables back to input, apply assertion statements to block erroneous behavior, and compose programs together. Although deep learning programs have demonstrated…

Machine Learning · Computer Science 2021-10-27 Mike Wu , Noah Goodman , Stefano Ermon

We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. To do so, researchers have created Deep Visualization techniques including activation maximization, which…

Neural and Evolutionary Computing · Computer Science 2016-05-10 Anh Nguyen , Jason Yosinski , Jeff Clune

Neural-symbolic learning, an intersection of neural networks and symbolic reasoning, aims to blend neural networks' learning capabilities with symbolic AI's interpretability and reasoning. This paper introduces an approach designed to…

Artificial Intelligence · Computer Science 2025-06-10 Fadi Al Machot

Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal…

Artificial Intelligence · Computer Science 2018-05-10 Vitalii Zhelezniak , Dan Busbridge , April Shen , Samuel L. Smith , Nils Y. Hammerla

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often…

Machine Learning · Computer Science 2026-04-09 Vivek Narayanaswamy , Kowshik Thopalli , Bhavya Kailkhura , Wesam Sakla

Deep neural networks (DNNs) demonstrate outstanding performance across most computer vision tasks. Some critical applications, such as autonomous driving or medical imaging, also require investigation into their behavior and the reasons…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly , Xavier Fischer

Reconstructing the high-fidelity surface from multi-view images, especially sparse images, is a critical and practical task that has attracted widespread attention in recent years. However, existing methods are impeded by the memory…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Rui Peng , Shihe Shen , Kaiqiang Xiong , Huachen Gao , Jianbo Jiao , Xiaodong Gu , Ronggang Wang

We frame the task of predicting a semantic labeling as a sparse reconstruction procedure that applies a target-specific learned transfer function to a generic deep sparse code representation of an image. This strategy partitions training…

Computer Vision and Pattern Recognition · Computer Science 2014-10-17 Michael Maire , Stella X. Yu , Pietro Perona

Deep learning based methods have recently pushed the state-of-the-art on the problem of Single Image Super-Resolution (SISR). In this work, we revisit the more traditional interpolation-based methods, that were popular before, now with the…

Computer Vision and Pattern Recognition · Computer Science 2017-12-19 Xu Jia , Hong Chang , Tinne Tuytelaars

Despite the recent success on image classification, self-training has only achieved limited gains on structured prediction tasks such as neural machine translation (NMT). This is mainly due to the compositionality of the target space, where…

Computation and Language · Computer Science 2020-12-08 Minkai Xu , Mingxuan Wang , Zhouhan Lin , Hao Zhou , Weinan Zhang , Lei Li

We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of…

Machine Learning · Computer Science 2019-06-18 Brian Cheung , Alex Terekhov , Yubei Chen , Pulkit Agrawal , Bruno Olshausen

Incorporating relational reasoning into neural networks has greatly expanded their capabilities and scope. One defining trait of relational reasoning is that it operates on a set of entities, as opposed to standard vector representations.…

Machine Learning · Computer Science 2020-06-18 Qian Huang , Horace He , Abhay Singh , Yan Zhang , Ser-Nam Lim , Austin Benson

In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be…

Computer Vision and Pattern Recognition · Computer Science 2019-03-08 Ronghang Hu , Jacob Andreas , Trevor Darrell , Kate Saenko
‹ Prev 1 4 5 6 7 8 10 Next ›