English
Related papers

Related papers: CoFrNets: Interpretable Neural Architecture Inspir…

200 papers

Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new function class for generative modeling. The architecture family implementing this function…

Computation and Language · Computer Science 2026-05-25 Amit Dhurandhar , Vijil Chenthamarakshan , Dennis Wei , Tejaswini Pedapati , Karthikeyan Natesan Ramamurthy , Rahul Nair

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

In human perception and cognition, a fundamental operation that brains perform is interpretation: constructing coherent neural states from noisy, incomplete, and intrinsically ambiguous evidence. The problem of interpretation is well…

Machine Learning · Computer Science 2019-09-30 Michael Iuzzolino , Yoram Singer , Michael C. Mozer

Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution. However, they are less capable of systematic generalization to data drawn from unseen but related distributions, a…

Neural networks are powerful function estimators, leading to their status as a paradigm of choice for modeling structured data. However, unlike other structured representations that emphasize the modularity of the problem -- e.g., factor…

Machine Learning · Computer Science 2022-06-20 Tsvetomila Mihaylova , Vlad Niculae , André F. T. Martins

We study the approximation properties of convolutional architectures applied to time series modelling, which can be formulated mathematically as a functional approximation problem. In the recurrent setting, recent results reveal an…

Machine Learning · Computer Science 2021-07-21 Haotian Jiang , Zhong Li , Qianxiao Li

This paper proposes FractalNet, a framework based on fractal design principles that automatically generates and evaluates convolutional neural network (CNN) architectures using recursive template patterns. Rather than relying on…

Machine Learning · Computer Science 2026-05-19 Yash Mittal , Dmitry Ignatov , Radu Timofte

The remarkable performance of convolutional neural networks (CNNs) is entangled with their huge number of uninterpretable parameters, which has become the bottleneck limiting the exploitation of their full potential. Towards network…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Yuchao Li , Rongrong Ji , Shaohui Lin , Baochang Zhang , Chenqian Yan , Yongjian Wu , Feiyue Huang , Ling Shao

Understanding neural networks is challenging in part because of the dense, continuous nature of their hidden states. We explore whether we can train neural networks to have hidden states that are sparse, discrete, and more interpretable by…

Machine Learning · Computer Science 2023-10-27 Alex Tamkin , Mohammad Taufeeque , Noah D. Goodman

Invertible neural networks (INNs) are neural network architectures with invertibility by design. Thanks to their invertibility and the tractability of Jacobian, INNs have various machine learning applications such as probabilistic modeling,…

Machine Learning · Computer Science 2022-04-18 Isao Ishikawa , Takeshi Teshima , Koichi Tojo , Kenta Oono , Masahiro Ikeda , Masashi Sugiyama

We propose ProtoArgNet, a novel interpretable deep neural architecture for image classification in the spirit of prototypical-part-learning as found, e.g., in ProtoPNet. While earlier approaches associate every class with multiple…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Hamed Ayoobi , Nico Potyka , Francesca Toni

Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides…

Machine Learning · Computer Science 2025-11-21 Yang Ji , Ying Sun , Yuting Zhang , Zhigaoyuan Wang , Yuanxin Zhuang , Zheng Gong , Dazhong Shen , Chuan Qin , Hengshu Zhu , Hui Xiong

We introduce CQnet, a neural network with origins in the CQ algorithm for solving convex split-feasibility problems and forward-backward splitting. CQnet's trajectories are interpretable as particles that are tracking a changing constraint…

Machine Learning · Computer Science 2023-02-23 Bas Peters

Artificial Neural Networks are computational network models inspired by signal processing in the brain. These models have dramatically improved the performance of many learning tasks, including speech and object recognition. However,…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Machine Learning · Computer Science 2019-10-08 Yulong Wang , Xiaolin Hu , Hang Su

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these…

Machine Learning · Computer Science 2018-11-16 Raghuram Mandyam Annasamy , Katia Sycara

State-of-the-art deep reading comprehension models are dominated by recurrent neural nets. Their sequential nature is a natural fit for language, but it also precludes parallelization within an instances and often becomes the bottleneck for…

Computation and Language · Computer Science 2017-11-15 Felix Wu , Ni Lao , John Blitzer , Guandao Yang , Kilian Weinberger

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel…

Machine Learning · Computer Science 2025-02-20 Antoine Ledent , Peng Liu

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a…

Machine Learning · Computer Science 2023-05-09 Jędrzej Kozal , Michał Woźniak

Leveraging the infinite dimensional neural network architecture we proposed in arXiv:2109.13512v4 and which can process inputs from Fr\'echet spaces, and using the universal approximation property shown therein, we now largely extend the…

Functional Analysis · Mathematics 2024-06-14 Luca Galimberti
‹ Prev 1 2 3 10 Next ›