English
Related papers

Related papers: Estimating Information Flow in Deep Neural Network…

200 papers

In this paper, we provide an overview of a common phenomenon, condensation, observed during the nonlinear training of neural networks: During the nonlinear training of neural networks, neurons in the same layer tend to condense into groups…

Machine Learning · Computer Science 2026-04-14 Zhi-Qin John Xu , Yaoyu Zhang , Zhangchen Zhou

Recent research demonstrate that prediction of time series by predictive recurrent neural networks based on the noisy input generates a smooth anticipated trajectory. We examine influence of the noise component in both the training data…

Machine Learning · Computer Science 2023-05-02 Boris Rubinstein

Impulse response estimation in high noise and in-the-wild settings, with minimal control of the underlying data distributions, is a challenging problem. We propose a novel framework for parameterizing and estimating impulse responses based…

Sound · Computer Science 2022-02-08 Alexander Richard , Peter Dodds , Vamsi Krishna Ithapu

The ever-increasing parameter counts of deep learning models necessitate effective compression techniques for deployment on resource-constrained devices. This paper explores the application of information geometry, the study of…

Machine Learning · Computer Science 2025-07-15 Zakhar Shumaylov , Vasileios Tsiaras , Yannis Stylianou

Fully connected deep neural networks (DNN) often include redundant weights leading to overfitting and high memory requirements. Additionally, the performance of DNN is often challenged by traditional machine learning models in tabular data…

Machine Learning · Computer Science 2022-05-18 Manar Samad , Sakib Abrar

Despite their outstanding performance in a broad spectrum of real-world tasks, deep artificial neural networks are sensitive to input noises, particularly adversarial perturbations. On the contrary, human and animal brains are much less…

Neural and Evolutionary Computing · Computer Science 2022-05-23 Xiyuan Chen , Xingyu Li , Yi Zhou , Tianming Yang

Various forms of representations may arise in the many layers embedded in deep neural networks (DNNs). Of these, where can we find the most compact representation? We propose to use a pruning framework to answer this question: How compact…

Machine Learning · Computer Science 2019-01-10 Hyun-Joo Jung , Jaedeok Kim , Yoonsuck Choe

We study how neural networks compress uninformative input space in models where data lie in $d$ dimensions, but whose label only vary within a linear manifold of dimension $d_\parallel < d$. We show that for a one-hidden layer network…

Machine Learning · Computer Science 2021-05-07 Jonas Paccolat , Leonardo Petrini , Mario Geiger , Kevin Tyloo , Matthieu Wyart

The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited edge devices. To address this issue, abundant methods such as…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Muzhou Yu , Linfeng Zhang , Kaisheng Ma

The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning…

Machine Learning · Computer Science 2024-06-07 Daniel Becking , Maximilian Dreyer , Wojciech Samek , Karsten Müller , Sebastian Lapuschkin

The increasing computational requirements of deep neural networks (DNNs) have led to significant interest in obtaining DNN models that are sparse, yet accurate. Recent work has investigated the even harder case of sparse training, where the…

Machine Learning · Computer Science 2021-12-16 Alexandra Peste , Eugenia Iofinova , Adrian Vladu , Dan Alistarh

Deep neural networks (DNNs) exhibit an exceptional capacity for generalization in practical applications. This work aims to capture the effect and benefits of depth for supervised learning via information-theoretic generalization bounds. We…

Machine Learning · Computer Science 2025-05-09 Haiyun He , Ziv Goldfeld

In this paper, we interpret Deep Neural Networks with Complex Network Theory. Complex Network Theory (CNT) represents Deep Neural Networks (DNNs) as directed weighted graphs to study them as dynamical systems. We efficiently adapt CNT…

Machine Learning · Computer Science 2021-10-19 Emanuele La Malfa , Gabriele La Malfa , Giuseppe Nicosia , Vito Latora

Compressing deep neural network (DNN) models becomes a very important and necessary technique for real-world applications, such as deploying those models on mobile devices. Knowledge distillation is one of the most popular methods for model…

Machine Learning · Computer Science 2020-03-02 Makoto Takamoto , Yusuke Morishita , Hitoshi Imaoka

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are…

Computer Vision and Pattern Recognition · Computer Science 2019-04-23 Daiki Tanaka , Daiki Ikami , Toshihiko Yamasaki , Kiyoharu Aizawa

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial…

Machine Learning · Computer Science 2019-04-26 Shu Changyong , Li Peng , Xie Yuan , Qu Yanyun , Dai Longquan , Ma Lizhuang

Bidirectional language models have better context understanding and perform better than unidirectional models on natural language understanding tasks, yet the theoretical reasons behind this advantage remain unclear. In this work, we…

Computation and Language · Computer Science 2025-10-10 Md Kowsher , Nusrat Jahan Prottasha , Shiyun Xu , Shetu Mohanto , Ozlem Garibay , Niloofar Yousefi , Chen Chen

Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…

Machine Learning · Computer Science 2016-06-16 Zhenzhou Wu , Sunil Sivadas , Yong Kiam Tan , Ma Bin , Rick Siow Mong Goh

Classical Recurrent Neural Networks (RNNs) summarize musical context into a deterministic hidden state vector, imposing an information bottleneck that fails to capture the inherent ambiguity in music. We propose the Density Matrix RNN…

Machine Learning · Computer Science 2026-01-09 Joonwon Seo , Mariana Montiel

Understanding complex systems with their reduced model is one of the central roles in scientific activities. Although physics has greatly been developed with the physical insights of physicists, it is sometimes challenging to build a…

Data Analysis, Statistics and Probability · Physics 2021-03-24 Yoh-ichi Mototake
‹ Prev 1 8 9 10 Next ›