English
Related papers

Related papers: Dual Skipping Networks

200 papers

Heuristic tools from statistical physics have been used in the past to locate the phase transitions and compute the optimal learning and generalization errors in the teacher-student scenario in multi-layer neural networks. In this…

Machine Learning · Computer Science 2024-03-01 Benjamin Aubin , Antoine Maillard , Jean Barbier , Florent Krzakala , Nicolas Macris , Lenka Zdeborová

Dynamic DNN optimization techniques such as layer-skipping offer increased adaptability and efficiency gains but can lead to i) a larger memory footprint as in decision gates, ii) increased training complexity (e.g., with non-differentiable…

Machine Learning · Computer Science 2025-05-26 Guilherme Korol , Antonio Carlos Schneider Beck , Jeronimo Castrillon

In recent years, deep neural networks have achieved high ac-curacy in the field of image recognition. By inspired from human learning method, we propose a semantic segmentation method using cooperative learning which shares the information…

Computer Vision and Pattern Recognition · Computer Science 2021-01-21 Ryota Ikedo , Kazuhiro Hotta

We propose that learning in deep neural networks proceeds in two phases: a rapid curve fitting phase followed by a slower compression or coarse graining phase. This view is supported by the shared temporal structure of three phenomena:…

High Energy Physics - Theory · Physics 2025-07-28 Robert de Mello Koch , Animik Ghosh

In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned…

Machine Learning · Computer Science 2019-12-09 René Larisch , Michael Teichmann , Fred H. Hamker

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples…

Computer Vision and Pattern Recognition · Computer Science 2016-07-20 Xiaojie Jin , Yunpeng Chen , Jian Dong , Jiashi Feng , Shuicheng Yan

This paper introduces Neural Subdivision, a novel framework for data-driven coarse-to-fine geometry modeling. During inference, our method takes a coarse triangle mesh as input and recursively subdivides it to a finer geometry by applying…

Graphics · Computer Science 2020-05-06 Hsueh-Ti Derek Liu , Vladimir G. Kim , Siddhartha Chaudhuri , Noam Aigerman , Alec Jacobson

For high-dimensional Gaussian data, we investigate theoretically how the features of a two-layer neural network adapt to the structure of the target function through a few large batch gradient descent steps, leading to an improvement in the…

Machine Learning · Statistics 2025-06-05 Yatin Dandi , Florent Krzakala , Bruno Loureiro , Luca Pesce , Ludovic Stephan

The brains of all bilaterally symmetric animals on Earth are divided into left and right hemispheres. The anatomy and functionality of the hemispheres have a large degree of overlap, but there are asymmetries, and they specialise in…

Neurons and Cognition · Quantitative Biology 2024-07-11 Chandramouli Rajagopalan , David Rawlinson , Elkhonon Goldberg , Gideon Kowadlo

We present a loss function for neural networks that encompasses an idea of trivial versus non-trivial predictions, such that the network jointly determines its own prediction goals and learns to satisfy them. This permits the network to…

Artificial Intelligence · Computer Science 2016-12-15 Nicholas Guttenberg , Martin Biehl , Ryota Kanai

The recent success of generative adversarial networks and variational learning suggests training a classifier network may work well in addressing the classical two-sample problem. Network-based tests have the computational advantage that…

Machine Learning · Statistics 2022-06-01 Xiuyuan Cheng , Alexander Cloninger

A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable…

Computer Vision and Pattern Recognition · Computer Science 2016-10-05 Shaoli Huang , Dacheng Tao

We describe how hierarchical concepts can be represented in three types of layered neural networks. The aim is to support recognition of the concepts when partial information about the concepts is presented, and also when some of the…

Neural and Evolutionary Computing · Computer Science 2025-03-25 Nancy A. Lynch

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing…

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical…

Machine Learning · Computer Science 2024-06-28 Konstantinos P. Panousis , Dino Ienco , Diego Marcos

Spike-based neuromorphic hardware promises to reduce the energy consumption of image classification and other deep learning applications, particularly on mobile phones or other edge devices. However, direct training of deep spiking neural…

Neural and Evolutionary Computing · Computer Science 2021-01-27 Christoph Stöckl , Wolfgang Maass

In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…

Machine Learning · Computer Science 2021-11-16 Cheng-Chou Lan

Double machine learning is a statistical method for leveraging complex black-box models to construct approximately unbiased treatment effect estimates given observational data with high-dimensional covariates, under the assumption of a…

Machine Learning · Statistics 2022-06-03 Nitai Fingerhut , Matteo Sesia , Yaniv Romano

The training of machine learning models is typically carried out using some form of gradient descent, often with great success. However, non-asymptotic analyses of first-order optimization algorithms typically employ a gradient smoothness…

Machine Learning · Computer Science 2024-06-18 Thomas Flynn