中文
相关论文

相关论文: Multi-Objective Linear Ensembles for Robust and Sp…

200 篇论文

Big neural networks trained on large datasets have advanced the state-of-the-art for a large variety of challenging problems, improving performance by a large margin. However, under low memory and limited computational power constraints,…

计算机视觉与模式识别 · 计算机科学 2019-04-12 Adrian Bulat , Georgios Tzimiropoulos , Jean Kossaifi , Maja Pantic

While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to…

计算机视觉与模式识别 · 计算机科学 2021-02-18 Corey Lammie , Wei Xiang , Mostafa Rahimi Azghadi

Binary Neural Networks (BNNs) are showing tremendous success on realistic image classification tasks. Notably, their accuracy is similar to the state-of-the-art accuracy obtained by full-precision models tailored to edge devices. In this…

硬件体系结构 · 计算机科学 2022-12-02 Franyell Silfa , Jose Maria Arnau , Antonio González

Machine learning is increasingly used to improve decisions within branch-and-bound algorithms for mixed-integer programming. Many existing approaches rely on deep learning, which often requires very large training datasets and substantial…

机器学习 · 计算机科学 2026-04-02 Selin Bayramoğlu , George L Nemhauser , Nikolaos V Sahinidis

Multi-bit quantization networks enable flexible deployment of deep neural networks by supporting multiple precision levels within a single model. However, existing approaches suffer from significant training overhead as full-dataset updates…

计算机视觉与模式识别 · 计算机科学 2025-10-24 Jinhee Kim , Jae Jun An , Kang Eun Jeon , Jong Hwan Ko

Ensemble Learning is an effective method for improving generalization in machine learning. However, as state-of-the-art neural networks grow larger, the computational cost associated with training several independent networks becomes…

机器学习 · 计算机科学 2022-03-28 Tim Whitaker , Darrell Whitley

Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled…

神经与进化计算 · 计算机科学 2016-11-22 Sebastian Vogel , Christoph Schorn , Andre Guntoro , Gerd Ascheid

We report that a very high accuracy on the MNIST test set can be achieved by using simple convolutional neural network (CNN) models. We use three different models with 3x3, 5x5, and 7x7 kernel size in the convolution layers. Each model…

计算机视觉与模式识别 · 计算机科学 2020-10-06 Sanghyeon An , Minjun Lee , Sanglee Park , Heerin Yang , Jungmin So

Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning. However, they generally struggle with underfitting at scale and parameter efficiency. On the…

Recent ensemble learning methods for image classification have been shown to improve classification accuracy with low extra cost. However, they still require multiple trained models for ensemble inference, which eventually becomes a…

计算机视觉与模式识别 · 计算机科学 2025-01-30 Hojung Lee , Jong-Seok Lee

Given a {features, target} dataset, we introduce an incremental algorithm that constructs an aggregate regressor, using an ensemble of neural networks. It is well known that ensemble methods suffer from the multicollinearity issue, which is…

机器学习 · 计算机科学 2021-05-03 Pola Lydia Lagari , Lefteri H. Tsoukalas , Salar Safarkhani , Isaac E. Lagaris

Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices…

机器学习 · 计算机科学 2020-03-25 Joseph Bethge , Christian Bartz , Haojin Yang , Ying Chen , Christoph Meinel

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

机器学习 · 计算机科学 2026-05-28 Mohammed Adnan , Rohan Jain , Tom Jacobs , Ekansh Sharma , Rahul G. Krishnan , Rebekka Burkholz , Yani Ioannou

The development of neural networks has greatly improved the performance in various computer vision tasks. In the filed of image denoising, convolutional neural network based methods such as DnCNN break through the limits of classical…

图像与视频处理 · 电气工程与系统科学 2021-01-26 Xiaoqi Ma

Binary Neural Networks (BNNs) have emerged as a promising solution for reducing the memory footprint and compute costs of deep neural networks, but they suffer from quality degradation due to the lack of freedom as activations and weights…

计算机视觉与模式识别 · 计算机科学 2023-10-20 Changhun Lee , Hyungjun Kim , Eunhyeok Park , Jae-Joon Kim

Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized NNs can easily overfit to such small dataset. Previous work…

机器学习 · 计算机科学 2023-02-10 Daiki Chijiwa , Shin'ya Yamaguchi , Atsutoshi Kumagai , Yasutoshi Ida

This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations. Optimizing a low-precision network is very challenging since the training process can easily get…

计算机视觉与模式识别 · 计算机科学 2021-06-05 Bohan Zhuang , Chunhua Shen , Mingkui Tan , Lingqiao Liu , Ian Reid

Ensemble learning is a process by which multiple base learners are strategically generated and combined into one composite learner. There are two features that are essential to an ensemble's performance, the individual accuracies of the…

机器学习 · 计算机科学 2021-09-30 Wenjing Li , Randy C. Paffenroth , David Berthiaume

A key enabler of deploying convolutional neural networks on resource-constrained embedded systems is the binary neural network (BNN). BNNs save on memory and simplify computation by binarizing both features and weights. Unfortunately,…

机器学习 · 计算机科学 2023-10-19 Floran de Putter , Henk Corporaal

Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically…

计算机视觉与模式识别 · 计算机科学 2019-02-22 Kashyap Chitta , Jose M. Alvarez , Adam Lesnikowski