English
Related papers

Related papers: Learning to Compose SuperWeights for Neural Parame…

200 papers

In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the…

Machine Learning · Computer Science 2024-07-02 Hongjun Choi , Jayaraman J. Thiagarajan , Ruben Glatt , Shusen Liu

Convolutional Neural Networks have been used in a variety of image related applications after their rise in popularity due to ImageNet competition. Convolutional Neural Networks have shown remarkable results in applications including face…

Machine Learning · Computer Science 2023-01-18 Anshumaan Chauhan , Siddhartha Bhattacharyya , S. Vadivel

The recent progress of deep convolutional neural networks has enabled great success in single image super-resolution (SISR) and many other vision tasks. Their performances are also being increased by deepening the networks and developing…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Joon Young Ahn , Nam Ik Cho

Network pruning reduces the computation costs of an over-parameterized network without performance damage. Prevailing pruning algorithms pre-define the width and depth of the pruned networks, and then transfer parameters from the unpruned…

Computer Vision and Pattern Recognition · Computer Science 2019-10-17 Xuanyi Dong , Yi Yang

Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when…

In this paper, we propose the differentiable channel sparsity search (DCSS) for convolutional neural networks. Unlike traditional channel pruning algorithms which require users to manually set prune ratios for each convolutional layer, DCSS…

Computer Vision and Pattern Recognition · Computer Science 2022-01-06 Yu Zhao , Chung-Kuei Lee

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge, this paper…

Computer Vision and Pattern Recognition · Computer Science 2021-05-10 Mohammed F. Tolba , Huruy Tekle Tesfai , Hani Saleh , Baker Mohammad , Mahmoud Al-Qutayri

Recent work in network quantization has substantially reduced the time and space complexity of neural network inference, enabling their deployment on embedded and mobile devices with limited computational and memory resources. However,…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 Bichen Wu , Yanghan Wang , Peizhao Zhang , Yuandong Tian , Peter Vajda , Kurt Keutzer

We introduce a parameter sharing scheme, in which different layers of a convolutional neural network (CNN) are defined by a learned linear combination of parameter tensors from a global bank of templates. Restricting the number of templates…

Machine Learning · Computer Science 2019-03-15 Pedro Savarese , Michael Maire

Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between agents significantly decreases the number of trainable…

Multiagent Systems · Computer Science 2021-06-15 Filippos Christianos , Georgios Papoudakis , Arrasy Rahman , Stefano V. Albrecht

One-Shot Neural architecture search (NAS) attracts broad attention recently due to its capacity to reduce the computational hours through weight sharing. However, extensive experiments on several recent works show that there is no positive…

Machine Learning · Computer Science 2019-07-23 Miao Zhang , Huiqi Li , Shirui Pan , Taoping Liu , Steven Su

A practical limitation of deep neural networks is their high degree of specialization to a single task and visual domain. Recently, inspired by the successes of transfer learning, several authors have proposed to learn instead universal,…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Sylvestre-Alvise Rebuffi , Hakan Bilen , Andrea Vedaldi

We propose a new algorithm to learn a one-hidden-layer convolutional neural network where both the convolutional weights and the outputs weights are parameters to be learned. Our algorithm works for a general class of (potentially…

Machine Learning · Computer Science 2018-06-05 Simon S. Du , Surbhi Goel

Neural architecture search (NAS) enables finding the best-performing architecture from a search space automatically. Most NAS methods exploit an over-parameterized network (i.e., a supernet) containing all possible architectures (i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Youngmin Oh , Hyunju Lee , Bumsub Ham

Multi-task learning aims to improve generalization performance of multiple prediction tasks by appropriately sharing relevant information across them. In the context of deep neural networks, this idea is often realized by hand-designed…

Computer Vision and Pattern Recognition · Computer Science 2016-11-17 Yongxi Lu , Abhishek Kumar , Shuangfei Zhai , Yu Cheng , Tara Javidi , Rogerio Feris

Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and…

Computation and Language · Computer Science 2021-09-09 Machel Reid , Edison Marrese-Taylor , Yutaka Matsuo

Despite the remarkable success of deep learning in pattern recognition, deep network models face the problem of training a large number of parameters. In this paper, we propose and evaluate a novel multi-path wavelet neural network…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 D. D. N. De Silva , H. W. M. K. Vithanage , K. S. D. Fernando , I. T. S. Piyatilake

The choice of parameters, and the design of the network architecture are important factors affecting the performance of deep neural networks. However, there has not been much work on developing an established and systematic way of building…

Neural and Evolutionary Computing · Computer Science 2018-05-25 Burak Kakillioglu , Yantao Lu , Senem Velipasalar

In this paper, we propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks, aiming to automate the design of SPD neural architectures. To address this problem, we first introduce a…

Machine Learning · Computer Science 2021-06-15 Rhea Sanjay Sukthanker , Zhiwu Huang , Suryansh Kumar , Erik Goron Endsjo , Yan Wu , Luc Van Gool

Adequate labeled data and expensive compute resources are the prerequisites for the success of neural architecture search(NAS). It is challenging to apply NAS in meta-learning scenarios with limited compute resources and data. In this…

Machine Learning · Computer Science 2021-10-13 Jingtao Rong , Xinyi Yu , Mingyang Zhang , Linlin Ou
‹ Prev 1 3 4 5 6 7 10 Next ›