paper-with-me

Papers

Backprojection for Training Feedforward Neural Networks in the Input and Feature Spaces

2020-04-05 · Benyamin Ghojogh, Fakhri Karray, Mark Crowley

After the tremendous development of neural networks trained by backpropagation, it is a good time to develop other algorithms for training neural networks to gain more insights into networks. In this paper, we propose a new algorithm for training feedforward neural networks which is fairly faster than backpropagation. This method is based on projection and reconstruction where, at every layer, the projected data and reconstructed labels are forced to be similar and the weights are tuned accordingly layer by layer. The proposed algorithm can be used for both input and feature spaces, named as backprojection and kernel backprojection, respectively. This algorithm gives an insight to networks with a projection-based perspective. The experiments on synthetic datasets show the effectiveness of the proposed method.

📄 PDF Abstract BibTeX arXiv:2004.04573

Code (1)

bghojogh/Backprojection 공식 구현

Tasks

Dimensionality Reduction

Similar Papers 제목 키워드 기반

XCycles Backprojection Acoustic Super-Resolution

2021-05-19 · Feras Almasri, Jurgen Vandendriessche, Laurent Segers, Bruno da Silva 외

The computer vision community has paid much attention to the development of visible image super-resolution (SR) using deep neural networks (DNNs) and has achieved impressive results. The advancement of non-visible light …

Image Super-ResolutionSuper-Resolution

Unsupervised Depth Completion with Calibrated Backprojection Layers

2021-08-24 · ICCV 2021 10 · Alex Wong, Stefano Soatto

We propose a deep neural network architecture to infer dense depth from an image and a sparse point cloud. It is trained using a video stream and corresponding synchronized sparse point cloud, as obtained from a LIDAR or…

DecoderDepth Completion

Multi-granularity Backprojection Transformer for Remote Sensing Image Super-Resolution

2023-10-19 · Jinglei Hao, Wukai Li, Binglu Wang, Shunzhou Wang 외

Backprojection networks have achieved promising super-resolution performance for nature images but not well be explored in the remote sensing image super-resolution (RSISR) field due to the high computation costs. In thi…

Image ReconstructionImage Super-ResolutionSuper-Resolution

Human Pose Estimation with Iterative Error Feedback

2015-07-23 · CVPR 2016 6 · Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik

Hierarchical feature extractors such as Convolutional Networks (ConvNets) have achieved impressive performance on a variety of classification tasks using purely feedforward processing. Feedforward architectures can learn…

Pose EstimationSemantic Segmentation

On shallow feedforward neural networks with inputs from a topological space

2025-04-03 · Vugar Ismailov

We study feedforward neural networks with inputs from a topological space (TFNNs). We prove a universal approximation theorem for shallow TFNNs, which demonstrates their capacity to approximate any continuous function de…