paper-with-me

Papers

SMU: smooth activation function for deep networks using smoothing maximum technique

2021-11-08 · Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Deep learning researchers have a keen interest in proposing two new novel activation functions which can boost network performance. A good choice of activation function can have significant consequences in improving network performance. A handcrafted activation is the most common choice in neural network models. ReLU is the most common choice in the deep learning community due to its simplicity though ReLU has some serious drawbacks. In this paper, we have proposed a new novel activation function based on approximation of known activation functions like Leaky ReLU, and we call this function Smooth Maximum Unit (SMU). Replacing ReLU by SMU, we have got 6.22% improvement in the CIFAR100 dataset with the ShuffleNet V2 model.

📄 PDF Abstract BibTeX arXiv:2111.04682

Code (6)

MindCode-4/code-13/tree/main/smu mindspore
iFe1er/SMU tf
iFe1er/SMU_pytorch pytorch
lk18322280259/SMU pytorch
pwc-1/Paper-9/tree/main/3/smu mindspore
reeered/SMU-MindSpore mindspore

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

Grouped Convolution A Grouped Convolution uses a group of convolutions - multiple kernels per layer - resulting in multiple channel outputs per layer. This leads to wider networks helping a…
Average Pooling 설명 없음
ShuffleNet V2 Block ShuffleNet V2 Block is an image model block used in the ShuffleNet V2 architecture, where speed is the metric optimized for…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
ShuffleNet V2 Downsampling Block ShuffleNet V2 Downsampling Block is a block for spatial downsampling used in the ShuffleNet V2 architecture. Unlike the…
Groupwise Point Convolution 설명 없음
Channel Shuffle 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique

2022-01-01 · CVPR 2022 1 · Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Deep learning researchers have a keen interest in proposing new novel activation functions that can boost neural network performance. A good choice of activation function can have a significant effect on improving ne…

Deep Learningimage-classificationImage ClassificationMachine Translation+3

SAU: Smooth activation function using convolution with approximate identities

2021-09-27 · Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey

Well-known activation functions like ReLU or Leaky ReLU are non-differentiable at the origin. Over the years, many smooth approximations of ReLU have been proposed using various smoothing techniques. We propose new smoot…

Spectral Smoothing via Random Matrix Perturbations

2015-07-10 · Jacob Abernethy, Chansoo Lee, Ambuj Tewari

We consider stochastic smoothing of spectral functions of matrices using perturbations commonly studied in random matrix theory. We show that a spectral function remains spectral when smoothed using a unitarily invariant…

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

2024-09-30 · Ke Yi, Zengke Liu, Jianwei Zhang, Chengyuan Li 외

Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantiz…

Quantization

Local Stability and Gaussian Smoothing of Quantized Neural Networks

2026-07-22 · Sergey Salishev, Anton Makarov, Oleg Granichin arxiv

We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bound on |f-g|, linking Gaussian smoothing to the stability analysis o…