IEEE

FPGA Implementation of Sigmoid, Hyperbolic Tangent and Softmax Functions using Efficient Architecture for Exponential Function

Abstract: Machine learning (ML) algorithms take help of different activation functions to calculate probabilities for classification problem. Over the past few years researchers are trying to ...
IEEE

A Fully Probabilistic Model for Sigmoid Approximation and Its Hardware- Efficient Implementation

Abstract: The sigmoid function is a representative activation function in shallow neural networks. Its hardware realization is challenging due to the complex exponential and reciprocal operations.
Scientific Research Publishing

Pedamonti, D. (2018) Comparison of Non-Linear Activation Functions for Deep Neural Networks on MNIST Classification Task. arXiv.

ABSTRACT: Artificial deep neural networks (ADNNs) have become a cornerstone of modern machine learning, but they are not immune to challenges. One of the most significant problems plaguing ADNNs is ...
Hosted on MSN

20 Activation Functions in Python for Deep Neural Networks – ELU, ReLU, Leaky-ReLU, Sigmoid, Cosine

Explore 20 different activation functions for deep neural networks, with Python examples including ELU, ReLU, Leaky-ReLU, Sigmoid, and more. #ActivationFunctions #DeepLearning #Python Tropical Storm ...
eLife

Importance of higher-order epistasis in protein sequence-function relationships

In this important work, the authors present a new transformer-based neural network designed to isolate and quantify higher-order epistasis in protein sequences. They provide solid evidence that higher ...
GitHub

torch.nn.functional.sigmoid produces inconsistent results on different device for complex inputs

The torch.nn.functional.sigmoid function produces inconsistent results on CPU and GPU for complex inputs with a real part of negative infinity (-inf). PyTorch version: 2.5.1+cu124 Is debug build: ...
GitHub

Binary Classification Issue #1647

i am running binary classification report. my "target" column is binary 0,1 values, "pred_lablel" is binary 01, values and "prediction" is probabilities between 0-1 i get auc/roc, log loss but ...
Scientific Research Publishing

Zaidi, A. and Al Luhayb, A.S.M. (2023) Two Statistical Approaches to Justify the Use of the Logistic Function in Binary Logistic Regression. Mathematical Problems in ...

ABSTRACT: Road traffic accidents are one of the global safety and socioeconomic challenges. According to WHO (2024), it has caused over 1.19 million annual fatalities. It is also projected to cause ...