Cover Image

Making Sigmoid-MSE Great Again: Output Reset Challenges Softmax Cross-Entropy in Neural Network Classification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tyagi, Kanishka, Rane, Chinmay, Vaidya, Ketaki, Challgundla, Jeshwanth, Auddy, Soumitro Swapan, Manry, Michael
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
by: Rane, Chinmay, et al.
Published: (2023)

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models
by: Challagundla, Jeshwanth
Published: (2025)

Adaptive multiple optimal learning factors for neural network training
by: Challagundla, Jeshwanth
Published: (2024)

#MakeBeefGreatAgain: A Cross-Platform Analysis of Early #MAHA Discourse
by: Xue, Haoning, et al.
Published: (2026)

Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecasting
by: Wang, Jieting, et al.
Published: (2025)

Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions
by: Varre, Aditya, et al.
Published: (2026)

The Great Reset
by: Cerniglia, Floriana, et al.
Published: (2021)

Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks
by: Yin, Bojian, et al.
Published: (2024)

FCN+: Global Receptive Convolution Makes FCN Great Again
by: Ren, Xiaoyu, et al.
Published: (2023)

SAM-SP: Self-Prompting Makes SAM Great Again
by: Zhou, Chunpeng, et al.
Published: (2024)

Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps
by: Oh, Yoojin, et al.
Published: (2025)

Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
by: Nguyen, Huy, et al.
Published: (2024)

Make Literature-Based Discovery Great Again through Reproducible Pipelines
by: Cestnik, Bojan, et al.
Published: (2025)

Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
by: Garrod, Connall, et al.
Published: (2025)

Make Shuffling Great Again: A Side-Channel Resistant Fisher-Yates Algorithm for Protecting Neural Networks
by: Puškáč, Leonard, et al.
Published: (2025)

Make America Great Again: ¿expresión de un nativismo blanco contemporáneo?
by: Antonio Alejo
Published: (2018)

Multiscale Softmax Cross Entropy for Fovea Localization on Color Fundus Photography
by: Wu, Yuli, et al.
Published: (2021)

BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering
by: Qiu, Xinmin, et al.
Published: (2024)

DRPCA-Net: Make Robust PCA Great Again for Infrared Small Target Detection
by: Xiong, Zihao, et al.
Published: (2025)

Make Graph Neural Networks Great Again: A Generic Integration Paradigm of Topology-Free Patterns for Traffic Speed Prediction
by: Zhou, Yicheng, et al.
Published: (2024)

Do Not Despair, We Are Together
by: Ketaki Datta
Published: (2019)

Translated Poem of late Jibanananda Das, the famous modern Bengali poet
by: Ketaki Datta
Published: (2020)

Ghosts of Softmax: Complex Singularities That Limit Safe Step Sizes in Cross-Entropy
by: Sao, Piyush
Published: (2026)

ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
by: He, Yunhang, et al.
Published: (2026)

X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
by: Geng, Zigang, et al.
Published: (2025)

Tensor Methods in High Dimensional Data Analysis: Opportunities and Challenges
by: Auddy, Arnab, et al.
Published: (2024)

How Network Topology Affects the Strength of Dangerous Power Grid Perturbations
by: Alvares, Calvin, et al.
Published: (2023)

Experimental verification of Generalised Synchronization
by: Ghosh, Tania, et al.
Published: (2025)

A Probabilistic Distance-Based Stability Quantifier for Complex Dynamical Systems
by: Alvares, Calvin, et al.
Published: (2023)

Upper Bounds for the I-MSE and max-MSE of Kernel Density Estimators
by: Hjort, Nils Lid, et al.
Published: (2026)

Entropy Production of Quantum Reset Models
by: Haack, Géraldine, et al.
Published: (2024)

Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraints
by: Auddy, Arnab, et al.
Published: (2024)

Gluon: Making Muon & Scion Great Again! (Bridging Theory and Practice of LMO-based Optimizers for LLMs)
by: Riabinin, Artem, et al.
Published: (2025)

Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective
by: Yan, Fanqi, et al.
Published: (2025)

Make Planning Research Rigorous Again!
by: Katz, Michael, et al.
Published: (2025)

Make Deep Networks Shallow Again
by: Bermeitinger, Bernhard, et al.
Published: (2023)

Enhancing Mobile "How-to" Queries with Automated Search Results Verification and Reranking
by: Ding, Lei, et al.
Published: (2024)

Inferring Dynamic Hidden Graph Structure in Heterogeneous Correlated Time Series
by: Mohan, Jeshwanth, et al.
Published: (2025)

Make Graph-based Referring Expression Comprehension Great Again through Expression-guided Dynamic Gating and Regression
by: Ke, Jingcheng, et al.
Published: (2024)

2 Poems by Ketaki Dutta
by: Dr Ketaki Dutta
Published: (2026)