Discrete Predictions: The Integer Revolution in Neural Networks
Predicting integer-constrained labels with discrete distributions can enhance neural network performance. Two innovative methods emerge as frontrunners.
Read the full articleYou might also wanna read
Wider Neural Networks with Fewer Parameters Improve Performance by Reducing Feature Interference
This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves
arxiv.org·1mo ago
Rethinking Overparameterization: Why the Lottery Ticket Analogy Falls Short
Lotteries and tickets are often used as a didactical analogy to explain the success of overparameterized neural networks: “larger networks s
infoscience.epfl.ch·16d ago
uGMM-NN: Neural Network Architecture with Gaussian Mixture Model Neurons for Probabilistic Reasoning
This paper introduces the Univariate Gaussian Mixture Model Neural Network (uGMM-NN), a novel neural architecture that embeds probabilistic
arxiv.org·10mo ago
Study Reveals Convergent Evolution in How Language Models Learn Number Representations
Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this pa
arxiv.org·2mo ago
Binary normalized neural networks achieve 32x memory reduction with single-bit parameters while maintaining performance
The increasing size of large neural network models, specifically language models and foundational image models, poses deployment challenges,
arxiv.org·9mo ago
DDN: Discrete Distribution Networks - A Novel Generative Model for Image Reconstruction
Novel Generative Model with Simple Principles and Unique Properties
discrete-distribution-networks.github.io·9mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.