paper-with-me

홈 › Papers

From Activation to Initialization: Scaling Insights for Optimizing Neural Fields

2024-03-28 · CVPR 2024 1 · Hemanth Saratchandran, Sameera Ramasinghe, Simon Lucey

In the realm of computer vision, Neural Fields have gained prominence as a contemporary tool harnessing neural networks for signal representation. Despite the remarkable progress in adapting these networks to solve a variety of problems, the field still lacks a comprehensive theoretical framework. This article aims to address this gap by delving into the intricate interplay between initialization and activation, providing a foundational basis for the robust optimization of Neural Fields. Our theoretical insights reveal a deep-seated connection among network initialization, architectural choices, and the optimization process, emphasizing the need for a holistic approach when designing cutting-edge Neural Fields.

📄 PDF Abstract BibTeX arXiv:2403.19205

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On weight initialization in deep neural networks

2017-04-28 · Siddharth Krishna Kumar

A proper initialization of the weights in a neural network is critical to its convergence. Current insights into weight initialization come primarily from linear activation functions. In this paper, I develop a theory fo…

Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth

2022-11-26 · Filipe de Avila Belbute-Peres, J. Zico Kolter

Neural networks with sinusoidal activations have been proposed as an alternative to networks with traditional activation functions. Despite their promise, particularly for learning implicit models, their training behavio…

Fast Training of Sinusoidal Neural Fields via Scaling Initialization

2024-10-07 · Taesun Yeom, Sangyoon Lee, Jaeho Lee

Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks. Despite many advantages, neural fields often have a high training cost, which prevents a broader adopti…

Variance Control via Weight Rescaling in LLM Pre-training

2025-03-21 · Louis Owen, Abhay Kumar, Nilabhra Roy Chowdhury, Fabian Güra

The outcome of Large Language Model (LLM) pre-training strongly depends on weight initialization and variance control strategies. Although the importance of initial variance control has been well documented in neural net…

Language ModelingLanguage ModellingLarge Language ModelManagement+1

Optimizing Neural Networks through Activation Function Discovery and Automatic Weight Initialization

2023-04-06 · Garrett Bingham

Automated machine learning (AutoML) methods improve upon existing models by optimizing various aspects of their design. While present methods focus on hyperparameters and neural network topologies, other aspects of neura…

AutoML