paper-with-me

홈 › Papers

Adaptive Neuron Apoptosis for Accelerating Deep Learning on Large Scale Systems

2016-10-03 · Charles Siegel, Jeff Daily, Abhinav Vishnu

We present novel techniques to accelerate the convergence of Deep Learning algorithms by conducting low overhead removal of redundant neurons -- apoptosis of neurons -- which do not contribute to model learning, during the training phase itself. We provide in-depth theoretical underpinnings of our heuristics (bounding accuracy loss and handling apoptosis of several neuron types), and present the methods to conduct adaptive neuron apoptosis. Specifically, we are able to improve the training time for several datasets by 2-3x, while reducing the number of parameters by up to 30x (4-5x on average) on datasets such as ImageNet classification. For the Higgs Boson dataset, our implementation improves the accuracy (measured by Area Under Curve (AUC)) for classification from 0.88/1 to 0.94/1, while reducing the number of parameters by 3x in comparison to existing literature. The proposed methods achieve a 2.44x speedup in comparison to the default (no apoptosis) algorithm.

📄 PDF Abstract BibTeX arXiv:1610.00790

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning

2025-03-27 · Yupei Li, Manuel Milling, Björn W. Schuller

Artificial Intelligence (AI) has achieved new levels of performance and spread in public usage with the rise of deep neural networks (DNNs). Initially inspired by human neurons and their connections, NNs have become the …

CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

2024-10-23 · Qinsi Wang, Saeed Vahidian, Hancheng Ye, Jianyang Gu 외

Large language models (LLMs) with billions of parameters have sparked a new wave of exciting AI applications. However, their high computational costs and memory demands during inference pose significant challenges. Adapt…

GPULanguage ModelingLanguage ModellingLarge Language Model+1

Connectome-Guided Automatic Learning Rates for Deep Networks

2025-10-27 · Peilin He, Tananun Songdechakraiwut arxiv

The human brain is highly adaptive: its functional connectivity reconfigures on multiple timescales during cognition and learning, enabling flexible information processing. By contrast, artificial neural networks typical…

Optimal Brain Apoptosis

2025-02-25 · Mingyuan Sun, Zheng Fang, Jiaxu Wang, Junjie Jiang 외

The increasing complexity and parameter count of Convolutional Neural Networks (CNNs) and Transformers pose challenges in terms of computational efficiency and resource demands. Pruning has been identified as an effectiv…

Computational Efficiency

Effective description of bistability and irreversibility in apoptosis

2021-05-14 · Sol M. Fernández Arancibia, Hernán E. Grecco, Luis G. Morelli

Apoptosis is a mechanism of programmed cell death in which cells engage in a controlled demolition and prepare to be digested without damaging their environment. In normal conditions apoptosis is repressed, until it is i…