相关实验视频

Updated: May 15, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

经过认证的强度的光滑分类器的多头组合

Kun Fang¹, Qinghua Tao², Yingwen Wu¹

¹Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, China.

Neural networks : the official journal of the International Neural Network Society

|April 10, 2025

概括

SmOothed多头组合 (SOME) 通过训练具有多个头的单个网络,提高了深度神经网络 (DNN) 的认证稳定性. 这种方法实现了最先进的性能,与传统合奏相比,计算成本大大降低.

科学领域:

人工智能的人工智能
机器学习机器学习
计算机视觉计算机视觉

背景情况:

随机平滑 (RS) 是在深度神经网络 (DNN) 中获得认证的稳定性的关键技术.
组合多个DNN可以提高RS性能,但会产生大量的计算开销.
现有的集体方法往往忽视了单个网络之间的协同潜力和通信.

研究的目的:

引入一种新的,计算效率高的方法,使用整体方法实现认证的稳定性.
开发一个培训策略,最大限度地利用在单一DNN架构中组合的好处.
提高DNN中可认证的强大防御的有效性和效率.

主要方法:

拟议的SmOothed多头组合 (SOME),一个单一的DNN与多个增强头使用共数约束训练.
实施了循环沟通流和自律学习策略,在使用平滑损失的头部之间进行自律学习.
专为经过认证的强度而设计的损耗,并鼓励头部之间的多样性.

主要成果:

与组合多个DNN相比,SOME表现出具有竞争力或优异的可认证的强大性能.
多头架构和循环教学方案显著降低了培训和认证计算成本.
通过在单一模型中的整体好处,实现了更有效和高效的防御对抗攻击.

结论:

SOME方法为DNN的认证稳定性提供了一个高度有效和计算效率高的解决方案.
新的培训策略和架构成功地利用了整体效应,同时减轻了计算负担.
在开发实用,可扩展,可认证的强大机器学习模型方面,SOME 代表了重大进展.

关键词:

经过认证的稳固性认证联合教学 (co-teaching) 是一种联合教学.合唱团组合在一起.随机调整平滑方式自己节奏的学习学习.

更多相关视频

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

相关概念视频

Classification of Systems-II

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,

Classification of Systems-I

Classification of Systems-I

Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:

Aggregates Classification

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

Confidence Coefficient

Confidence Coefficient

The confidence coefficient is also known as the confidence level or degree of confidence. It is the percent expression for the probability, 1-α, that the confidence interval contains the true population parameter assuming that the confidence interval is obtained after sufficient unbiased sampling; for example, if the CL = 90%, then in 90 out of 100 samples the interval estimate will enclose the true population parameter. Here α is the area under the curve, distributed equally under...

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...