梦想霍普菲尔德网络及其在相关数据上的惊人的有效性
Ludovica Serricchio1, Dario Bocchi2, Claudio Chilin3
1Dipartimento di Fisica, Sapienza Università di Roma, Piazzale Aldo Moro 5, Rome, 00185, Italy; Center for Life Nano & Neuro-Science, Istituto Italiano di Tecnologia, Viale Regina Elena 291, Rome, 00161, Italy.
概括
我们介绍了Daydreaming,这是一个新的算法,增强了Hopfield网络,以改善内存存储. 这种方法加强了所需的模式,并删除了虚假的记忆,提高了存储容量和检索精度.
科学领域:
- 人工智能的人工智能
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
背景情况:
- 霍普菲尔德网络是关联记忆的基本循环神经网络.
- 传统的霍普菲尔德模型面临存储容量和虚假记忆形成的局限性.
- 现有的梦想算法通过删除虚假记忆提供了部分解决方案.
研究的目的:
- 开发一种增强的算法,Daydreaming,以提高霍普菲尔德网络的存储容量和检索性能.
- 创建一个非破坏性学习算法,将模式强化与虚假记忆擦除相结合.
- 调查算法对非相关和相关数据的有效性,包括真实世界的数据集.
主要方法:
- 开发了一种新的"白日梦"算法,将Hebbian-like强化与虚假记忆抑制集成在一起.
- 通过随机特征模型生成的随机无相关和相关数据集训练了白日梦算法.
- 在MNIST手写数字数据集上评估了算法的性能.
主要成果:
- 昼夜梦想表现出最佳的性能,具有大型的吸引力盆地和高质量的重建无关联数据.
- 该算法有效地利用数据相关性,进一步增加存储容量和吸引器稳定性.
- 梦想成功地稳定了隐藏的数据特征,并为MNIST上未见的例子产生了准确的吸引器.
结论:
- 日梦算法显著增强了霍普菲尔德网络的能力,提供了优越的存储容量和内存检索.
- 它有效地处理复杂的相关数据,稳定基本特征,优于以前的方法.
- 梦想在MNIST等具有挑战性的真实世界数据集上显示了实际适用性和强大的性能.
相关概念视频
Correlation of Experimental Data
188
Dimensional analysis simplifies complex physical problems and guides experimental investigations, but it does not provide complete solutions. It identifies the dimensionless groups that influence a phenomenon, but experimental data is needed to establish the specific relationships and validate theoretical predictions.
For example, a spherical particle moving through a viscous fluid experiences drag. Dimensional analysis shows that the drag force depends on the particle's diameter, velocity,...
For example, a spherical particle moving through a viscous fluid experiences drag. Dimensional analysis shows that the drag force depends on the particle's diameter, velocity,...
188
Cause and Effect
10.8K
While variables are sometimes correlated because one does cause the other, it could also be that some other factor, a confounding variable, is actually causing the systematic movement in our variables of interest. For instance, as sales in ice cream increase, so does the overall rate of crime. Is it possible that indulging in your favorite flavor of ice cream could send you on a crime spree? Or, after committing crime do you think you might decide to treat yourself to a cone?
10.8K
2D NMR: Overview of Heteronuclear Correlation Techniques
143
Heteronuclear correlation spectroscopy is an analytical technique that investigates the coupling between different types of nuclei, often a proton and an X-nucleus, such as carbon-13 or nitrogen-15. This method is commonly used in nuclear magnetic resonance (NMR) spectroscopy to gain insights into complex chemical compounds' structural and compositional aspects. A typical heteronuclear correlation spectrum displays X-nucleus chemical shifts on one axis and a proton spectrum on the other...
143
Correlations
32.5K
Correlation means that there is a relationship between two or more variables (such as ice cream consumption and crime), but this relationship does not necessarily imply cause and effect. When two variables are correlated, it simply means that as one variable changes, so does the other. We can measure correlation by calculating a statistic known as a correlation coefficient. A correlation coefficient is a number from -1 to +1 that indicates the strength and direction of the relationship between...
32.5K
2D NMR: Overview of Homonuclear Correlation Techniques
153
Homonuclear correlation spectroscopy (COSY) is a powerful technique used in Nuclear Magnetic Resonance (NMR) spectroscopy to study the correlations between nuclei of the same type within a molecule. It provides information about scalar couplings between adjacent nuclei, which helps determine connectivity and structural information. There are several COSY variants, each with its unique strengths and experimental parameters.
COSY90 is the standard two-dimensional (2D) COSY experiment that...
COSY90 is the standard two-dimensional (2D) COSY experiment that...
153
Coefficient of Correlation
6.0K
The correlation coefficient, r, developed by Karl Pearson in the early 1900s, is numerical and provides a measure of strength and direction of the linear association between the independent variable x and the dependent variable y.
If you suspect a linear relationship between x and y, then r can measure how strong the linear relationship is.
What the VALUE of r tells us:
The value of r is always between –1 and +1: –1 ≤ r ≤ 1.
The size of the correlation r indicates the...
If you suspect a linear relationship between x and y, then r can measure how strong the linear relationship is.
What the VALUE of r tells us:
The value of r is always between –1 and +1: –1 ≤ r ≤ 1.
The size of the correlation r indicates the...
6.0K


