在卷积神经网络中,信心和准确性之间的类似人类分离
Medha Shekhar1, Dobromir Rahnev1
1School of Psychology, Georgia Institute of Technology, Atlanta, Georgia, United States of America.
PLoS computational biology
|November 14, 2024
概括
人工神经网络 (ANN) 在刺激能量被操纵时表现出类似于人类的信心准确度解离. 这表明信号和方差变化,而不仅仅是认知启发式,驱动这些影响的感知.
科学领域:
- 认知科学 认知科学
- 计算神经科学是一种神经科学.
- 人工智能的人工智能
背景情况:
- 当刺激能量 (对比度,可变性) 发生变化时,人类的信心-精度分离会发生,更高的能量会导致更高的信心,即使与匹配的性能相匹配.
- 积极证据启发式是一个常见的解释,表明信心忽视了不证实的证据.
- 信号和变异增加假设提供了一个替代方案,将分离归因于知觉表现分离和变异的变化.
研究的目的:
- 测试信任-准确性解离是否在人工神经网络 (ANN) 中自然出现,特别是卷积神经网络 (CNN),这些神经网络缺乏内置的信任启发式.
- 确定ANN是否可以复制由刺激能量操纵引起的人类信心精度解离.
- 研究CNN中这些解离的潜在机制,并将其与人类认知模型进行比较.
主要方法:
- 测试了各种架构的卷积神经网络 (CNN) (浅层到深层,包括VGG-19和ResNet-50).
- 用对比度和可变性操纵刺激能量.
- 在不同的CNN和刺激条件中分析了信心-准确性关系.
主要成果:
- CNN系统始终产生了信心-准确度分离,反映了人类在各种刺激能量操纵中的发现.
- 这些分离在一系列CNN架构中被观察到,从简单到复杂.
- 在CNN中发现的机制是输出层的信号分离和方差增加,与信号和方差增加假设一致.
结论:
- 在没有明确的信任启发式的人工系统中,信任-准确性分离可能会出现,这挑战了人类积极证据启发式的必要性.
- 信号和偏差增加机制似乎是信任准确度解离的基本驱动力,适用于人工和生物系统.
- CNNs作为测试和完善人类感知和信心的认知理论的有价值的模型.
相关概念视频
01:24Confidence Coefficient
7.5K
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...
7.5K
01:28Accuracy, limits, and approximation
441
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
441
02:07Improving Translational Accuracy
9.1K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.1K
01:21Confidence Intervals
6.1K
An unbiased point estimate is often insufficient to predict a population estimate, such as population mean or population proportion. In this scenario, a confidence interval is used. A confidence interval is an estimate similar to a sample proportion. However, unlike the point estimate which is a single value, the confidence interval contains a range of values. These values have lower and upper limits, known as confidence limits, and can be designated as L1 and L2, respectively.
A...
A...
6.1K
01:13Accuracy and Errors in Hypothesis Testing
176
Hypothesis testing is a fundamental statistical tool that begins with the assumption that the null hypothesis H0 is true. During this process, two types of errors can occur: Type I and Type II. A Type I error refers to the incorrect rejection of a true null hypothesis, while a Type II error involves the failure to reject a false null hypothesis.
In hypothesis testing, the probability of making a Type I error, denoted as α, is commonly set at 0.05. This significance level indicates a 5%...
In hypothesis testing, the probability of making a Type I error, denoted as α, is commonly set at 0.05. This significance level indicates a 5%...
176
01:31Confirmation Biases
5.5K
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
5.5K