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, GA.
bioRxiv : the preprint server for biology
|February 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. 这些ANN表明,低级信号和方差变化,而不是认知启发式,可以解释这些影响在人类和机器.
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:
- 人类的信心-准确性关系往往被刺激能量 (对比度,可变性) 分离.
- 积极证据启发式是常见的解释,但信号和方差增加假设提供了一个替代方案.
- 人工神经网络 (ANN) 提供了一个模型系统来测试认知启发术的必要性.
研究的目的:
- 为了调查是否信任-准确性解离自然出现卷积神经网络 (CNNs) 在刺激能量操纵下.
- 确定CNN中的这些分离是否是由低级信号和方程变化驱动的,类似于拟议的人类机制.
- 评估认知启发式与低级处理在解释人类信心-准确性分离中的作用.
主要方法:
- 通过改变视觉刺激的对比度和变异性来操纵刺激能量.
- 不同架构的卷积神经网络 (CNN) (包括VGG-19,ResNet-50在内的浅到深) 被训练和测试.
- 分析了CNN内部的内部表述,以确定信任差异的来源.
主要成果:
- CNN系统始终产生了信心-准确度分离,反映了人类在不同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的潜在原因被确定为由于更高的刺激能量增加了内部表示的分离和变异,导致信心升高.
结论:
- 在没有明确的信任启发术的情况下,信任-准确性解离可能会在ANN中出现,这表明它们对这种现象并不严格必要.
- 这些发现支持信号和变异增加假设,作为人类和人工系统中信任精度分离的潜在解释.
- 对于区分低级别的,刺激驱动的和高级别的,行为认知解释,CNN作为有价值的模型.
关键词:
人工神经网络的人工神经网络信心 信心 信心 信心 信心感知决策 感知决策视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指视觉元认知 (Visual Metacognition) 是指相关概念视频
Confidence Coefficient
7.6K
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...
7.6K
Accuracy, limits, and approximation
449
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...
449
Improving Translational Accuracy
10.4K
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...
10.4K
Confidence Intervals
6.2K
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...
6.2K
Accuracy and Errors in Hypothesis Testing
199
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%...
199
Confirmation 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


