Grounding models of category learning in the visual experiences of young children

幼儿视觉体验中类别学习的基础模型

基本信息

批准号：
10704062
负责人：
Bria Long
金额：
$ 10.54万
依托单位：
STANFORD UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2022
资助国家：
美国
起止时间：
2022-09-16 至 2024-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10704062
关键词：
Achievement Adult Age Apple Architecture Award Behavioral Blindness Canis familiaris Cataract Extraction Categories Child Cognitive Computer Models Data Data Set Development Diet Educational Materials Educational workshop Environment Exclusion Exhibits Foundations Goals Infant Intervention Knowledge Label Labrador Language Delays Language Development Learning Life Machine Learning Measures Mentors Modeling Modernization Neural Network Simulation Output Parents Phase Pomegranate Reporting Research Research Personnel Rest Risk Stream Surveys Testing Time Training Visual Work autistic children cognitive development crowdsourcing deep neural network effective intervention experience experimental study improved insight learning outcome longitudinal dataset models and simulation neural novel peer predictive modeling social statistical learning statistics vision science visual learning wolves word learning

项目摘要

PROJECT SUMMARY Early word learning is a major developmental achievement that rests on a foundation of visual category learning: to learn that the word “dog” refers to a category dog that includes chihuahuas and excludes wolves, children must make an impressive visual generalization. However, deep neural networks—our best models of category learning—are unable to learn from the same visual diet as children, limiting our ability to construct mechanistic accounts of early category and word learning. While infants learn the categories that words refer to while experiencing a few categories (e.g., spoons, cups) dramatically more often than others (and while experiencing certain categories as drawings or illustrations), current models learn from uniform distributions of categories where exemplars are photos taken from the adult perspective. The proposed work will overcome these limitations and use deep neural networks to understand how children’s everyday visual experiences interact with statistical learning mechanisms to yield the category representations that support early word learning. In Aim 1 (K99 phase), I will determine how variability in children’s visual experiences relates to early word learning outcomes. To do so, I will collect a representative dataset of the categories in the infant view using a parent-report measure and photographs taken from the infant perspective, and determine whether variance in visual experience with different categories predicts which words are learned earlier in development. In Aim 2 (K99/R00 phase) I will evaluate how well current models and infants learn from diverse sets of realistic visual inputs using looking-time experiments and model simulations, evaluating whether networks with more neurally plausible architectures are better predictors of infant learning. In Aim 3 (R00 phase), I will adapt an existing deep neural network for infant categorization. To do so, I will build output layers on top of a state-of-the-art unsupervised model of object segmentation to identify the categories in the infant view and to make principled generalizations from frequently experienced to infrequently experienced but similar categories—much like young children in early development. The empirical findings and resulting computational model will provide insight into the relevant visual experiences for learning the categories that words refer to. This understanding of how typically-developing children learn rapidly and efficiently in everyday environments is essential to improve interventions for children struggling to learn the categories that words refer to, including late talkers, children with ASD, and children recovering from blindness (e.g., after cataract surgery). This award will build upon my strong background in visual category recognition and provide me with relevant training in both early language acquisition and deep neural networks via interdisciplinary workshops, coursework, and the scientific expertise of a team of mentors and consultants. This award will thus facilitate my transition to become an independent investigator at the forefront of cognitive development, vision science, and machine learning.

项目摘要早期单词学习是一个主要的发展成就，它依赖于视觉类别的基础学习：了解“狗”一词是指包含奇瓦瓦人的类别狗，不包括狼，儿童必须进行令人印象深刻的视觉概括。但是，深层神经网络 - 我们的最佳模型类别学习 - 无法与儿童相同的视觉饮食学习，限制了我们的构建能力早期类别和单词学习的机械叙述。虽然婴儿学习单词参考的类别在经历几类（例如，汤匙，杯子）的同时，比其他类别更频繁地（而当前模型从某些类别或插图中体验某些类别），从从成人角度拍摄照片的示例的类别。拟议的工作将克服这些局限性并使用深层神经网络来了解儿童每天的视觉体验与统计学习机制互动以产生支持早期词的类别表示学习。在AIM 1（K99阶段）中，我将确定儿童视觉体验的可变性与早期有关单词学习结果。为此，我将收集婴儿视图中类别的代表性数据集使用父母报告的测量和从婴儿角度拍摄的照片，并确定是否是否视觉体验与不同类别的视觉体验的差异预测哪些单词在开发中较早学习。在AIM 2（K99/R00阶段）中，我将评估当前的模型和婴儿从潜水员组中学习的程度使用查看时间实验和模型模拟现实的视觉输入，评估是否与更中性的建筑师是婴儿学习的更好预测指标。在AIM 3（R00阶段）中，我将适应现有的婴儿类别的深层神经网络。为此，我将在对象细分的最新无监督模型，以识别婴儿视图中的类别从经常经历到经常经历但相似的经常经历到经常经验的概括类别 - 像幼儿在早期发展中一样。经验发现和结果计算模型将洞悉学习单词所指类别的相关视觉体验。这种对典型开发儿童如何在每天环境中迅速有效地学习的理解对于改善努力学习单词所指类别的儿童的干预措施至关重要，包括最新的谈话者，有ASD的儿童以及从失明中康复的孩子（例如，在白内障手术后）。这个奖项将基于我在视觉类别识别方面的强烈背景，并为我提供相关的培训早期语言获取和深层神经网络都通过跨学科研讨会，课程和导师和顾问团队的科学专业知识。因此，这个奖项将有助于我的过渡在认知发展，视觉科学和机器学习的最前沿的独立研究者。