CRII: RI: Neuromodulated Deep Vision: Continual Learning and Goal-Oriented Adaptation

CRII：RI：神经调节深度视觉：持续学习和目标导向的适应

• 批准号: 1849946
• 负责人: Rolando Estrada
• 金额: $ 17.5万
• 依托单位: Georgia State University Research Foundation, Inc.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2022-03-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1849946&HistoricalAwards=false
• 关键词: CRII; RI; Neuromodulated; Deep; Vision

Deep neural networks are revolutionizing many fields and industries. These systems can learn to solve problems ranging from parsing natural language to discovering new drugs. However, current networks can only solve individual, static problems; they cannot learn gradually over time or adapt their computations in real time. This project seeks to bridge the gap between human and machine intelligence by modeling a chemical process in the brain that help humans learn and adjust their behavior based on context. Specifically, the chemical acetylcholine (ACh) has been shown to modulate responses to visual stimuli by selectively raising or lowering the activity level of individual neurons. This chemical is also crucial for visual learning in infants. An insufficient concentration of ACh in the brain leads to poor visual attention and has also been linked to memory deficits and Alzheimer?s disease. Thus, adding ACh-like mechanisms to deep neural networks can potentially allow them to learn over time and adapt their behavior to rapidly changing conditions--a growing need in domains ranging from forest conservation to cybersecurity.In more detail, deep convolutional neural networks (CNNs) are the state-of-the-art approach for a wide variety of image processing tasks, such as object recognition and semantic segmentation. This project will investigate how to add ACh-like regulation to CNNs by modeling the spatial and temporal dynamics of this chemical process. Specifically, the CNN will be connected to a set of spatially and temporally heterogeneous sources of modulation. Each neuron in the CNN will have different receptors that determine how that particular neuron responds to different ambient levels of ACh. The system will use two controllers: one to determine the current level of ACh across different parts of the network and another to set the correct context (i.e., to model top-down feedback from higher cortical areas). The first controller will allow the system to quickly adjust its behavior, while the second will enable long-term learning. This project constitutes an initial step in developing intelligent systems that, like biological organisms, can autonomously cope with changing, dynamic environments. In addition to its technical contributions, this project will allow students at Georgia State University, one of the most diverse institutions in the country, to foster interdisciplinary connections between artificial intelligence, neuroscience, and related STEM disciplines.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

深度神经网络正在革新许多领域和行业。这些系统可以学习解决从解析自然语言到发现新药的各种问题。然而，目前的网络只能解决个体的、静态的问题；他们不能随着时间的推移逐渐学习，也不能实时调整他们的计算。该项目旨在通过模拟大脑中的化学过程来弥合人类和机器智能之间的差距，帮助人类根据环境学习和调整自己的行为。具体来说，化学乙酰胆碱（ACh）已被证明可以通过选择性地提高或降低单个神经元的活动水平来调节对视觉刺激的反应。这种化学物质对婴儿的视觉学习也至关重要。乙酰胆碱在大脑中的浓度不足会导致视觉注意力低下，也与记忆缺陷和阿尔茨海默病有关。年代的疾病。因此，将类似ach的机制添加到深度神经网络中，可能会使它们随着时间的推移而学习，并使其行为适应快速变化的条件——这在从森林保护到网络安全等领域都是一种日益增长的需求。更详细地说，深度卷积神经网络（cnn）是各种图像处理任务的最先进方法，例如对象识别和语义分割。该项目将研究如何通过模拟这一化学过程的空间和时间动态来将类似ach的调节添加到cnn中。具体来说，CNN将连接到一组空间和时间上异构的调制源。CNN中的每个神经元都有不同的受体，这些受体决定了特定神经元如何对不同环境水平的乙酰胆碱做出反应。该系统将使用两个控制器：一个用于确定网络不同部分乙酰氨基酚的当前水平，另一个用于设置正确的环境（即，模拟来自高级皮质区域的自上而下的反馈）。第一个控制器将允许系统快速调整其行为，而第二个控制器将实现长期学习。这个项目是开发智能系统的第一步，像生物有机体一样，可以自主应对不断变化的动态环境。除了技术贡献外，该项目还将使佐治亚州立大学（美国最多样化的机构之一）的学生能够促进人工智能、神经科学和相关STEM学科之间的跨学科联系。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

SuperCaustics: Real-time, open-source simulation of transparent objects for deep learning applications

SuperCaustics：用于深度学习应用的透明对象的实时开源模拟

• DOI: 10.1109/icmla52953.2021.00108
• 发表时间: 2021
• 期刊: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA
• 作者: Mousavi, Mehdi;Estrada, Rolando
• 通讯作者: Estrada, Rolando

Continual Learning with Deep Artificial Neurons

使用深度人工神经元进行持续学习

• 发表时间: 2022
• 期刊: International Conference on Learning Representations (ICLR
• 作者: Camp, Brendan;Mandivarapu, Jaya K.;Estrada, Rolando
• 通讯作者: Estrada, Rolando

Dynamic Deep Networks for Retinal Vessel Segmentation

• DOI: 10.3389/fcomp.2020.00035
• 发表时间: 2020-08-26
• 期刊: FRONTIERS IN COMPUTER SCIENCE
• 影响因子: 2.6
• 作者: Khanal, Aashis;Estrada, Rolando
• 通讯作者: Estrada, Rolando