经常性神经网络学习多步视觉例程,并进行强化学习
Sami Mollard1, Catherine Wacongne1,2, Sander M Bohte3,4
1Department of Vision & Cognition, Netherlands Institute for Neuroscience, Amsterdam, The Netherlands.
PLoS computational biology
|April 29, 2024
概括
这项研究介绍了一种新的循环神经网络,它通过将复杂的视觉任务分解成连续的操作来学习复杂的视觉任务. 通过使用生物学上可信的学习规则,该网络成功地模仿了在子中观察到的神经活动模式,证明了有效的工作记忆和任务序列.
科学领域:
- 计算神经科学是一种计算神经科学.
- 认知科学是一种认知科学.
- 人工智能的人工智能是人工智能.
背景情况:
- 认知任务通常是顺序地解决的,需要存储和传播中间结果.
- 视觉皮层中的工作记忆增强了神经活动,用于存储和访问中间结果.
研究的目的:
- 研究如何在经强化学习训练的神经网络中出现元素视觉操作及其序列.
- 提出一种新的循环神经网络架构,能够学习复合视觉任务.
主要方法:
- 开发了一种新的循环神经网络架构.
- 使用RELEARNN训练网络,这是一个生物学上可信的四个因素的Hebbian学习规则.
- 利用子视觉皮层的可用电生理记录来完成三个视觉任务.
主要成果:
- 网络学习了诸如轮分组和视觉搜索之类的基本操作.
- 该网络成功执行了基于视觉刺激和任务奖励的操作序列.
- 经过训练的网络活动显示对行为相关刺激的反应增强,反映了子视觉皮层活动.
- 相关信息被保留为增强活动,并在子程序之间传递.
结论:
- 从生物学上讲,可信的学习规则可以训练循环神经网络进行多步视觉任务.
- 拟议的架构和学习规则为理解神经系统中的序列处理提供了一个模型.
- 这项工作弥合了强化学习和生物启发的神经计算之间的差距,用于复杂的认知功能.
相关概念视频
01:24Reinforcement Schedules
144
Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...
Once a behavior is learned,...
144
01:25Neural Circuits
1.2K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
1.2K