解决深度神经网络的问题需要更好的训练数据和学习算法
1Department of Cognitive Linguistic & Psychological Sciences, Carney Institute for Brain Science, Brown University, Providence, RI, USA drew_linsley@brown.edu thomas_serre@brown.eduhttps://sites.brown.edu/drewlinsleyhttps://serre-lab.clps.brown.edu.
The Behavioral and brain sciences
|December 6, 2023
概括
由于不同的策略,深度神经网络 (DNN) 往往无法准确地模拟人类视觉. 这项研究解决了这一挑战,提供了为理解生物视觉创造更好的DNN的方法.
科学领域:
- 计算机视觉 计算机视觉
- 神经科学是一个神经科学.
- 人工智能的人工智能
背景情况:
- 深度神经网络 (DNN) 越来越多地用于模拟生物视觉.
- 人们担心DNN可能无法准确地反映人类的视觉处理策略.
- 尔斯等人以前的工作. 突出了这些差异.
研究的目的:
- 调查与人类视觉策略不同的DNN日益恶化的问题.
- 为开发可靠模拟生物视觉的DNNs提出方法.
主要方法:
- 对大规模,高精度DNN的分析.
- 将DNN的内部策略与人类视觉处理进行比较.
主要成果:
- 随着DNN的规模和准确性,DNN与人类视觉策略之间的差异正在增加.
- 目前的DNN通常使用非生物方法实现高精度.
结论:
- 目前开发的DNN是生物视觉的不充分模型.
- 需要一些方法来引导DNN开发向生物可行的解决方案.
- 未来的研究应该专注于创建模拟人类视觉策略的DNN,以便更好地进行生物建模.
相关概念视频
01:35Long-term Potentiation
55.3K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
55.3K
01:01Neuroplasticity
368
Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.
368