了解深度学习的重要性
Tim Räz1, Claus Beisbart1,2
1University of Bern, Institute of Philosophy, Länggassstrasse 49a, 3012 Bern, Switzerland.
概括
深度神经网络 (DNN) 是科学中的强大工具,但我们对它们内部运作的有限理解可能会阻碍我们真正理解它们的经验现象的能力. 这篇论文认为,强烈的解释性理解受到这种知识差距的损害.
科学领域:
- 人工智能的人工智能
- 科学哲学的哲学科学哲学
- 科学方法科学方法学
背景情况:
- 深度神经网络 (DNN) 越来越多地被用于科学研究.
- 关于DNN的"黑盒子"性质是否阻碍了科学理解存在争论.
- 艾米丽·沙利文的论点表明,DNN可以用于理解,尽管它们本身缺乏可解释性.
研究的目的:
- 批判性地评估艾米丽·沙利文关于理解DNN的论点.
- 确定DNN中缺乏可解释性是否限制了它们对科学理解的有用性.
- 在DNN的背景下,区分弱和强的理解概念.
主要方法:
- 在科学中对"理解"概念的哲学分析.
- 对艾米丽·沙利文关于DNN和科学理解的立场进行论证性批评.
- 理解的弱和强 (解释性) 形式之间的区别.
主要成果:
- 萨利文的说法只有在理解的定义较弱的情况下才是可以支持的.
- 使用DNN对经验现象的强有力的解释性理解确实受到DNN解释性缺乏的限制.
- 这篇论文驳斥了DNN可以提供深入的科学洞察力,而不需要解决自身的不透明性.
结论:
- 深度神经网络 (DNN) 的可解释性对于实现真正的科学理解至关重要.
- 为了科学发现,依赖DNN需要解决它们的"黑子"问题.
- 一个强有力的理解概念需要的不仅仅是预测的准确性;它要求解释性的洞察力,目前受到DNN不透明度的限制.
相关概念视频
Generalization, Discrimination, and Extinction
532
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
532
Associative Learning
344
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
344
Understanding Memory
293
Memory is the retention of information or experiences over time, facilitated through three main processes: encoding, storage, and retrieval. Encoding is the process of inputting information into the memory system. For instance, when listening to a lecture, watching a play, reading a book, or having a conversation, the brain is actively encoding information. This initial stage involves transforming sensory input into a form that can be processed and stored by the brain. Various factors, such as...
293
Directional Terms
8.4K
Directional terms are essential for describing the relative locations of different body structures. For instance, an anatomist might describe one band of tissue as "inferior to" another, or a physician might describe a tumor as "superficial to" a deeper body structure. These terms often use comparative terms in pairs to trace out the relative locations of one body part to another or descriptions of body tissues like the deeper ones from superficially present with reference to...
8.4K
Real-World Application of Classical Conditioning
550
Classical conditioning not only includes the initial pairing of stimuli but also extends to more complex forms, such as higher-order conditioning. Higher-order conditioning involves creating associations beyond the primary conditioned stimulus, resulting in a chain of conditioned responses.
Higher-order, or second-order, conditioning occurs when a neutral stimulus becomes associated with an already established conditioned stimulus through repeated pairings. For instance, if a dog has been...
Higher-order, or second-order, conditioning occurs when a neutral stimulus becomes associated with an already established conditioned stimulus through repeated pairings. For instance, if a dog has been...
550
Parallel Processing
150
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
150


