Perspectives of Neural-Symbolic Integration
Barbara Hammer ¡ Pascal Hitzler
āĻāĻ ā§¨ā§Ļā§Ļā§ ¡ Springer
āĻāĻŦā§āĻ
319
āĻĒā§āĻˇā§āĻ āĻž
reportāĻŽā§āĻ˛ā§āĻ¯āĻžāĻāĻāĻ¨ āĻā§°ā§ āĻĒā§°ā§āĻ¯āĻžāĻ˛ā§āĻāĻ¨āĻž āĻ¸āĻ¤ā§āĻ¯āĻžāĻĒāĻ¨ āĻā§°āĻž āĻšā§ā§ąāĻž āĻ¨āĻžāĻ  āĻ
āĻ§āĻŋāĻ āĻāĻžāĻ¨āĻ
āĻāĻ āĻāĻŦā§āĻāĻāĻ¨ā§° āĻŦāĻŋāĻˇā§ā§
The human brain possesses the remarkable capability of understanding, - terpreting, and producing human language, thereby relying mostly on the left hemisphere. The ability to acquire language is innate as can be seen from d- orders such as speci?c language impairment (SLI), which manifests itself in a missing sense for grammaticality. Language exhibits strong compositionality and structure. Hence biological neural networks are naturally connected to processing and generation of high-level symbolic structures. Unlike their biological counterparts, arti?cial neural networks and logic do not form such a close liason. Symbolic inference mechanisms and statistical machine learning constitute two major and very di?erent paradigms in ar- ?cial intelligence which both have their strengths and weaknesses: Statistical methods o?er ?exible and highly e?ective tools which are ideally suited for possibly corrupted or noisy data, high uncertainty and missing information as occur in everyday life such as sensor streams in robotics, measurements in medicine such as EEG and EKG, ?nancial and market indices, etc. The m- els, however, are often reduced to black box mechanisms which complicate the integration of prior high level knowledge or human inspection, and they lack theabilitytocopewitharichstructureofobjects,classes,andrelations. S- bolic mechanisms, on the other hand, are perfectly applicative for intuitive human-machine interaction, the integration of complex prior knowledge, and well founded recursive inference. Their capability of dealing with uncertainty andnoiseandtheire?ciencywhenaddressingcorruptedlargescalereal-world data sets, however, is limited. Thus, the inherent strengths and weaknesses of these two methods ideally complement each other.
āĻāĻ āĻāĻŦā§āĻāĻāĻ¨āĻ āĻŽā§āĻ˛ā§āĻ¯āĻžāĻāĻāĻ¨ āĻā§°āĻ
āĻāĻŽāĻžāĻ āĻāĻĒā§āĻ¨āĻžā§° āĻŽāĻ¤āĻžāĻŽāĻ¤ āĻāĻ¨āĻžāĻāĻāĨ¤
āĻĒāĻĸāĻŧāĻžā§° āĻ¨āĻŋāĻ°ā§āĻĻā§āĻļāĻžā§ąāĻ˛ā§
āĻ¸ā§āĻŽāĻžā§°ā§āĻāĻĢâāĻ¨ āĻā§°ā§ āĻā§āĻŦāĻ˛ā§āĻ
Android āĻā§°ā§ iPad/iPhoneā§° āĻŦāĻžāĻŦā§ Google Play Books āĻāĻĒāĻā§ āĻāĻ¨āĻˇā§āĻāĻ˛ āĻā§°āĻāĨ¤ āĻ āĻ¸ā§āĻŦāĻ¯āĻŧāĻāĻā§āĻ°āĻŋāĻ¯āĻŧāĻāĻžā§ąā§ āĻāĻĒā§āĻ¨āĻžā§° āĻāĻāĻžāĻāĻŖā§āĻā§° āĻ¸ā§āĻ¤ā§ āĻāĻŋāĻāĻ āĻšāĻ¯āĻŧ āĻā§°ā§ āĻāĻĒā§āĻ¨āĻŋ āĻ¯'āĻ¤ā§ āĻ¨āĻžāĻĨāĻžāĻāĻ āĻ¤'āĻ¤ā§āĻ āĻā§āĻ¨ā§ āĻ
āĻĄāĻŋāĻ
'āĻŦā§āĻ āĻ
āĻ¨āĻ˛āĻžāĻāĻ¨ āĻŦāĻž āĻ
āĻĢāĻ˛āĻžāĻāĻ¨āĻ¤ āĻļā§āĻ¨āĻŋāĻŦāĻ˛ā§ āĻ¸ā§āĻŦāĻŋāĻ§āĻž āĻĻāĻŋāĻ¯āĻŧā§āĨ¤
āĻ˛ā§āĻĒāĻāĻĒ āĻā§°ā§ āĻāĻŽā§āĻĒāĻŋāĻāĻāĻžā§°
āĻāĻĒā§āĻ¨āĻŋ āĻāĻŽā§āĻĒāĻŋāĻāĻāĻžā§°ā§° ā§ąā§āĻŦ āĻŦā§āĻ°āĻžāĻāĻāĻžā§° āĻŦā§āĻ¯ā§ąāĻšāĻžā§° āĻā§°āĻŋ Google PlayāĻ¤ āĻāĻŋāĻ¨āĻž āĻ
āĻĄāĻŋāĻ
'āĻŦā§āĻāĻ¸āĻŽā§āĻš āĻļā§āĻ¨āĻŋāĻŦ āĻĒāĻžā§°ā§āĨ¤
āĻ-ā§°ā§āĻĄāĻžā§° āĻā§°ā§ āĻ
āĻ¨ā§āĻ¯ āĻĄāĻŋāĻāĻžāĻāĻ
Kobo eReadersā§° āĻĻā§°ā§ āĻ-āĻāĻŋā§āĻžāĻāĻšā§ā§° āĻĄāĻŋāĻāĻžāĻāĻāĻ¸āĻŽā§āĻšāĻ¤ āĻĒā§āĻŋāĻŦāĻ˛ā§, āĻāĻĒā§āĻ¨āĻŋ āĻāĻāĻž āĻĢāĻžāĻāĻ˛ āĻĄāĻžāĻāĻ¨āĻ˛âāĻĄ āĻā§°āĻŋ āĻ¸ā§āĻāĻā§ āĻāĻĒā§āĻ¨āĻžā§° āĻĄāĻŋāĻāĻžāĻāĻāĻ˛ā§ āĻ¸ā§āĻĨāĻžāĻ¨āĻžāĻ¨ā§āĻ¤ā§°āĻŖ āĻā§°āĻŋāĻŦ āĻ˛āĻžāĻāĻŋāĻŦāĨ¤ āĻ¸āĻŽā§°ā§āĻĨāĻŋāĻ¤ āĻ-ā§°āĻŋāĻĄāĻžā§°āĻ˛ā§ āĻĢāĻžāĻāĻ˛āĻā§ āĻā§āĻ¨ā§āĻā§ āĻ¸ā§āĻĨāĻžāĻ¨āĻžāĻ¨ā§āĻ¤ā§° āĻā§°āĻŋāĻŦ āĻāĻžāĻ¨āĻŋāĻŦāĻ˛ā§ āĻ¸āĻšāĻžāĻ¯āĻŧ āĻā§āĻ¨ā§āĻĻā§ā§°āĻ¤ āĻĨāĻāĻž āĻ¸āĻŦāĻŋāĻļā§āĻˇ āĻ¨āĻŋā§°ā§āĻĻā§āĻļāĻžā§ąāĻ˛ā§ āĻāĻžāĻāĻāĨ¤
