دورية أكاديمية
Building on prior knowledge without building it in
العنوان: | Building on prior knowledge without building it in |
---|---|
المؤلفون: | Hansen, Steven S., Lampinen, Andrew K., Suri, Gaurav, McClelland, James L. |
المصدر: | Behavioral and Brain Sciences ; volume 40 ; ISSN 0140-525X 1469-1825 |
بيانات النشر: | Cambridge University Press (CUP) |
سنة النشر: | 2017 |
مصطلحات موضوعية: | Behavioral Neuroscience, Physiology, Neuropsychology and Physiological Psychology |
الوصف: | Lake et al. propose that people rely on “start-up software,” “causal models,” and “intuitive theories” built using compositional representations to learn new tasks more efficiently than some deep neural network models. We highlight the many drawbacks of a commitment to compositional representations and describe our continuing effort to explore how the ability to build on prior knowledge and to learn new tasks efficiently could arise through learning in deep neural networks. |
نوع الوثيقة: | article in journal/newspaper |
اللغة: | English |
DOI: | 10.1017/s0140525x17000176 |
الإتاحة: | https://doi.org/10.1017/s0140525x17000176Test https://www.cambridge.org/core/services/aop-cambridge-core/content/view/S0140525X17000176Test |
حقوق: | https://www.cambridge.org/core/termsTest |
رقم الانضمام: | edsbas.6E60011D |
قاعدة البيانات: | BASE |
DOI: | 10.1017/s0140525x17000176 |
---|