Deep learning for AI
Глубокое обучение для искусственного интеллекта
2021-06-21
SCID: 54.1/vkswvucq
Discuss with AI
deep learninginternal representationslanguage understandingneural networksobject recognition
Figures from the paper
Abstract (AI)
How can neural networks learn the rich internal representations required for difficult tasks such as recognizing objects or understanding language?
Key Findings
1
Object recognition and language understanding are highlighted as representative tasks requiring advanced internal representations.
2
The abstract identifies learning rich internal representations as a central challenge for neural networks tackling difficult tasks.
3
The provided abstract poses a research question but reports no specific method, experiment, quantitative result, or limitation.
Research Object
Neural networks
Research Subject
Learning rich internal representations for difficult tasks such as object recognition and language understanding
Publication Details
Publication Date
2021-06-21
Journal
Publisher
ISSN
Cited by
798
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
ImageNet classification with deep convolutional neural networks2017
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
ImageNet: A large-scale hierarchical image database2009
Gradient-based learning applied to document recognition1998
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
Reducing the Dimensionality of Data with Neural Networks2006
Neural Machine Translation by Jointly Learning to Align and Translate2014
Intriguing properties of neural networks2013
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
Improving neural networks by preventing co-adaptation of feature detectors2012
A Theory of Causal Learning in Children: Causal Maps and Bayes Nets.2004