Title Statements
- Full title :Learning deep architectures for AI / Yoshua Bengio.
Edition Statements
- Publication Date:cop. 2009.
Publication Statements
- Publisher(s):Now Publishers
- Place of Publication:Hanover (Massachusetts)
- Language:eng
- Publication Date:cop. 2009.
Notes
Índice abreviado: 1. Introduction 2. Theoretical advantages of deep architectures 3. Local vs non-local generalization 4. Neural networks for deep architectures 5. Energy-based models and Boltzmann machines 6. Greedy layer-wise training of deep architectures 7. Variants of RBMs and auto-encoders 8. Stochastic variational bounds for joint optimization of DBN layers 9. Looking forward 10. Conclusion.
The Physical Object
- Description:131 p. ; : 24 cm.
Edition Identifiers
- ISBN:9781601982940, 1601982941
- oclc:on1026147043
- Dewey Decimal:006.31
Table of Contents
Theoretical advantages of deep architectures -- Local vs non-local generalization -- Neural networks for deep architectures -- Energy-based models and Boltzmann machines -- Greedy layer-wise training of deep architectures -- Variants of RBMs and auto-encoders -- Stochastic variational bounds for joint optimization of DBN layers -- Looking forward.
Read More ↓Subjects
Writers
More from this Series
No reviews yet. Be the first to rate this work.
Related Works
more →
Neural networks with R: smart models using CNN, RNN, deep learn…
Ciabuschi, Francesco
Document processing using machine learning
Machine learning pocket reference: working with structured data in Python
Harrison, Matt
Machine learning pocket reference: working with structured data in Python
Harrison, Matt
Practical time series analysis: master time series data processing, vis…
Pal, Avishek
Visual attributes
Files & Downloads
-
Learning Deep Architectures for AI -- (.pdf)
PDF · 893.6 KB · updated
Rate & Review