Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ max-min activation functions have been a subject of interest in recent years. Since max-min functions are not strictly dif
β¦ LIBER β¦
Learning in recurrent neural networks
β Scribed by Halbert White
- Book ID
- 107908819
- Publisher
- Elsevier Science
- Year
- 1991
- Tongue
- English
- Weight
- 85 KB
- Volume
- 22
- Category
- Article
- ISSN
- 0165-4896
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Effective learning in recurrent maxβmin
β
Loo-Nin Teow; Kia-Fock Loe
π
Article
π
1998
π
Elsevier Science
π
English
β 208 KB
Learning as a nonlinear line of attracti
β
Ming-Jung Seow; Vijayan K. Asari; Adam Livingston
π
Article
π
2009
π
Springer-Verlag
π
English
β 421 KB
How embedded memory in recurrent neural
β
Tsungnan Lin; Bill G. Horne; C.Lee Giles
π
Article
π
1998
π
Elsevier Science
π
English
β 202 KB
Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than conventional recurrent neural networks for learning certain simple long-term dependen
Stable reinforcement learning with recur
β
James Nate Knight; Charles Anderson
π
Article
π
2011
π
South China University of Technology and Academy o
π
English
β 375 KB
A realtime learning algorithm for recurr
β
Tadasu Uchiyama; Katsunori Shimohara
π
Article
π
1991
π
John Wiley and Sons
π
English
β 438 KB
A recurrent perceptron learning algorith
β
C. GΓΌzeliΕ; S. Karamamut; Δ°. GenΓ§
π
Article
π
1999
π
Springer
π
English
β 560 KB