주 메뉴 열기

바뀜

잔글
단, <math>\mathbf{w}_1, \mathbf{w}_2, \dots , \mathbf{w}_N, \mathbf{\alpha}</math>와 <math>\mathbf{\theta}</math>를 잘못 선택하거나 은닉층의 뉴런 수가 부족할 경우 충분한 정확도로 근사하는데 실패할 수 있다.
 
== References참고문헌 ==
* Hassoun, M. (1995) "[http://books.google.co.kr/books?id=Otk32Y3QkxQC&dq=&pg=PP1&ots=d88OaFxcR3&sig=_wJ7N18It-OrMIA2udd4FILRi-Q&prev=http://www.google.co.kr/search%3Fsourceid%3Dnavclient%26hl%3Dko%26ie%3DUTF-8%26rlz%3D1T4GFRI_koKR235KR236%26q%3DFundamentals%2Bof%2BArtificial%2BNeural%2BNetworks&sa=X&oi=print&ct=title Fundamentals of Artificial Neural Networks,]" MIT Press, p.48
* G. [http://actcomm.dartmouth.edu/gvc/ Cybenko], (1989) "[http://actcomm.dartmouth.edu/gvc/papers/approx_by_superposition.pdf Approximation by Superpositions of a Sigmoidal Function]"

편집

176