Learning Picture Languages Using Dimensional Reduction
نویسندگان
چکیده
One-dimensional (string) formal languages and their learning have been studied in considerable depth. However, the knowledge of two-dimensional (picture) counterpart, which retains similar importance, is lacking. We investigate problem picture by applying methods for one-dimensional languages. formalize transcription process from a input into string propose few adaptations to it. These proposals are then tested series experiments, outcomes compared. Finally, these applied practical an automaton recognizing part MNIST dataset learned. The obtained results show improvements topic potential use automata fitting problems.
منابع مشابه
On Reversal-Bounded Picture Languages
Kim, C. and I.H. Sudborough, On reversal-bounded picture languages, Theoretical Computer Science 104 (1992) 185-206. For an integer k >O, a k-reversal-bounded picture language is a chain-code picture language which is described by a language L over the alphabet R= {u,d,r, I} such that, for every word x in L, the number of alternating occurrences of r’s and I’s in x is bounded by k. It is shown ...
متن کاملOn Some Recognizable Picture-Languages
We show that the language of pictures over fa; bg, where all occurring b's are connected is recognizable, which solves an open problem in Mat98]. We generalize the used construction to show that monocausal deterministically recognizable picture languages are recognizable, which is surprisingly nontrivial. Furthermore we show that the language of pictures over fa; bg, where the number of a's is ...
متن کاملLearning regular languages using RFSAs
Residual languages are important and natural components of regular languages and several grammatical inference algorithms naturally rely on this notion. In order to identify a given target language L, classical inference algorithms try to identify words which de/ne identical residual languages of L. Here, we study whether it could be interesting to perform a tighter analysis by identifying incl...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Inteligencia artificial
سال: 2023
ISSN: ['1988-3064', '1137-3601']
DOI: https://doi.org/10.4114/intartif.vol26iss71pp59-74