• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.

• Korean Journal of Mathematics
• /
• v.24 no.3
• /
• pp.319-330
• /
• 2016

The manifold $^*g-ESX_n$ is a generalized n-dimensional Riemannian manifold on which the differential geometric structure is imposed by the unied eld tensor $^*g^{{\lambda}{\nu}}$ through the ES-connection which is both Einstein and semi-symmetric. The purpose of the present paper is to study the algebraic geometric structures of 5-dimensional $^*g-ESX_5$. Particularly, in 5-dimensional $^*g-ESX_5$, we derive a new set of powerful recurrence relations in the first class.

• Korean Journal of Mathematics
• /
• v.6 no.2
• /
• pp.281-289
• /
• 1998

On a generalized Riemannian manifold $X_n$, we may impose a particular geometric structure by the basic tensor field $g_{\lambda\mu}$ by means of a particular connection ${\Gamma}{_\lambda}{^\nu}_{\mu}$. For example, Einstein's manifold $X_n$ is based on the Einstein's connection defined by the Einstein's equations. Many recurrent connections have been studied by many geometers, such as Datta and Singel, M. Matsumoto, and E.M. Patterson. The purpose of the present paper is to study some relations between a generalized semisymmetric $g$-recurrent manifold $GSX_n$ and its submanifold. All considerations in this present paper deal with the general case $n{\geq}2$ and all possible classes.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.179-185
• /
• 2017

Document summarization aims to generate a summary that is consistent and contains the highly related sentences in a document. In this study, we implemented for document summarization that extracts highly related sentences from a whole document by considering both similarities and entailment relations between sentences. Accordingly, we proposed a new algorithm, TextRank-NLI, which combines a Recurrent Neural Network based Natural Language Inference model and a Graph-based ranking algorithm used in single document extraction-based summarization task. In order to evaluate the performance of the new algorithm, we conducted experiments using the same datasets as used in TextRank algorithm. The results indicated that TextRank-NLI showed 2.3% improvement in performance, as compared to TextRank.

• Communications of the Korean Mathematical Society
• /
• v.12 no.2
• /
• pp.383-391
• /
• 1997

The main purpose of the present paper is to derive the induced (Finsler) connections on the hypersurface from the Finsler connections of Berwald type (a Berwald h-recurrent connection and a $F\Gamma$' connection) of a Finsler space and to seek the necessary and sufficient conditions that the induced connections coincide with the intrinsic connections. And we show the quantities and relations with respect to the respective induced connections. Finally we show some examples.

• Journal of the Korean Mathematical Society
• /
• v.52 no.1
• /
• pp.23-41
• /
• 2015

We present a semilocal convergence analysis of a third order method for approximating a locally unique solution of an equation in a Banach space setting. Recently, this method was studied by Chun, Stanica and Neta. These authors extended earlier results by Kou, Li and others. Our convergence analysis extends the applicability of these methods under less computational cost and weaker convergence criteria. Numerical examples are also presented to show that the earlier results cannot apply to solve these equations.

• Korean Journal of Mathematics
• /
• v.22 no.1
• /
• pp.207-216
• /
• 2014

The manifold $^*g-ESX_n$ is a generalized n-dimensional Riemannian manifold on which the differential geometric structure is imposed by the unified field tensor $^*g^{{\lambda}{\nu}}$ through the ES-connection which is both Einstein and semi-symmetric. The purpose of the present paper is to study the algebraic geometric structures of 3-dimensional $^*g-ESX_3$. Particularly, in 3-dimensional $^*g-ESX_3$, we derive a new set of powerful recurrence relations in the first class.

• Bulletin of the Korean Mathematical Society
• /
• v.57 no.4
• /
• pp.1033-1048
• /
• 2020

We synthesize the recent work done on conditionally defined Lucas and Fibonacci numbers, tying together various definitions and results generalizing the linear recurrence relation. Allowing for any initial conditions, we determine the generating function and a Binet-like formula for the general sequence, in both the positive and negative directions, as well as relations among various sequence pairs. We also determine conditions for periodicity of these sequences and graph some recurrent figures in Python.

• Korean Journal of Mathematics
• /
• v.18 no.2
• /
• pp.133-139
• /
• 2010

The manifold $g-ESX_n$ is a generalized n-dimensional Riemannian manifold on which the differential geometric structure is imposed by the unified field tensor $g_{{\lambda}{\mu}}$ through the ES-connection which is both Einstein and semi-symmetric. In this paper, we investigate the properties of the vectors $X_{\lambda}$, $S_{\lambda}$ and $U_{\lambda}$ of $g-ESX_n$, with main emphasis on the derivation of several useful generalized identities involving it.

• Analyses & Alternatives
• /
• v.4 no.2
• /
• pp.163-202
• /
• 2020

This paper examines how Japanese society produced and reproduced a distinctively gendered history and memories of the experience of WWII and colonialism in the postwar era. We argue that these gendered narratives, which were embedded in postwar debates about the Peace Constitution and comfort women, have engendered contradictions and made the historical conflicts with neighboring countries challenging to resolve. On the one hand, this deepens conflict, but on the other, it also generates stability in East Asia. After Japan's defeat in WWII, the American Occupation government created the Peace Constitution, which permanently "renounces war as a sovereign right of the nation and the threat or use of force as means of settling international disputes." The removal of the state's monopoly on violence - the symbol of masculinity - resulted in Japan's feminization. This feminization led to collective forgetting of prewar imperialism and militarism in postwar Japan. While collectively forgetting the wartime history of comfort women within these feminized narratives, the conservative movement to revise the Peace Constitution attempted to recover Japan's masculinity for a new, autonomous role in international politics, as uncertainty in East Asia increased. Ironically, however, this effort strengthened Japan's femininity because it involved forgetting Japan's masculine role in the past. This forgetting has undermined efforts to achieve masculine independence, thus reinforcing dependence on the United States. Recurrent debates about the Peace Constitution and comfort women have influenced how Japanese political elites and intellectual society have constructed distinctive social institutions, imagined foreign relations, and framed contemporary problems, as indicated in their gendered restructuring of history.