ISI Digital Commons (Indian Statistical Institute )
Not a member yet
7571 research outputs found
Sort by
A1-connected components and characterisation of A2
No full textIn this article, we prove that any A1-contractible smooth complex surface is isomorphic as a variety to C2. We show that the A1-connected component of a variety X contains the information about A1’s in X
Adaptive Nonstationary Fuzzy Neural Network
No full textFuzzy neural network (FNN) plays an important role as an inference system in practical applications. To enhance its ability of handling uncertainty without invoking high computational cost, and to take variations in rules into consideration as well, we propose a new inference framework—nonstationary fuzzy neural network (NFNN). This NFNN is composed of a series of zero-order TSK FNNs with the same structure but using slightly perturbed fuzzy sets in the corresponding neurons, which is inspired from the non-stationary fuzzy sets and can mimic the variation in human\u27s decision-making process. In order to obtain a concise and adaptive rule base for NFNN, a modified affinity propagation (MAP) clustering method is proposed. The MAP can determine the number of rules in an adaptive manner, and is used to initialize the rule parameters of NFNN, which we call Adaptive NFNN (ANFNN). Numerical experiments have been carried out over 17 classification datasets and three regression datasets. The experimental results demonstrate that ANFNN exhibits better accuracy, generalization ability, and fault-tolerance ability compared with the classical type-1 fuzzy neural network. In 15 of the 17 classification datasets, ANFNN achieves the same or better accuracy performance compared to interval type-2 FNNs with about half time consumed. This work confirms the feasibility of integrating simple-structured type-1 TSK FNNs to achieve the performance of interval type-2 FNNs, and proves that ANFNN can be a more accurate and reliable alternative to classical type-1 FNN
Association between neonatal mortality and births not weighed among 400 thousand institutional deliveries in 32 low- and middle-income countries
No full textBackground: Low birthweight (LBW) children have a higher risk of neonatal mortality. All institutional deliveries, therefore, should be weighed to determine appropriate care. Mortality risk for newborns who are not weighed at birth (NWB) is unknown. Methods: This paper used logit regression models to compare the odds of death for NWB neonates to that of other neonates using data on 401 712 institutional births collected in Demographic and Health Surveys from 32 low- and middle-income countries. Results: In the pooled sample, 2.3% died in the neonatal period and 12% were NWB. NWB neonates had a high risk of mortality compared to normal birthweight children (Adjusted odds ratio [AOR] 5.8, 95% CI: 5.3, 6.5). The mortality risk associated with NWB was higher than for LBW. The neonatal mortality risk associated with NWB varied across countries from AOR of 2.1 (95% CI: 1.22, 3.8) in Afghanistan to 94 (95% CI: 22, 215) in Gabon. In the pooled sample, the 12% of children who were NWB accounted for 37% of all neonatal deaths. Conclusions: The association between NWB and neonatal mortality may suggest a need to focus on the quality of institutions related to newborn care. However, further studies are needed to determine causality. A health emergency or death may also cause NWB
Automorphisms and generalized projections on spaces of analytic functions
No full textWe present complete classifications of automorphisms of two closed subalgebras of the space of bounded analytic functions on the open unit disc D, namely, the subalgebra of functions vanishing at the origin, and the subalgebra of functions whose first derivative vanishes at the origin. The later subalgebra is known as the Neil algebra. We also characterize generalized tri-circular projections on Hp(D) and Hp(D2), 1≤p≤∞, p≠2
Bertini Type Results and Their Applications: Bertini Type Results and Their Applications: I. Biswas et al.
No full textWe prove Bertini type theorems and give some applications of them. The applications are in the context of Lefschetz theorem for Nori fundamental group for normal varieties as well as for geometric formal orbifolds. In another application, it is shown that a certain class of a smooth quasi-projective variety contains a smooth curve such that irreducible lisse ℓ–adic sheaves on the variety with “ramification bounded by a branch data” remains irreducible when restricted to the curve
Cluster formation due to repulsive spanning trees in attractively coupled networks
No full textEnsembles of coupled nonlinear oscillators are a popular paradigm and an ideal benchmark for analyzing complex collective behaviors. The onset of cluster synchronization is found to be at the core of various technological and biological processes. The current literature has investigated cluster synchronization by focusing mostly on the case of attractive coupling among the oscillators. However, the case of two coexisting competing interactions is of practical interest due to their relevance in diverse natural settings, including neuronal networks consisting of excitatory and inhibitory neurons, the coevolving social model with voters of opposite opinions, and ecological plant communities with both facilitation and competition, to name a few. In the present article, we investigate the impact of repulsive spanning trees on cluster formation within a connected network of attractively coupled limit-cycle oscillators. We successfully predict which nodes belong to each cluster and the emergent frustration of the connected networks independent of the particular local dynamics at the network nodes. We also determine local asymptotic stability of the cluster states using an approach based on the formulation of a master stability function. We additionally validate the emergence of solitary states and antisynchronization for some specific choices of spanning trees and networks
COMPUTING SQUARE ROOTS FASTER THAN THE TONELLI-SHANKS/BERNSTEIN ALGORITHM
No full textLet p be a prime such that p = 1+2n m, where n ≥ 1 and m is odd. Given a square u in Zp and a non-square z in Zp, we describe an algorithm to compute a square root of u which requires T + O(n3/2) operations (i.e., squarings and multiplications), where T is the number of operations required to exponentiate an element of Zp to the power (m−1)/2. This improves upon the Tonelli-Shanks (TS) algorithm which requires T + O(n2) operations. Bernstein had proposed a table look-up based variant of the TS algorithm which requires T + O((n/w)2) operations and O(2w n/w) storage, where w is a parameter. A table look-up variant of the new algorithm requires T+O((n/w)3/2) operations and the same storage. In concrete terms, the new algorithm is shown to require significantly fewer operations for particular values of n
Compositional Zero-Shot Learning using Multi-Branch Graph Convolution and Cross-layer Knowledge Sharing
No full textThe purpose of the Compositional Zero-Shot Learning (CZSL) is to recognize new state-object compositions of known objects and known states. For example, the CZSL model should recognize young cat when the model has seen images of a few state-object compositions like young tiger, old tiger and old cat. The visual features of a state may have significant variation across different compositions of the state with different objects. For example, in the compositions peeled apple and peeled orange, the state peeled has different visual features. This context dependency of state features is difficult to learn from the annotated images of different compositions. We propose a Graph Convolutional Network (GCN) with two distinct branches for object and state recognition. GCN utilizes its ability to aggregate features from the non-Euclidean neighbourhood. This aggregation ability of GCN can help our model to capture the intricate dependencies between visual features of state and object. We also propose a novel cross-layer knowledge sharing strategy for the purpose of reducing ambiguity in learning state features due to context dependency. The proposed cross-layer knowledge sharing helps in identifying a set of objects having feasible compositions with a particular state and thereby reducing the ambiguity in the state features. Finally, we propose a feasibility based penalization to better regularize the joint prediction from the two branches of the network. The proposed algorithm is evaluated on the challenging benchmarks and competitive results in comparison to state-of-the-art algorithms have been achieved
CONTROLLED MARTINGALE PROBLEMS AND THEIR MARKOV MIMICS
No full textIn this article we prove under suitable assumptions that the marginals of any solution to a relaxed controlled martingale problem on a Polish space E can be mimicked by a Markovian solution of a Markov-relaxed controlled martingale problem. We also show how such Markov mimics\u27\u27 can be obtained by relative entropy minimization. We provide many examples where the above results can be applied
Deep learning models for perception of brightness related illusions
No full textIllusions are like holes in our effortless visual mechanism through which we can peep into the internal mechanisms of the brain. Scientists attempted to explain underlying physiological, physical, and cognitive mechanisms of illusions by the receptive field hierarchical organizations, information sampling, filtering, etc. Some antagonistic illusions cannot be explained by them and for this, deep learning networks were used recently as a model for illusion perception. To further broaden the scope of the perceptual functionality in the brightness contrast genre, handle the background removal effects on some illusions that reduce the illusory effects, and replicate the antagonistic illusions with the same parameter setup, we have used Convolutional Neural Network, Autoencoder, U-Net, and U-Net++ models for replicating the visual illusions. The networks are specialized in low-level vision tasks like De-noising, De-blurring, and a combination of both. A high number of brightness contrast visual illusions are tested on all the networks and most of the outcomes significantly matched human perceptions. Overall, our method will guide the development of neurobiological frameworks which might enrich the computational neuroscience study by distilling some biological principles. On the other hand, the machine learning community will benefit from knowing the inherent flaws of the networks so that the true image of reality can be taken into consideration, especially in imaging situations where experts too can be deceived