Abstract

Handwritten documents are often characterized by dense and uneven layout. Despite advances, standard deep network based approaches for semantic layout segmentation are not robust to complex deformations seen across semantic regions. This phenomenon is especially pronounced for the low-resource Indic palm-leaf manuscript domain. To address the issue, we first introduce Indiscapes2, a new large-scale diverse dataset of Indic manuscripts with semantic layout annotations. Indiscapes2 contains documents from four different historical collections and is 150% larger than its predecessor, Indiscapes. We also propose a novel deep network Palmira for robust, deformation-aware instance segmentation of regions in handwritten manuscripts. We also report Hausdorff distance and its variants as a boundary-aware performance measure. Our experiments demonstrate that Palmira provides robust layouts, outperforms strong baseline approaches and ablative variants. We also include qualitative results on Arabic, South-East Asian and Hebrew historical manuscripts to showcase the generalization capability of Palmira .

Abstract

We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involved modalities (visual, language). The inter-modal constraints are defined between action sequence embedding and embeddings of Parts of Speech (PoS) tagged words in the corresponding action description. We deploy SynSE for the task of skeleton-based action sequence recognition. Our design choices enable SynSE to generalize compositionally, i.e., recognize sequences whose action descriptions contain words not encountered during training. We also extend our approach to the more challenging Generalized Zero-Shot Learning (GZSL) problem via a confidence-based gating mechanism. We are the first to present zero-shot skeleton action recognition results on the largescale NTU-60 and NTU-120 skeleton action datasets with multiple splits. Our results demonstrate SynSE’s state of the art performance in both ZSL and GZSL settings compared to strong baselines on the NTU-60 and NTU-120 datasets.

Abstract

In many works, the problem of extractive summarisation has been framed as the problem of extracting the best summary from a given document. Many popular recent works aim to solve this by employing neural networks. And many of them are trained using a very limited scope, for example, a vast majority of the neural models are trained only using the best summary. Some also consider pruning useless summaries using other models. In this work, we show the problems that can arise when training neural models using such methods. We analyse those problems in some major milestones in Neural Extractive Summarisation. We also show and demonstrate ways to overcome them experimentally. Keywords: Extractive Summarisation · training bias

Abstract

Machine learning (ML) has been increasingly adopted due to its ability to model complex and nonlinearities between river water temperature (RWT) and its predictors (e.g., Air Temperature, AT). Most of these ML approaches have been applied using average AT without any detailed sensitivity analysis of other forms of AT (e.g., maximum and minimum). The present study demonstrates how new ML approaches, such as ridge regression (RR), K-nearest neighbors (KNN) regressor, random forest (RF) regressor, and support vector regression (SVR), can be coupled with Sobol’ global sensitivity analysis (GSA) to predict accurate RWT estimates with the most appropriate form of AT. Furthermore, the proposed ML approaches have been combined with the Ensemble Kalman Filter (EnKF), a data assimilation (DA) technique to improve the predicted values based on the measured data. The proposed modelling framework’s effectiveness is demonstrated with a tropical river system of India, Tunga-Bhadra River, as a case study. The SVR has been noted as the most robust ML model to predict RWT at a monthly time scale compared with daily and seasonal. The study demonstrates how ML methods can be coupled with a global sensitivity algorithm and DA techniques to generate accurate RWT predictions in river water quality modelling.

Abstract

A structure-based drug design pipeline involves the development of potential drug molecules or ligands that form stable complexes with a given receptor at its binding site. A prerequisite to this is finding druggable and functionally relevant binding sites on the 3D structure of the protein. Although several methods for detecting binding sites have been developed beforehand, a majority of them surprisingly fail in the identification and ranking of binding sites accurately. The rapid adoption and success of deep learning algorithms in various sections of structural biology beckons the usage of such algorithms for accurate binding site detection. As a combination of geometry based software and deep learning, we report a novel framework, DeepPocket that utilises 3D convolutional neural networks for the rescoring of pockets identified by Fpocket and further segments these identified cavities on the protein surface. Apart from this, we also propose another dataset SC6K containing protein structures submitted in the Protein Data Bank (PDB) from 1st January, 2018 till 28th February, 2020 for ligand binding site (LBS) detection. DeepPocket’s results on various binding site datasets and SC6K highlights its better

Abstract

Protein-drug interactions play important roles in many biological processes and therapeutics. Prediction of the active binding site of a protein helps discover and optimise these interactions leading to the design of better ligand molecules. The tertiary structure of a protein determines the binding sites available to the drug molecule. A quick and accurate prediction of the binding site from sequence alone without utilising the three-dimensional structure is challenging. Deep Learning has been used in a variety of biochemical tasks and has been hugely successful. In this paper, a Residual Neural Network (leveraging skip connections) is implemented to predict a protein's most active binding site. An Annotated Database of Druggable Binding Sites from the Protein DataBank, sc-PDB, is used for training the network. Features extracted from the Multiple Sequence Alignments (MSAs) of the protein generated using DeepMSA, such as Position-Specic Scoring Matrix (PSSM), Secondary Structure (SS3), and Relative Solvent Accessibility (RSA), are provided as input to the network. A weighted binary cross-entropy loss function is used to counter the substantial imbalance in the

Abstract

— In this paper, we address the highly challenging problem of object goal navigation. The agent, in an unseen environment, has to perceive its surroundings to identify and navigate towards potential regions where the specified goal category can occur. Rather than developing goal driven exploration policies, we aim to adapt the existing exploration policies that maximize scene coverage to be goal-conditioned. Thus, we propose a standalone scene understanding module to identify potential regions where the goal occurs. We also propose Goal-Conditioned Exploration (GCExp), an algorithm that entails the integration of our novel scene understanding module with any existing exploration policy. We test our solution in photo-realistic simulation environments using stateof-the-art exploration policy, Active Neural Slam [1], and show improved performance over the same on every evaluation metric.

Abstract

Synthetic ion channels are a promising technology in the medical and materials sciences because of their ability to conduct ions. Channels based on cyclodextrin, a cyclic oligomer of glucose, are of particular interest because of their non-toxicity and bio-compatibility. Using molecular dynamics-based free energy calculations, this study identifies cyclodextrin channel types that are best suited to serve as synthetic ion channels. Free energy profiles show that the connectivity in the channel determines whether the channel is cation-selective or anion-selective. Furthermore, the energy barrier for ion transport is governed by the number of glucose molecules constituting the cyclodextrin units of the channel. A detailed mechanism is proposed for ion transport through these channels. Findings from this study will aid in designing cyclodextrinbased channels that could be either cation-selective or anion-selective, by modifying the linkages of the channel or the number of glucose molecules in the cyclodextrin rings.

Abstract

In this chapter, we introduce Hopfield neural networks based on the ceiling neuron model. Inspired by the binary Hopfield neural network and by the definition of ceiling neuron, we propose an extension of the Hopfield neural network from a binary set of possible states of a real-valued neuron to a multistate set. We investigate the dynamics of the proposed model in asynchronous and synchronous update modes. Computational experiments illustrate that the Hopfield neural network based on the ceiling neuron in an asynchronous update mode always settles down to a stationary state under the usual conditions on synaptic weights, that is, the synaptic weight matrix is symmetric with non-negative diagonal elements. In turn, the Hopfield neural network with ceiling neurons in the synchronous update mode can generate limit cycles, similarly to the classic Hopfield neural network.

Abstract

In this research paper storage as well as retrieval of 1-D/2-D/3-D information using Hopfield type Associative Memories (AMs) is discussed. Various Artificial Neural Networks(ANN) architectures are proposed. Also, implementational issues associated with those Associative Memories are discussed. Cascade connection of AM and Convolutional Neural Network is proposed for noise immunity. Keywords: Associative Memories, Hopfield Network, Ceiling Neuron