Search Results for author:
Found 44 papers, 12 papers with code
Team AINLPML @ MuP in SDP 2021: Scientific Document Summarization by End-to-End Extractive and Abstractive Approach
This paper introduces the proposed summarization system of the AINLPML team for the First Shared Task on Multi-Perspective Scientific Document Summarization at SDP 2022.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we present the latest model of the Gemini family, Gemini 1. 5 Pro, a highly compute-efficient multimodal mixture-of-experts model capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #19 on
Code Generation
on HumanEval
From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility
This groundbreaking study explores the expanse of Large Language Models (LLMs), such as Generative Pre-Trained Transformer (GPT) and Bidirectional Encoder Representations from Transformers (BERT) across varied domains ranging from technology, finance, healthcare to education.
GRAPHGINI: Fostering Individual and Group Fairness in Graph Neural Networks
Extensive experimentation on real-world datasets showcases the efficacy of GRAPHGINI in making significant improvements in individual fairness compared to all currently available state-of-the-art methods while maintaining utility and group equality.
A Comprehensive Review on Computer Vision Analysis of Aerial Data
With the emergence of new technologies in the field of airborne platforms and imaging sensors, aerial data analysis is becoming very popular, capitalizing on its advantages over land data.
Best practices for machine learning in antibody discovery and development
Over the past few years, we have observed rapid developments in the field of ML-guided antibody discovery and development (D&D).
No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation
However, integrating these graph models into the Federated Learning (FL) paradigm with fairness constraints poses formidable challenges as this requires access to the entire interaction graph and sensitive user information (such as gender, age, etc.)
When Reviewers Lock Horn: Finding Disagreement in Scientific Peer Reviews
To the best of our knowledge, we make the first attempt to identify disagreements among peer reviewers automatically.
An abstractive text summarization technique using transformer model with self-attention mechanism
The proposed model gives the training loss minimum to 1. 8220 from 10. 3058 (at the starting point) up to 30 epochs, and it achieved model accuracy 48. 50% F1-Score on both the Inshorts and DUC-2004 news datasets.
Ranked #1 on
Abstractive Text Summarization
on Inshorts News
Free Lunch for Privacy Preserving Distributed Graph Learning
Through extensive experimentation on both synthetic and real datasets, we demonstrate the efficacy of the framework in terms of comparing the results obtained without data sharing to those obtained with data sharing as a benchmark.
Inhibitory feedback from the motor circuit gates mechanosensory processing in C. elegans
Inhibiting neurons SAA, RIV and SMB during a turn restores the likelihood with which mechanosensory activation evokes reversals.
Forecasting formation of a Tropical Cyclone Using Reanalysis Data
In this study, a deep learning model has been proposed that can forecast the formation of a tropical cyclone with a lead time of up to 60 hours with high accuracy.
A Unified Framework for Optimization-Based Graph Coarsening
In this paper, we introduce a novel optimization-based framework for graph dimensionality reduction.
Enhancement to Training of Bidirectional GAN : An Approach to Demystify Tax Fraud
To validate the proposed approach, we train a BiGAN with the proposed training approach to detect taxpayers, who are manipulating their tax returns.
Robust Graph Neural Networks using Weighted Graph Laplacian
For demonstration, the experiments are conducted with Graph convolutional neural network(GCNN) architecture, however, the proposed framework is easily amenable to any existing GNN architecture.
Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique
Deep learning researchers have a keen interest in proposing new novel activation functions that can boost neural network performance.
SMU: smooth activation function for deep networks using smoothing maximum technique
A good choice of activation function can have significant consequences in improving network performance.
SAU: Smooth activation function using convolution with approximate identities
Well-known activation functions like ReLU or Leaky ReLU are non-differentiable at the origin.
Closed-loop targeted optogenetic stimulation of C. elegans populations
The instrument addresses three technical challenges: it delivers targeted illumination to specified regions of the animal's body such as its head or tail; it automatically delivers stimuli triggered upon the animal's behavior; and it achieves high throughput by targeting many animals simultaneously.
ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions
An activation function is a crucial component of a neural network that introduces non-linearity in the network.
INNOVATORS at SemEval-2021 Task-11: A Dependency Parsing and BERT-based model for Extracting Contribution Knowledge from Scientific Papers
In this work, we describe our system submission to the SemEval 2021 Task 11: NLP Contribution Graph Challenge.
Tropical cyclone intensity estimations over the Indian ocean using Machine Learning
We use multi-class classification models for the categorical outcome variable, cyclone grade, and regression models for MSWS as it is a continuous variable.
Intensity Prediction of Tropical Cyclones using Long Short-Term Memory Network
Therefore, the prediction of the intensity of tropical cyclones advance in time is of utmost importance.
Prediction of Landfall Intensity, Location, and Time of a Tropical Cyclone
The model takes as input the best track data of cyclone consisting of its location, pressure, sea surface temperature, and intensity for certain hours (from 12 to 36 hours) anytime during the course of the cyclone as a time series and then provide predictions with high accuracy.
Predicting Landfall's Location and Time of a Tropical Cyclone Using Reanalysis Data
Landfall of a tropical cyclone is the event when it moves over the land after crossing the coast of the ocean.
Static and Dynamical, Fractional Uncertainty Principles
We study the process of dispersion of low-regularity solutions to the Schr\"odinger equation using fractional weights (observables).
Analysis of PDEs 35J10, 35B99
EIS -- a family of activation functions combining Exponential, ISRU, and Softplus
In recent years, several novel activation functions arising from these basic functions have been proposed, which have improved accuracy in some challenging datasets.
TanhSoft -- a family of activation functions combining Tanh and Softplus
Deep learning at its core, contains functions that are composition of a linear transformation with a non-linear function known as activation function.
A Novel GDP Prediction Technique based on Transfer Learning using CO2 Emission Dataset
In the last 150 years, CO2 concentration in the atmosphere has increased from 280 parts per million to 400 parts per million.
Deep Bayesian Network for Visual Question Generation
This is a Bayesian framework and the results show a remarkable similarity to natural questions as validated by a human study.
Structured Graph Learning Via Laplacian Spectral Constraints
Then we introduce a unified graph learning framework, lying at the integration of the spectral properties of the Laplacian matrix with Gaussian graphical modeling that is capable of learning structures of a large class of graph families.
Distributed Inexact Successive Convex Approximation ADMM: Analysis-Part I
Different from a number of existing approaches, however, the proposed framework is flexible enough to incorporate a class of non-convex objective functions, allow distributed operation with and without a fusion center, and include variance reduced methods as special cases.
A Unified Framework for Structured Graph Learning via Spectral Constraints
Then we develop an optimization framework that leverages graph learning with specific structures via spectral constraints on graph matrices.
Moonshots for aging
As the global population ages, there is increased interest in living longer and improving one's quality of life in later years.
Multimodal Differential Network for Visual Question Generation
Generating natural questions from an image is a semantic task that requires using visual and language modality to learn multimodal representations.
Live Detection of Face Using Machine Learning with Multi-feature Method
This research proposed a new algorithm for automatic live FED using radial basis function; Haar discrete wavelet transform and Gray-level difference method is used for feature extraction and classification.
Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator
One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.
Design and Implementation of Modified Fuzzy based CPU Scheduling Algorithm
Scheduling is a process which decides order of task from a set of multiple tasks that are ready to execute.
Stochastic Multidimensional Scaling
Multidimensional scaling (MDS) is a popular dimensionality reduction techniques that has been widely used for network visualization and cooperative localization.
Performance Tuning of Hadoop MapReduce: A Noisy Gradient Approach
Our method, when tested on a 25 node Hadoop cluster shows 66\% decrease in execution time of Hadoop jobs on an average, when compared to the default configuration.
Memetic Search in Differential Evolution Algorithm
The proposed strategy is named as Memetic Search in Differential Evolution (MSDE).
Randomized Memetic Artificial Bee Colony Algorithm
In order to balance between diversification and intensification capability of the Memetic ABC, it is randomized the step size in Memetic ABC.
Improved Onlooker Bee Phase in Artificial Bee Colony Algorithm
Artificial Bee Colony (ABC) is a distinguished optimization strategy that can resolve nonlinear and multifaceted problems.
A Novel Hybrid Crossover based Artificial Bee Colony Algorithm for Optimization Problem
ABC has been proved its superiority over some other Nature Inspired Algorithms (NIA) when applied for both benchmark functions and real world problems.
