Rishabh Singh
YOU?
Author Swipe
View article: Fake Product Identification Using Blockchain
Fake Product Identification Using Blockchain Open
bstract: One of the greatest challenges in today's retail market is the counterfeiting of products. Counterfeiting Products are merely low-quality counterfeits of a certain brand. Over time, many different methods have been adopted to prev…
View article: Texas Water Observatory: A Distributed Network for Monitoring Water, Energy, and Carbon Cycles Under Variable Climate and Land Use on Gulf Coast Plains
Texas Water Observatory: A Distributed Network for Monitoring Water, Energy, and Carbon Cycles Under Variable Climate and Land Use on Gulf Coast Plains Open
In the Gulf Coastal Plains of Texas, a state-of-the-art distributed network of field observatories, known as the Texas Water Observatory (TWO), is developed to better understand the water, energy, and carbon cycles across the critical zone…
View article: Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks
Automated Correction for Syntax Errors in Programming Assignments using Recurrent Neural Networks Open
We present a method for automatically generating repair feedback for syntax errors for introductory programming problems. Syntax errors constitute one of the largest classes of errors (34%) in our dataset of student submissions obtained fr…
View article: Analysis and Design of G+15 Building With Connecting Skywalk in Gorakhpur
Analysis and Design of G+15 Building With Connecting Skywalk in Gorakhpur Open
The structural analysis and design of G+15 building with the connection skywalk is done using software StaddPRO V8i. The planning is done in AUTOCAD 2019. The G+15 building with the connection skywalk which connect the two buildings to fac…
View article: Natural Language Processing for Covid-19 Consulting System
Natural Language Processing for Covid-19 Consulting System Open
The world was taken aback when the Covid-19 pandemic hit in 2019. Ever since precautions have been taken to prevent the spreading or mutating of the virus, but the virus still keeps spreading and mutating. Scientists predict that the virus…
View article: Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS
Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS Open
Deep learning models for semantic segmentation are prone to poor performance in real-world applications due to the highly challenging nature of the task. Model uncertainty quantification (UQ) is one way to address this issue of lack of mod…
View article: Robust Dependence Measure using RKHS based Uncertainty Moments and Optimal Transport
Robust Dependence Measure using RKHS based Uncertainty Moments and Optimal Transport Open
Reliable measurement of dependence between variables is essential in many applications of statistics and machine learning. Current approaches for dependence estimation, especially density-based approaches, lack in precision, robustness and…
View article: Screening of Antimicrobial and Antidiabetic Activities of Native and Cultivated Medicinal Plants of India
Screening of Antimicrobial and Antidiabetic Activities of Native and Cultivated Medicinal Plants of India Open
Background and Objective: Chronic health complications such as obesity and diabetes are associated with disrupted energy balance and abnormal glucose metabolism.Traditional and alternative medicinal systems are used to manage obesity and d…
View article: Solving Program Sketches with Large Integer Values
Solving Program Sketches with Large Integer Values Open
Program sketching is a program synthesis paradigm in which the programmer provides a partial program with holes and assertions. The goal of the synthesizer is to automatically find integer values for the holes so that the resulting program…
View article: TF-Coder: Program Synthesis for Tensor Manipulations
TF-Coder: Program Synthesis for Tensor Manipulations Open
The success and popularity of deep learning is on the rise, partially due to powerful deep learning frameworks such as TensorFlow and PyTorch, which make it easier to develop deep learning models. However, these libraries also come with st…
View article: Platt-Bin: Efficient Posterior Calibrated Training for NLP Classifiers
Platt-Bin: Efficient Posterior Calibrated Training for NLP Classifiers Open
Modern NLP classifiers are known to return uncalibrated estimations of class posteriors. Existing methods for posterior calibration rescale the predicted probabilities but often have an adverse impact on final classification accuracy, thus…
View article: Neurosymbolic Programming
Neurosymbolic Programming Open
We survey recent work on neurosymbolic programming, an emerging area that bridges the areas of deep learning and program synthesis. Like in classic machine learning, the goal here is to learn functions from data. However, these functions a…
View article: A Physics inspired Functional Operator for Model Uncertainty Quantification in the RKHS
A Physics inspired Functional Operator for Model Uncertainty Quantification in the RKHS Open
Accurate uncertainty quantification of model predictions is a crucial problem in machine learning. Existing Bayesian methods, being highly iterative, are expensive to implement and often fail to accurately capture a model's true posterior …
View article: Deep Geospatial Interpolation Networks
Deep Geospatial Interpolation Networks Open
Interpolation in Spatio-temporal data has applications in various domains such as climate, transportation, and mining. Spatio-Temporal interpolation is highly challenging due to the complex spatial and temporal relationships. However, trad…
View article: SpreadsheetCoder: Formula Prediction from Semi-structured Context
SpreadsheetCoder: Formula Prediction from Semi-structured Context Open
Spreadsheet formula prediction has been an important program synthesis problem with many real-world applications. Previous works typically utilize input-output examples as the specification for spreadsheet formula synthesis, where each inp…
View article: Impact of encryption and decryption techniques for high speed optical domain
Impact of encryption and decryption techniques for high speed optical domain Open
This project proposes the design of ultrafast communication circuit which can enable the high speed secured data transmission at 50 Gb/s and 100 Gb/s by the use of distributed raman amplifier, erbium–doped fiber amplifier (EDFA), filter, s…
View article: Latent Programmer: Discrete Latent Codes for Program Synthesis
Latent Programmer: Discrete Latent Codes for Program Synthesis Open
In many sequence learning tasks, such as program synthesis and document summarization, a key problem is searching over a large space of possible output sequences. We propose to learn representations of the outputs that are specifically mea…
View article: Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration
Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration Open
Discrete structures play an important role in applications like program language modeling and software engineering. Current approaches to predicting complex structures typically consider autoregressive models for their tractability, with s…
View article: Joy of Learning Through Internet Memes
Joy of Learning Through Internet Memes Open
The currency of today’s social media is influence. The influence is any action or reaction by which you can drive your thoughts on people’s mind through social platforms. Internet memes are getting very popular in today’s generation. With …
View article: Deep Learning & Software Engineering: State of Research and Future Directions.
Deep Learning & Software Engineering: State of Research and Future Directions. Open
Given the current transformative potential of research that sits at the intersection of Deep Learning (DL) and Software Engineering (SE), an NSF-sponsored community workshop was conducted in co-location with the 34th IEEE/ACM International…
View article: Deep Learning & Software Engineering: State of Research and Future Directions
Deep Learning & Software Engineering: State of Research and Future Directions Open
Given the current transformative potential of research that sits at the intersection of Deep Learning (DL) and Software Engineering (SE), an NSF-sponsored community workshop was conducted in co-location with the 34th IEEE/ACM International…
View article: Impact of encryption and decryption techniques for high speed optical domain
Impact of encryption and decryption techniques for high speed optical domain Open
This project proposes the design of ultrafast communication circuit which can enable the high speed secured data transmission at 50 Gb/s and 100 Gb/s by the use of distributed Raman amplifier, EDFA (Erbium – doped fiber amplifier), filter,…
View article: BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration
BUSTLE: Bottom-Up Program Synthesis Through Learning-Guided Exploration Open
Program synthesis is challenging largely because of the difficulty of search in a large space of programs. Human programmers routinely tackle the task of writing complex programs by writing sub-programs and then analyzing their intermediat…