Naveen Panwar
YOU?
Author Swipe
View article: SPASE: SPAtial Saliency Explanation for time series models in Microsoft Azure products
SPASE: SPAtial Saliency Explanation for time series models in Microsoft Azure products Open
We have seen recent advances in the field of Machine Learning (ML), Deep Learning (DL), and Artificial intelligence (AI) that the models are becoming increasingly complex and large in terms of architecture and parameter size. These complex…
View article: Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets
Data Quality Toolkit: Automatic assessment of data quality and remediation for machine learning datasets Open
The quality of training data has a huge impact on the efficiency, accuracy and complexity of machine learning tasks. Various tools and techniques are available that assess data quality with respect to general cleaning and profiling checks.…
View article: Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text
Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text Open
Machine Learning has seen tremendous growth recently, which has led to a larger adaptation of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP s…
View article: Generate Your Counterfactuals: Towards Controlled Counterfactual\n Generation for Text
Generate Your Counterfactuals: Towards Controlled Counterfactual\n Generation for Text Open
Machine Learning has seen tremendous growth recently, which has led to larger\nadoption of ML systems for educational assessments, credit risk, healthcare,\nemployment, criminal justice, to name a few. The trustworthiness of ML and NLP\nsy…
View article: Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text
Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text Open
Machine Learning has seen tremendous growth recently, which has led to larger adoption of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP syste…
View article: Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks
Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks Open
Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protecte…
View article: Study of modifiable risk factors associated with learning abilities in MBBS students
Study of modifiable risk factors associated with learning abilities in MBBS students Open
Study of modifiable risk factors associated with learning abilities in MBBS students - JCHM- Print ISSN No: - 2394-272X Online ISSN No:- 2394-2738 Article DOI No:- 10.18231/j.jchm.2019.022, The Journal of Community Health Management-J Comm…
View article: A visual programming paradigm for abstract deep learning model development
A visual programming paradigm for abstract deep learning model development Open
Deep learning is one of the fastest growing technologies in computer science with a plethora of applications. But this unprecedented growth has so far been limited to the consumption of deep learning experts. The primary challenge being a …
View article: An age and gender-based analysis of ‘Metacognitive Awareness Inventory’ (MCAI) among first-year MBBS students from a Central Indian medical college
An age and gender-based analysis of ‘Metacognitive Awareness Inventory’ (MCAI) among first-year MBBS students from a Central Indian medical college Open
Introduction: Cognition includes all mental processes and abilities which help to generate new knowledge through activities like memory, attention, reasoning, learning, and solving problems. Meta-cognition is a subdivision of cognition. It…
View article: Study of Modifiable Risk Factors Associated with Learning Abilities in MBBS Students
Study of Modifiable Risk Factors Associated with Learning Abilities in MBBS Students Open
Introduction: Healthy body is the basis for healthy mind and sound learning. Factors affecting physical health can influence one‟s learning abilities. BMI, neck girth, breakfast eating habits, resting blood pressures are surrogates of phys…
View article: Democratization of Deep Learning Using DARVIZ
Democratization of Deep Learning Using DARVIZ Open
With an abundance of research papers in deep learning, adoption and reproducibility of existing works becomes a challenge. To make a DL developer life easy, we propose a novel system, DARVIZ, to visually design a DL model using a drag-and-…
View article: DLPaper2Code: Auto-Generation of Code From Deep Learning Research Papers
DLPaper2Code: Auto-Generation of Code From Deep Learning Research Papers Open
With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Even if the source code is availa…
View article: Sanskrit Sandhi Splitting using seq2(seq)2
Sanskrit Sandhi Splitting using seq2(seq)2 Open
In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi. Sandhi splitting is the process of splitting a given compound word into its constituent morphemes. Although rules governing word sp…
View article: DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers
DLPaper2Code: Auto-generation of Code from Deep Learning Research Papers Open
With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Further, re-implementing research…
View article: mAnI: Movie Amalgamation using Neural Imitation
mAnI: Movie Amalgamation using Neural Imitation Open
Cross-modal data retrieval has been the basis of various creative tasks performed by Artificial Intelligence (AI). One such highly challenging task for AI is to convert a book into its corresponding movie, which most of the creative film m…
View article: DARVIZ: Deep Abstract Representation, Visualization, and Verification of Deep Learning Models
DARVIZ: Deep Abstract Representation, Visualization, and Verification of Deep Learning Models Open
Traditional software engineering programming paradigms are mostly object or\nprocedure oriented, driven by deterministic algorithms. With the advent of deep\nlearning and cognitive sciences there is an emerging trend for data-driven\nprogr…