• Publications
  • Influence
Study of Different Deep Learning Approach with Explainable AI for Screening Patients with COVID-19 Symptoms: Using CT Scan and Chest X-ray Image Dataset
TLDR
A deep learning-based model is developed that can detect COVID-19 patients with better accuracy both on CT scan and chest X-ray image dataset and test results demonstrate that it is conceivable to interpret top features that should have worked to build a trust AI framework to distinguish between patients with CO VID-19 symptoms with other patients.
Adaptive blocked Gibbs sampling for inference in probabilistic graphical models
TLDR
This work utilizes correlation among variables in the probabilistic graphical model to develop an adaptive blocked Gibbs sampler that automatically tunes its proposal distribution based on statistics derived from previous samples, which improves the performance of blocked Gibbs sampling, an advanced variant of the Gibbs sampling algorithm.
COVID-19 Symptoms Detection Based on NasNetMobile with Explainable AI Using Various Imaging Modalities
TLDR
Results demonstrate that the proposed models can identify the infectious regions and top features; ultimately, it provides a potential opportunity to distinguish between COVID-19 patients with others.
Augmenting Deep Learning with Relational Knowledge from Markov Logic Networks
TLDR
This paper develops a novel model that combines the best of both worlds, namely, the scalable learning capabilities of DNNs and symbolic knowledge specified in MLNs, and outperforms purely-MLN or purely-DNN based models in several different problem domains.
Learning Mixtures of MLNs
TLDR
This paper proposes a novel, intuitive approach for learning MLNs discriminatively by utilizing approximate symmetries, and shows that this approach is much more scalable and accurate as compared to existing state-of-the-art MLN learning methods.
Contrastive Learning in Neural Tensor Networks using Asymmetric Examples
TLDR
This paper develops a Neuro-Symbolic approach to infer unknown facts from relational data using statistical relational models to perform probabilistic inference, and trains a Neural Tensor Network to learn representations for symmetries implied by the symbolic knowledge.
Scaling up Inference in MLNs with Spark
TLDR
This work designs a novel lifted inference system built on top of Spark that takes advantage of parallelism to identify symmetries in the MLN and unifies advances in inference for relational data with advances in big data processing technologies.
Learning Embeddings for Approximate Lifted Inference in MLNs
TLDR
An overview of the approach, some experimental results that show its promise in improving inference algorithms for MLNs, and an embedding for MLN objects that predicts the context of an object that can adapt existing skip-gram models to learn symmetries efficiently are presented.