Mohit Pandey

Mohit Pandey

Ph.D. Candidate

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Named entity recognition with simple Attention

less than 1 minute read

Published:

NER implementation hosted within browser using Tensorflow-JS.

Definition from Wikipedia

Named Entity Recognition is a subtask of information extraction that seeks to locate and classify named entities mentioned in unstructured text into pre-defined categories such as person names, organizations, locations, etc. See demo below. Continue reading for model explanation and code.

Encoder - Attention - Decoder

10 minute read

Published:

Explaining Attention Network in Encoder-Decoder setting using Recurrent Neural Networks

Encoder-Decoder paradigm has become extremely popular in deep learning particularly in the space of natural language processing. Attention modules complement encoder-decoder architecture to make learning more close to humans way. I present a gentle introduction to encode-attend-decode. I provide motivation for each block and explain the math governing the model. Further, I break down the code into digestible bits for each mathematical equation. While there are good explanations to attention mechanism for machine translation task, I will try to explain the same for a sequence tagging task (Named Entity Recognition).

Encode-Attend-Decode Architecture

In the next part of the series, I will use the architecture explained here to solve the problem of Named Entity Recognition

Seq2Seq Machine Translation

less than 1 minute read

Published:

I explore Seq2Seq model in Pytorch to build a neural machine translation system. Currently the system translates from German to English. In this series, I will explore various state-of-the-art NLP architectures to build NMT systems algorithms and hope to focus on English to Hindi translation. I will also attempt to provide simplified mathematical explanations of the models as well as implementation details.

Digit Classification

less than 1 minute read

Published:

Digit Recognition using Deep Learning

This page is best viewed here

Webapp to recognize handwritten digits between 0 and 9. Model trained using Keras and served using Tensorflow.js

publications

[C] Automated diagnosis of echocardiographic views using deep learning: P2-39

G. Singh, G. Maliakal, S. Al‘Aref, A. Dwivedi, M. Pandey, A. Kumar, M. Gummalla, P. Dunham, M. Gomez, H.-J. Chang, et al. Journal of the American Society of Echocardiography, vol. 31, no. 6, 2018

DEEP LEARNING BASED AUTOMATIC SEGMENTATION OF CARDIAC COMPUTED TOMOGRAPHY

G. Singh, S. Alaref, G. Maliakal, M. Pandey, A. van Rosendael, B. Lee, J.Wang, Z. Xu, and J. Min. Journal of the American College of Cardiology, vol. 73, no. 9 Supplement 1, p. 1643 doi: 10.1016/S0735-1097(19)32249-1

Tracking immigration discussion in social media: A survey on deep learning based natural language processing for social media insights

Pandey M, Hayman S. American Association for Public Opinion Research 2020 [Accepted] Not Presented due to COVID-19

Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging

AlAref SJ, Anchouche K, Singh G, Slomka PJ, Kolli KK, Kumar A, Pandey M, Maliakal G, van Rosendael AR, Beecy AN, et al. Eur Heart J. 2019 Jun 21;40(24):1975-1986. doi: 10.1093/eurheartj/ehy404. PMID: 30060039.

Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing

Pandey M, Xu Z, Sholle E, Maliakal G, Singh G, Fatima Z, AlAref SJ, et al. "Extraction of radiographic findings from unstructured thoracoabdominal computed tomography reports using convolutional neural network based natural language processing." PLoS One. 2020 Jul 30;15(7):e0236827.doi: 10.1371/journal.pone.0236827. PMID: 32730362; PMCID: PMC7392233.

The transformational role of GPU computing and deep learning in drug discovery.

Pandey, M., Fernandez, M., Gentile, F. et al. The transformational role of GPU computing and deep learning in drug discovery. Nat Mach Intell 4, 211–221 (2022). https://doi.org/10.1038/s42256-022-00463-x

research

talks