Sujit Pal

statlearning-notebooks. Python notebooks for exercises covered in Stanford statlearning class (where exercises were in R).

eeap-examples. Code for Document Similarity on Reuters dataset using Encode, Embed, Attend, Predict recipe

dl-models-for-qa. Keras DL models to answer 8th grade science multiple choice questions (Kaggle AllenAI competition).

nltk-examples. Worked examples from the NLTK Book

holiday-similarity. Finding similar images in the Holidays dataset

fttl-with-keras. Transfer Learning and Fine Tuning for Cross Domain Image Classification with Keras

ner-re-with-transformers-odsc2022. Building NER and RE components using HuggingFace Transformers

pytorch-gnn-tutorial-odsc2021. Repository for GNN tutorial using Pytorch and Pytorch Geometric (PyG) for ODSC 2021

llm-rag-eval. Large Language Model (LLM) powered evaluator for Retrieval Augmented Generation (RAG) pipelines.

hia-examples. Hadoop In Action Examples

mlia-examples. Python and R Examples

reuters-docsim. Different approaches to computing document similarity

keras-tutorial-odsc2020. Notebooks for Keras Tutorial presented at ODSC West 2020

mia-scala-examples. Mahout Examples

nerds. Python

ltr-examples. Supporting code for Learning to Rank (LTR) presentation

polydlot. My attempt to learn more than one Deep Learning framework

intro-dl-talk-code. Jupyter notebooks and code for Intro to DL talk at Genesys

nlp-graph-examples. Examples for Graphorum 2019 presentation -- Graph Techniques for Natural Language Processing

scalcium. Scala NLP Algorithms

bpwj. Java Parser Development Framework from Steven Metsker's "Building Parsers With Java book"

delsym. An actor based content ingestion pipeline

solr4-extras. Random solr4 customizations

esc. Scala client for ElasticSearch

deeplearning-ai-examples. Jupyter Notebook

kg-aligned-entity-linker. Knowledge Graph Aligned Entity Linker using BERT and Sentence Transformers

thinkstats-examples. Worked examples for exercises in Think Stats using the Scientific Python stack.

saturn-scispacy. SaturnCloud notebooks to extract annotations from CORD-19 dataset using SciSpacy pretrained models

content-engineering-tutorial. Jupyter Notebook

vespa-poc. Small Proof of Concept to familiarize myself with Vespa.ai functionality

neural-re-experiments. Jupyter Notebook

bayesian-stats-examples. Python versions of things taught in the Bayesian Statistics courses on Coursera

tgni. Experimental NER techniques to address common (for me) text analysis problems.

neurips-papers-node2vec. Jupyter Notebook

snorkel-pytorch-lstm-gpu. Code for my GPU port of Snorkel 's Pytorch discriminative model (LSTM)

compmethods-notebooks. Python Notebooks for the Computional Methods for Data Analysis course on Coursera.

spark-data-algorithms. Implementations of common data algorithms in Spark

llm-doc-explore. Platform to teach myself cool SoTA LLM stuff like langchain and llamaindex, while (hopefully) also creating something useful.

llm-agents-foodminions. Simple Agent based application to teach myself Agents and CrewAI

datascience-anthology-pydata. PyData, The Complete Works of

Deep-Learning-with-TensorFlow-2-and-Keras. Deep Learning with TensorFlow 2 and Keras, published by Packt

misc-docs. Account for storing miscellaneous text files for sharing

pytorch-drl-examples. Reimplementation of Deep Reinforcement Learning examples from "Deep Reinforcement Learning with Python" by Sudharsan Ravichandran

claimintel. Descriptive Stats on Claims Data