A Scalable Space-efficient In-database Interpretability Framework for Embedding-based Semantic SQL Queries

no code implementations • 23 Feb 2023 • Prabhakar Kudva, Rajesh Bordawekar, Apoorva Nitsure

AI-Powered database (AI-DB) is a novel relational database system that uses a self-supervised neural network, database embedding, to enable semantic SQL queries on relational tables.

EFloat: Entropy-coded Floating Point Format for Compressing Vector Embedding Models

no code implementations • NeurIPS 2021 • Rajesh Bordawekar, Bulent Abali, Ming-Hung Chen

EFloat uses entropy coding on exponent values and signs to minimize the average width of the exponent and sign fields, while preserving the original FP32 exponent range unchanged.

Data Compression

Unlocking New York City Crime Insights using Relational Database Embeddings

no code implementations • 19 May 2020 • Apoorva Nitsure, Rajesh Bordawekar, Jose Neves

This paper demonstrates the use of the AI-Powered Database (AI-DB) in identifying non-obvious patterns in crime data that could serve as an aid to predictive policing measures.

Feature Engineering

Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities

no code implementations • 19 Dec 2017 • Rajesh Bordawekar, Bortik Bandyopadhyay, Oded Shmueli

We propose Cognitive Databases, an approach for transparently enabling Artificial Intelligence (AI) capabilities in relational databases.

Enabling Cognitive Intelligence Queries in Relational Databases using Low-dimensional Word Embeddings

no code implementations • 23 Mar 2016 • Rajesh Bordawekar, Oded Shmueli

We describe various techniques for extracting token sequences from a database.

Word Embeddings