Communications of the ACM

Building Intelligent Agents with Neuro-Symbolic Concepts

The agent acquires a vocabulary of neuro-symbolic concepts for objects, relations, and actions, represented through a ...
IEEE

Bringing Machine Learning Classifiers Into Critical Cyber-Physical Systems: A Matter of Design

Machine Learning (ML) models are increasingly used by domain experts to tackle classification tasks, aiming for high predictive accuracy. However, classifiers are inherently prone to ...
IEEE

Efficient Data Augmentation for Machine Learning Classifiers Using Horizontal and Vertical Contractions

Abstract: To yield better performance, machine learning (ML) classifiers are typically trained with augmented data (i.e., combining real data with synthetically generated data). While the amalgamation ...
GitHub

Mikecloud24/intent-classifier-model-k8s

A production-ready machine learning service for intent classification built with Python Flask and deployed on Amazon EKS (Elastic Kubernetes Service). This project demonstrates best practices for ...