After ‘Tokenmaxxing’, Token Spend Has Become The New Metric To Watch

As organizations move away from tokenmaxxing, business leaders are becoming more cautious over token spend. Users that spend ...

Why marketing mix modeling is still hard to get right

Open-source tools have made MMM more accessible, but reliable results still depend on clean data, thoughtful modeling, and ...
GitHub

AROS-S — Autonomous Real-time On-board Security for Satellites

I built AROS-S because defending a satellite from the ground doesn't really work in real time. By the time suspicious telemetry reaches a ground station and someone reacts, the hardware could already ...
Frontiers

Emotion estimation from video footage with LSTM

Emotion estimation is a field that has been studied for a long time, and several approaches using machine learning models exist. This article presents BlendFER-Lite, an LSTM model that uses ...
GitHub

Attributions for ML-based ICS Anomaly Detection

This repository contains code for the paper: "Attributions for ML-based ICS anomaly detection: From theory to practice", to appear at the 31st Network and Distributed System Security Symposium (NDSS ...
Frontiers

Genomic prediction for sugarcane diseases including hybrid Bayesian-machine learning approaches

Sugarcane smut and Pachymetra root rots are two serious diseases of sugarcane, with susceptible infected crops losing over 30% of yield. A heritable component to both diseases has been demonstrated, ...