Skip to content
GCC AI Research

Search

Results for "bagging"

Understanding ensemble learning

MBZUAI ·

An associate professor of Statistics at the University of Toronto gave a talk on how ensemble learning stabilizes and improves the generalization performance of an individual interpolator. The talk focused on bagged linear interpolators and introduced the multiplier-bootstrap-based bagged least square estimator. The multiplier bootstrap encompasses the classical bootstrap with replacement as a special case, along with a Bernoulli bootstrap variant. Why it matters: While the talk occurred at MBZUAI, the content is about ensemble learning which is a core area for improving AI model performance, and is of general interest to the AI research community.

Treated jute bags boost grain storage and other green goals

KAUST ·

KAUST researchers have developed a surface treatment for jute storage bags to prevent moisture-induced damage to stored grains. The treatment involves roughening the jute surface with an alkali and applying a thin layer of paraffin wax. Experiments showed that seed moisture content reduced by up to 7.5 percent in wax-coated bags, and seed germination efficacy after storage was up to 35 percent higher. Why it matters: This simple, scalable technique could significantly reduce grain losses in developing countries and provide an environmentally friendly alternative for grain storage.

Short-Term Traffic Forecasting Using High-Resolution Traffic Data

arXiv ·

Researchers developed a data-driven toolkit for short-term traffic forecasting using high-resolution traffic data from urban road sensors. The method models forecasting as a matrix completion problem, mapping inputs to a higher-dimensional space using kernels and adaptive boosting. Validated using real-world data from Abu Dhabi, UAE, the method outperforms state-of-the-art algorithms.

Deep Ensembles Work, But Are They Necessary?

MBZUAI ·

A recent study questions the necessity of deep ensembles, which improve accuracy and match larger models. The study demonstrates that ensemble diversity does not meaningfully improve uncertainty quantification on out-of-distribution data. It also reveals that the out-of-distribution performance of ensembles is strongly determined by their in-distribution performance. Why it matters: The findings suggest that larger, single neural networks can replicate the benefits of deep ensembles, potentially simplifying model deployment and reducing computational costs in the region.

Innovating Agritech, serving the nation

MBZUAI ·

Two student teams from MBZUAI won top prizes at the inaugural Agritech Hackathon (“Agrithon”) organized by ADAFSA. The “Masdar Boys” team developed a dashboard integrating ML models for plant disease diagnosis, optimal animal clinic placement, and disease outbreak zone classification. The “Green AI” team built a machine learning framework for plant disease classification, winning second prize. Why it matters: This highlights the growing role of AI in addressing food security challenges in the UAE and the region, with potential for real-world applications through ADAFSA's interest in further developing the students' work.

Mass production of AI solutions

MBZUAI ·

MBZUAI Assistant Professor Qirong Ho is researching AI operating systems to standardize algorithms and enable non-experts to create AI applications reliably. He emphasizes that countries mastering mass production of AI systems will benefit most from the Fourth Industrial Revolution. Ho is co-founder and CTO at Petuum Inc., an AI startup creating standardized building blocks for affordable and scalable AI production. Why it matters: This research aims to democratize AI development and promote widespread adoption across industries in the UAE and beyond.

Hybrid Deep Feature Extraction and ML for Construction and Demolition Debris Classification

arXiv ·

This paper introduces a hybrid deep learning and machine learning pipeline for classifying construction and demolition waste. A dataset of 1,800 images from UAE construction sites was created, and deep features were extracted using a pre-trained Xception network. The combination of Xception features with machine learning classifiers achieved up to 99.5% accuracy, demonstrating state-of-the-art performance for debris identification.