paper-with-me

홈 › Papers

The Duck's Brain: Training and Inference of Neural Networks in Modern Database Engines

2023-12-28 · Maximilian E. Schüle, Thomas Neumann, Alfons Kemper

Although database systems perform well in data access and manipulation, their relational model hinders data scientists from formulating machine learning algorithms in SQL. Nevertheless, we argue that modern database systems perform well for machine learning algorithms expressed in relational algebra. To overcome the barrier of the relational model, this paper shows how to transform data into a relational representation for training neural networks in SQL: We first describe building blocks for data transformation, model training and inference in SQL-92 and their counterparts using an extended array data type. Then, we compare the implementation for model training and inference using array data types to the one using a relational representation in SQL-92 only. The evaluation in terms of runtime and memory consumption proves the suitability of modern database systems for matrix algebra, although specialised array data types perform better than matrices in relational representation.

📄 PDF Abstract BibTeX arXiv:2312.17355

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DuckSegmentation: A segmentation model based on the AnYue Hemp Duck Dataset

2025-03-27 · Ling Feng, Tianyu Xie, Wei Ma, Ruijie Fu 외

The modernization of smart farming is a way to improve agricultural production efficiency, and improve the agricultural production environment. Although many large models have achieved high accuracy in the task of object…

Knowledge DistillationObject RecognitionSegmentation

DUCK: Distance-based Unlearning via Centroid Kinematics

2023-12-04 · Marco Cotogni, Jacopo Bonato, Luigi Sabetta, Francesco Pelosin 외

Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models. This technique primarily aims to eradicate any residual influence of a specific …

Inference AttackMachine UnlearningMembership Inference AttackMetric Learning

PSyDUCK: Training-Free Steganography for Latent Diffusion

2025-01-31 · Aqib Mahfuz, Georgia Channing, Mark van der Wilk, Philip Torr 외

Recent advances in generative AI have opened promising avenues for steganography, which can securely protect sensitive information for individuals operating in hostile environments, such as journalists, activists, and wh…

Denoising

Lyra: A Benchmark for Turducken-Style Code Generation

2021-08-27 · Qingyuan Liang, Zeyu Sun, Qihao Zhu, Wenjie Zhang 외

Recently, neural techniques have been used to generate source code automatically. While promising for declarative languages, these approaches achieve much poorer performance on datasets for imperative languages. Since a …

Code Generation

Developing a Purely Visual Based Obstacle Detection using Inverse Perspective Mapping

2018-09-04 · Julian Nubert, Niklas Funk, Fabio Meier, Fabrice Oehler

Our solution is implemented in and for the frame of Duckietown. The goal of Duckietown is to provide a relatively simple platform to explore, tackle and solve many problems linked to autonomous driving. "Duckietown" is s…

Autonomous DrivingManagement