Abstract

GPU Accelerated Machine Learning

Artificial Intelligence is a wide field where different types of learning models serve different kinds of tasks. Deep neural networks (DL), for example, are great for data with spatial-temporal locality like images, audio, and text. However, for data without inherent locality, non-neural network machine learning algorithms....


Session No: SIL8137
Speaker: Paul Mahler
Type:

Accelerated Data Analytics

Date: Thursday - October 18, 2018 02:00 PM - 02:45 PM
Location: Hall I
Topic: Professional Visualization
Industry: Software

Artificial Intelligence is a wide field where different types of learning models serve different kinds of tasks. Deep neural networks (DL), for example, are great for data with spatial-temporal locality like images, audio, and text. However, for data without inherent locality, non-neural network machine learning algorithms, such as random forest or gradient boosted trees, are often used instead. In this session, we will discuss our work towards optimizing non-neural-network based ML algorithms for latest GPU architectures.