A5062687176- Machine Learning and Data Classification
- Topic Modeling
- Parallel Computing and Optimization Techniques
- Ubiquitin and proteasome pathways
- Cardiac Valve Diseases and Treatments
- Cardiovascular Function and Risk Factors
- Cell death mechanisms and regulation
- Biochemical and Molecular Research
- Metabolism and Genetic Disorders
University of Chinese Academy of Sciences
2023
Institute of Computing Technology
2023
Hubei University of Chinese Medicine
2016
Classical machine learning (CML) occupies nearly half of pipelines in production applications. Unfortunately, it fails to utilize the state-of-the-practice devices fully and performs poorly. Without a unified framework, hybrid deployments deep (DL) CML also suffer from severe performance portability issues. This paper presents design compiler, called CMLCompiler, for inference. We propose two abstractions: operator representations extended computational graphs. The CMLCompiler framework...
Classical machine learning (CML) occupies nearly half of pipelines in production applications. Unfortunately, it fails to utilize the state-of-the-practice devices fully and performs poorly. Without a unified framework, hybrid deployments deep (DL) CML also suffer from severe performance portability issues. This paper presents design compiler, called CMLCompiler, for inference. We propose two abstractions: operator representations extended computational graphs. The CMLCompiler framework...