RTNeural: Fast Neural Inferencing for Real-Time Systems

2021/06/06 by Jatin Chowdhury, Chowdhury, Jatin · 2 citations
Computer Science · #Advanced Neural Network Applications #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Neural Networks and Applications #Parallel Computing and Optimization Techniques #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2106.03037

openalex publication_date 2021/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

RTNeural is a neural inferencing library written in C++. RTNeural is designed to be used in systems with hard real-time constraints, with additional emphasis on speed, flexibility, size, and convenience. The motivation and design of the library are described, as well as real-world use-cases, and performance comparisons with other neural inferencing libraries.

Citations

• Theory of ferromagnetic hysteresis
• Long Short-Term Memory

Cited by

• Neutone SDK: An Open Source Framework for Neural Audio Processing
• ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications

Related

• RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks
• Neural Speed Reading via Skim-RNN
• NNStreamer: Stream Processing Paradigm for Neural Networks, Toward Efficient Development and Execution of On-Device AI Applications
• CGRA4ML: A Framework to Implement Modern Neural Networks for Scientific Edge Computing
• SpiNNaker2: A Large-Scale Neuromorphic System for Event-Based and Asynchronous Machine Learning