paper-with-me

홈 › Papers

NNStreamer: Stream Processing Paradigm for Neural Networks, Toward Efficient Development and Execution of On-Device AI Applications

2019-01-12 · MyungJoo Ham, Ji Joong Moon, Geunsik Lim, Wook Song, Jaeyun Jung, Hyoungjoo Ahn, Sangjung Woo, Youngchul Cho, Jinhyuck Park, Sewon Oh, Hong-Seok Kim

We propose nnstreamer, a software system that handles neural networks as filters of stream pipelines, applying the stream processing paradigm to neural network applications. A new trend with the wide-spread of deep neural network applications is on-device AI; i.e., processing neural networks directly on mobile devices or edge/IoT devices instead of cloud servers. Emerging privacy issues, data transmission costs, and operational costs signifies the need for on-device AI especially when a huge number of devices with real-time data processing are deployed. Nnstreamer efficiently handles neural networks with complex data stream pipelines on devices, improving the overall performance significantly with minimal efforts. Besides, nnstreamer simplifies the neural network pipeline implementations and allows reusing off-shelf multimedia stream filters directly; thus it reduces the developmental costs significantly. Nnstreamer is already being deployed with a product releasing soon and is open source software applicable to a wide range of hardware architectures and software platforms.

📄 PDF Abstract BibTeX arXiv:1901.04985

Code (1)

nnstreamer/nnstreamer tf

Similar Papers 제목 키워드 기반

NNStreamer: Efficient and Agile Development of On-Device AI Systems

2021-01-16 · MyungJoo Ham, Jijoong Moon, Geunsik Lim, Jaeyun Jung 외

We propose NNStreamer, a software system that handles neural networks as filters of stream pipelines, applying the stream processing paradigm to deep neural network applications. A new trend with the wide-spread of deep …

Toward Among-Device AI from On-Device AI with Stream Pipelines

2022-01-16 · MyungJoo Ham, Sangjung Woo, Jaeyun Jung, Wook Song 외

Modern consumer electronic devices often provide intelligence services with deep neural networks. We have started migrating the computing locations of intelligence services from cloud servers (traditional AI systems) to …

AutoStreamPipe: LLM Assisted Automatic Generation of Data Stream Processing Pipelines

2025-10-27 · Abolfazl Younesi, Zahra Najafabadi Samani, Thomas Fahringer arxiv

Data pipelines are essential in stream processing as they enable the efficient collection, processing, and delivery of real-time data, supporting rapid data analysis. In this paper, we present AutoStreamPipe, a novel fra…

Towards AI Search Paradigm

2025-06-20 · Yuchen Li, Hengyi Cai, Rui Kong, Xinran Chen 외

In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-making. The paradigm employs a modular archi…

Decision MakingRetrieval-augmented GenerationTask Planning

DFEE: Interactive DataFlow Execution and Evaluation Kit

2022-12-04 · Han He, Song Feng, Daniele Bonadiman, Yi Zhang 외

DataFlow has been emerging as a new paradigm for building task-oriented chatbots due to its expressive semantic representations of the dialogue tasks. Despite the availability of a large dataset SMCalFlow and a simplifie…

BenchmarkingScheduling