Search Results for author:
Found 3 papers, 0 papers with code
Towards Causal Physical Error Discovery in Video Analytics Systems
Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug.
ServeFlow: A Fast-Slow Model Architecture for Network Traffic Analysis
We identify that on the same task, inference time across models can differ by 2. 7x-136. 3x, while the median inter-packet waiting time is often 6-8 orders of magnitude higher than the inference time!
EdgeServe: A Streaming System for Decentralized Model Serving
The relevant features for a machine learning task may arrive as one or more continuous streams of data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
