Data-centric artificial intelligence: A survey
Artificial Intelligence (AI) is making a profound impact in almost every domain. A vital enabler
of its great success is the availability of abundant and high-quality data for building machine …
of its great success is the availability of abundant and high-quality data for building machine …
Winner-take-all column row sampling for memory efficient adaptation of language model
As the model size grows rapidly, fine-tuning the large pre-trained language model has
become increasingly difficult due to its extensive memory usage. Previous works usually …
become increasingly difficult due to its extensive memory usage. Previous works usually …
Hardware solutions for low-power smart edge computing
L Martin Wisniewski, JM Bec, G Boguszewski… - Journal of Low Power …, 2022 - mdpi.com
The edge computing paradigm for Internet-of-Things brings computing closer to data
sources, such as environmental sensors and cameras, using connected smart devices. Over …
sources, such as environmental sensors and cameras, using connected smart devices. Over …
DIVISION: memory efficient training via dual activation precision
Activation compressed training provides a solution towards reducing the memory cost of
training deep neural networks (DNNs). However, state-of-the-art work combines a search of …
training deep neural networks (DNNs). However, state-of-the-art work combines a search of …
Autovideo: An automated video action recognition system
Action recognition is an important task for video understanding with broad applications.
However, developing an effective action recognition solution often requires extensive …
However, developing an effective action recognition solution often requires extensive …
TransCAB: Transferable clean-annotation backdoor to object detection with natural trigger in real-world
Object detection is the foundation of various critical computer-vision tasks such as
segmentation, object tracking, and event detection, which can be deployed on pervasive …
segmentation, object tracking, and event detection, which can be deployed on pervasive …
Qualitative analysis of anomaly detection in time series
We present an end-end system for time series anomaly detection specifically aimed at
detecting fraudulent transactions in bank transaction datasets. The goal of anomaly …
detecting fraudulent transactions in bank transaction datasets. The goal of anomaly …
[PDF][PDF] Backbone search for object detection for applications in intrusion warning systems
In this work, we propose a novel backbone search method for object detection for
applications in intrusion warning systems. The goal is to find a compact model for use in …
applications in intrusion warning systems. The goal is to find a compact model for use in …
Efficient Methods for Deep Reinforcement Learning: Algorithms and Applications
D Zha - 2023 - search.proquest.com
Deep reinforcement learning (deep RL) has recently achieved remarkable success in
various domains, from simulated games to real-world applications. However, deep RL …
various domains, from simulated games to real-world applications. However, deep RL …