Suchergebnisse - Computing methodologies → Machine learning algorithms

Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models von Sheng, Yi, Yang, Junhuan, Yang, Lei, Shi, Yiyu, Hu, Jingtong, Jiang, Weiwen

“… Model fairness (a.k.a., bias) has become one of the most critical problems in a wide range of AI applications. An unfair model in autonomous driving may cause …”
Volltext

Toward Individual Fairness Testing with Data Validity von Kitamura, Takashi, Amasaki, Sousuke, Inoue, Jun, Isobe, Yoshinao, Toda, Takahisa

“… )". We develop a solid foundation of Ift-v and demonstrate the feasibility of Ift-v. Our preliminary evaluation with Ift-v reveals the possibility that many of discriminatory instances detected by state-of-the-art Ift algorithms are considered invalid …”
Volltext

DARL: Distributed Reconfigurable Accelerator for Hyperdimensional Reinforcement Learning von Chen, Hanning, Issa, Mariam, Ni, Yang, Imani, Mohsen

“… Modern RL algorithms, i.e., Deep Q-Learning, are based on costly and resource hungry deep neural networks …”
Volltext

A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning von Fu, Yonggan, Zhang, Yongan, Li, Chaojian, Yu, Zhongzhi, Lin, Yingyan

“… Driven by the explosive interest in applying deep reinforcement learning (DRL) agents to numerous real-time control and decision-making applications …”
Volltext

GARL: Genetic Algorithm-Augmented Reinforcement Learning to Detect Violations in Marker-Based Autonomous Landing Systems von Liang, Linfeng, Deng, Yao, Morton, Kye, Kallinen, Valtteri, James, Alice, Seth, Avishkar, Kuantama, Endrowednes, Mukhopadhyay, Subhas, Han, Richard, Zheng, Xi

“… To address these issues, we introduce GARL, a framework combining a genetic algorithm (GA) and reinforcement learning (RL …”
Volltext

Cocktail: Learn a Better Neural Network Controller from Multiple Experts via Adaptive Mixing and Robust Distillation von Wang, Yixuan, Huang, Chao, Wang, Zhilu, Xu, Shichao, Wang, Zhaoran, Zhu, Qi

“… Neural networks are being increasingly applied to control and decision making for learning-enabled cyber-physical systems (LE-CPSs …”
Volltext

Lightning Talk: The New Era of Computational Cognitive Intelligence von Dutt, Nikil, Donyanavard, Bryan

“… ), and the environment (e.g., context) renders ineffective the classical computational/algorithmic/numerical computing paradigm in dealing with the inherent runtime dynamism and uncertainty faced by emerging systems …”
Volltext

Making Fair ML Software using Trustworthy Explanation von Chakraborty, Joymallya, Peng, Kewen, Menzies, Tim

“… Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice …”
Volltext

DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification von Wang, Junyao, Huang, Sitao, Imani, Mohsen

“… Many applications exploit machine learning methodology to dissect collected data, and edge computing was introduced to enhance the efficiency and scalability in resource-constrained computing environments …”
Volltext

SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments von Putra, Rachmad Vidya Wicaksana, Shafique, Muhammad

“… Spiking Neural Networks (SNNs) bear the potential of efficient unsupervised and continual learning capabilities because of their biological plausibility, but their complexity still poses a serious research challenge to enable …”
Volltext

Llanimation: Llama Driven Gesture Animation von Windle, J, Matthews, I, Taylor, S

“… Co‐speech gesturing is an important modality in conversation, providing context and social cues. In character animation, appropriate and synchronised gestures …”
Volltext

FedLight: Federated Reinforcement Learning for Autonomous Multi-Intersection Traffic Signal Control von Ye, Yutong, Zhao, Wupan, Wei, Tongquan, Hu, Shiyan, Chen, Mingsong

“… Although Reinforcement Learning (RL) has been successfully applied in traffic control, it suffers from the problems of high average vehicle travel time and slow convergence to optimized solutions …”
Volltext

Iterative Generation of Adversarial Example for Deep Code Models von Huang, Li, Sun, Weifeng, Yan, Meng

“… Deep code models are vulnerable to adversarial attacks, making it possible for semantically identical inputs to trigger different responses. Current black-box …”
Volltext

RegHD: Robust and Efficient Regression in Hyper-Dimensional Learning System von Hernandez-Cano, Alejandro, Zhuo, Cheng, Yin, Xunzhao, Imani, Mohsen

“… Machine learning (ML) algorithms are key enablers to effectively assimilate and extract information from many generated data in the Internet of Things …”
Volltext

FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision von Ma, Jingxiao, Panda, Priyadarshini, Reda, Sherief

“… Recently, the Forward-Forward (FF) algorithm has emerged as a promising alternative to backpropagation, replacing the backward pass with an additional forward pass …”
Volltext

Fast Adversarial Training with Dynamic Batch-level Attack Control von Jung, Jaewon, Song, Jaeyong, Jang, Hongsun, Lee, Hyeyoon, Choi, Kanghyun, Park, Noseong, Lee, Jinho

“… Despite the fact that adversarial training provides an effective protection against adversarial attacks, it suffers from a huge computational overhead. To …”
Volltext

Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning von Fu, Yonggan, Yuan, Ye, Wu, Shang, Yuan, Jiayi, Lin, Yingyan Celine

“… Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks …”
Volltext

On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations von Hundal, Rajdeep Singh, Xiao, Yan, Cao, Xiaochun, Dong, Jin Song, Rigger, Manuel

“… Deep Reinforcement Learning (DRL) is a paradigm of artificial intelligence where an agent uses a neural network to learn which actions to take in a given environment …”
Volltext

RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs von Yin, Jiaqi, Li, Yingjie, Robinson, Daniel, Yu, Cunxi

“… , computation, I/O, and memory-bound) edge computing systems. While efficient execution of their computational graph requires an effective scheduling algorithm, generating the optimal scheduling solution is a challenging NP-hard problem …”
Volltext

ADVeRL-ELF: ADVersarial ELF Malware Generation using Reinforcement Learning von Ravi, Akshara, Chaturvedi, Vivek, Shafique, Muhammad

“… Deep learning models are now pervasive in the malware detection domain owing to their high accuracy and performance efficiency …”
Volltext