Suchergebnisse - "Computing methodologies Machine learning Learning paradigms Supervised learning"

Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers von Stevens, Jacob R., Venkatesan, Rangharajan, Dai, Steve, Khailany, Brucek, Raghunathan, Anand

“… Transformers have transformed the field of natural language processing. Their superior performance is largely attributed to the use of stacked "self-attention" …”
Volltext

PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning von Roy, Rajarshi, Raiman, Jonathan, Kant, Neel, Elkin, Ilyas, Kirby, Robert, Siu, Michael, Oberman, Stuart, Godil, Saad, Catanzaro, Bryan

“… In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are …”
Volltext

Code Prediction by Feeding Trees to Transformers von Kim, Seohyun, Zhao, Jinman, Tian, Yuchi, Chandra, Satish

“… Code prediction, more specifically autocomplete, has become an essential feature in modern IDEs. Autocomplete is more effective when the desired next token is …”
Volltext

PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models von Lee, Yunjae, Kim, Hyeseong, Rhu, Minsoo

“… Training recommendation systems (RecSys) faces several challenges as it requires the "data preprocessing" stage to preprocess an ample amount of raw data and …”
Volltext

Dissecting Global Search: A Simple Yet Effective Method to Boost Individual Discrimination Testing and Repair von Quan, Lili, Li, Tianlin, Xie, Xiaofei, Chen, Zhenpeng, Chen, Sen, Jiang, Lingxiao, Li, Xiaohong

“… Deep Learning (DL) has achieved significant success in socially critical decision-making applications but often exhibits unfair behaviors, raising social …”
Volltext

Code Difference Guided Adversarial Example Generation for Deep Code Models von Tian, Zhao, Chen, Junjie, Jin, Zhi

“… Adversarial examples are important to test and enhance the robustness of deep code models. As source code is discrete and has to strictly stick to complex …”
Volltext

Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding von Wang, Deze, Jia, Zhouyang, Li, Shanshan, Yu, Yue, Xiong, Yun, Dong, Wei, Liao, Xiangke

“… With the great success of pre-trained models, the pretrain-then-fine tune paradigm has been widely adopted on downstream tasks for source code understanding …”
Volltext

Neurally-Inspired Hyperdimensional Classification for Efficient and Robust Biosignal Processing von Ni, Yang, Lesica, Nicholas, Zeng, Fan-Gang, Imani, Mohsen

“… The biosignals consist of several sensors that collect time series information. Since time series contain temporal dependencies, they are difficult to process …”
Volltext

Online Human Activity Recognition using Low-Power Wearable Devices von Bhat, Ganapati, Deb, Ranadeep, Chaurasia, Vatika Vardhan, Shill, Holly, Ogras, Umit Y.

“… Human activity recognition (HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent …”
Volltext

Augmenting API Documentation with Insights from Stack Overflow von Treude, Christoph, Robillard, Martin P.

“… Software developers need access to different kinds of information which is often dispersed among different documentation sources, such as API documentation or …”
Volltext

CodeS: Towards Code Model Generalization Under Distribution Shift von Hu, Qiang, Guo, Yuejun, Xie, Xiaofei, Cordy, Maxime, Papadakis, Mike, Ma, Lei, Le Traon, Yves

“… Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation. Although …”
Volltext

A Unified DNN Weight Pruning Framework Using Reweighted Optimization Methods von Zhang, Tianyun, Ma, Xiaolong, Zhan, Zheng, Zhou, Shanglin, Ding, Caiwen, Fardad, Makan, Wang, Yanzhi

“… To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and …”
Volltext

An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge von Tundo, Alessandro, Mobilio, Marco, Ilager, Shashikant, Brandic, Ivona, Bartocci, Ezio, Mariani, Leonardo

“… The advent of edge devices dedicated to machine learning tasks enabled the execution of AI-based applications that efficiently process and classify the data …”
Volltext

Fairquant: Certifying and Quantifying Fairness of Deep Neural Networks von Kim, Brian Hyeongseok, Wang, Jingbo, Wang, Chao

“… We propose a method for formally certifying and quantifying individual fairness of deep neural networks (DNN). Individual fairness guarantees that any two …”
Volltext

Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software von Chen, Zhenpeng, Li, Xinyue, Zhang, Jie M., Sarro, Federica, Liu, Yang

“… Intersectional fairness is a critical requirement for Machine Learning (ML) software, demanding fairness across subgroups defined by multiple protected …”
Volltext

Efficient Transformer Inference with Statically Structured Sparse Attention von Dai, Steve, Genc, Hasan, Venkatesan, Rangharajan, Khailany, Brucek

“… Self-attention matrices of Transformers are often highly sparse because the relevant context of each token is typically limited to just a few other tokens in …”
Volltext

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

“… Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability …”
Volltext

SSpMV: A Sparsity-aware SpMV Framework Empowered by Multimodal Machine Learning von Lin, Shengle, Liu, Chubo, Ding, Yan, Zhou, Joey Tianyi, Li, Kenli, Yang, Wangdong

“… Sparse Matrix-Vector Multiplication (SpMV) is an essential sparse operation in scientific computing and artificial intelligence. Efficiently adapting SpMV …”
Volltext

LMM-IR: Large-Scale Netlist-Aware Multimodal Framework for Static IR-Drop Prediction von Ma, Kai, Wang, Zhen, He, Hongquan, Xu, Qi, Chen, Tinghuan, Geng, Hao

“… Static IR drop analysis is a fundamental and critical task in the field of chip design. Nevertheless, this process can be quite time-consuming, potentially …”
Volltext

Enabling On-Tiny-Device Model Personalization via Gradient Condensing and Alternant Partial Update von Jia, Zhenge, Shi, Yiyang, Bao, Zeyu, Wang, Zirui, Pang, Xin, Liu, Huiguo, Duan, Yu, Shen, Zhaoyan, Zhao, Mengying

“… On-device training enables the model to adapt to user-specific data by fine-tuning a pre-trained model locally. As embedded devices become ubiquitous, …”
Volltext