Výsledky vyhľadávania - "Computing methodologies Machine learning Learning paradigms Supervised learning"

Softermax: Hardware/Software Co-Design of an Efficient Softmax for Transformers Autor 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"…”
Získať plný text

PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning Autor 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…”
Získať plný text

Code Prediction by Feeding Trees to Transformers Autor 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…”
Získať plný text

PreSto: An In-Storage Data Preprocessing System for Training Recommendation Models Autor 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…”
Získať plný text

Dissecting Global Search: A Simple Yet Effective Method to Boost Individual Discrimination Testing and Repair Autor 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…”
Získať plný text

Code Difference Guided Adversarial Example Generation for Deep Code Models Autor 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…”
Získať plný text

Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding Autor 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…”
Získať plný text

Neurally-Inspired Hyperdimensional Classification for Efficient and Robust Biosignal Processing Autor 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…”
Získať plný text

Online Human Activity Recognition using Low-Power Wearable Devices Autor 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…”
Získať plný text

Augmenting API Documentation with Insights from Stack Overflow Autor 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…”
Získať plný text

CodeS: Towards Code Model Generalization Under Distribution Shift Autor 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…”
Získať plný text

A Unified DNN Weight Pruning Framework Using Reweighted Optimization Methods Autor 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…”
Získať plný text

An Energy-Aware Approach to Design Self-Adaptive AI-based Applications on the Edge Autor 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…”
Získať plný text

Fairquant: Certifying and Quantifying Fairness of Deep Neural Networks Autor 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…”
Získať plný text

Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software Autor 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…”
Získať plný text

Efficient Transformer Inference with Statically Structured Sparse Attention Autor 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…”
Získať plný text

FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision Autor 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…”
Získať plný text

Enabling On-Tiny-Device Model Personalization via Gradient Condensing and Alternant Partial Update Autor 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,…”
Získať plný text

SSpMV: A Sparsity-aware SpMV Framework Empowered by Multimodal Machine Learning Autor 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…”
Získať plný text

Late Breaking Results: Less Sense Makes More Sense: In-Sensor Compressive Learning for Efficient Machine Vision Autor Liang, Yiwen, Cao, Weidong

“…Integrating deep learning and image sensors has significantly transformed machine vision applications. Yet, conventional highresolution image acquisition…”
Získať plný text