Výsledky vyhledávání - "Computing methodologies Machine learning Machine learning approaches Neural networks"

DeepTest: automated testing of deep-neural-network-driven autonomous cars Autor Tian, Yuchi, Pei, Kexin, Jana, Suman, Ray, Baishakhi

“…Recent advances in Deep Neural Networks (DNNs) have led to the development of DNN-driven autonomous cars that, using sensors like camera, LiDAR, etc., can…”
Získat plný text

Deep Code Comment Generation Autor Hu, Xing, Li, Ge, Xia, Xin, Lo, David, Jin, Zhi

“…During software maintenance, code comments help developers comprehend programs and reduce additional time spent on reading and navigating source code…”
Získat plný text

Large Language Models for Test-Free Fault Localization Autor Yang, Aidan Z.H., Goues, Claire Le, Martins, Ruben, Hellendoorn, Vincent J.

“…Fault Localization (FL) aims to automatically localize buggy lines of code, a key first step in many manual and automatic debugging tasks. Previous FL…”
Získat plný text

Natural Attack for Pre-trained Models of Code Autor Yang, Zhou, Shi, Jieke, He, Junda, Lo, David

“…Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial…”
Získat plný text

Lost in Translation: A Study of Bugs Introduced by Large Language Models While Translating Code Autor Pan, Rangeet, Ibrahimzada, Ali Reza, Krishna, Rahul, Sankar, Divya, Wassi, Lambert Pougeum, Merler, Michele, Sobolev, Boris, Pavuluri, Raju, Sinha, Saurabh, Jabbarvand, Reyhaneh

“…Code translation aims to convert source code from one programming language (PL) to another. Given the promising abilities of large language models (LLMs) in…”
Získat plný text

Fuzz Testing based Data Augmentation to Improve Robustness of Deep Neural Networks Autor Gao, Xiang, Saha, Ripon K., Prasad, Mukul R., Roychoudhury, Abhik

“…Deep neural networks (DNN) have been shown to be notoriously brittle to small perturbations in their input data. This problem is analogous to the over-fitting…”
Získat plný text

Bit-pragmatic deep neural network computing Autor Albericio, Jorge, Delmás, Alberto, Judd, Patrick, Sharify, Sayeh, O'Leary, Gerard, Genov, Roman, Moshovos, Andreas

“…Deep Neural Networks expose a high degree of parallelism, making them amenable to highly data parallel architectures. However, data-parallel architectures…”
Získat plný text

Watermarking Deep Neural Networks for Embedded Systems Autor Guo, Jia, Potkonjak, Miodrag

“…Deep neural networks (DNNs) have become an important tool for bringing intelligence to mobile and embedded devices. The increasingly wide deployment, sharing…”
Získat plný text

Dual-side Sparse Tensor Core Autor Wang, Yang, Zhang, Chen, Xie, Zhiqiang, Guo, Cong, Liu, Yunxin, Leng, Jingwen

“…Leveraging sparsity in deep neural network (DNN) models is promising for accelerating model inference. Yet existing GPUs can only leverage the sparsity from…”
Získat plný text

Semantically Enhanced Software Traceability Using Deep Learning Techniques Autor Jin Guo, Jinghui Cheng, Cleland-Huang, Jane

“…In most safety-critical domains the need for traceability is prescribed by certifying bodies. Trace links are generally created among requirements, design,…”
Získat plný text

Deep learning similarities from different representations of source code Autor Tufano, Michele, Watson, Cody, Bavota, Gabriele, Di Penta, Massimiliano, White, Martin, Poshyvanyk, Denys

“…Assessing the similarity between code components plays a pivotal role in a number of Software Engineering (SE) tasks, such as clone detection, impact analysis,…”
Získat plný text

A Pixel‐Based Framework for Data‐Driven Clothing Autor Jin, N., Zhu, Y., Geng, Z., Fedkiw, R.

“…We propose a novel approach to learning cloth deformation as a function of body pose, recasting the graph‐like triangle mesh data structure into image‐based…”
Získat plný text

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"…”
Získat plný text

Latent Space Subdivision: Stable and Controllable Time Predictions for Fluid Flow Autor Wiewel, S., Kim, B., Azevedo, V. C., Solenthaler, B., Thuerey, N.

“…We propose an end‐to‐end trained neural network architecture to robustly predict the complex dynamics of fluid flows with high temporal stability. We focus on…”
Získat plný text

Rescuing memristor-based neuromorphic design with high defects Autor Chenchen Liu, Miao Hu, Strachan, John Paul, Hai Li

“…Memristor-based synaptic network has been widely investigated and applied to neuromorphic computing systems for the fast computation and low design cost. As…”
Získat plný text

Cats Are Not Fish: Deep Learning Testing Calls for Out-Of-Distribution Awareness Autor Berend, David, Xie, Xiaofei, Ma, Lei, Zhou, Lingjun, Liu, Yang, Xu, Chi, Zhao, Jianjun

“…As Deep Learning (DL) is continuously adopted in many industrial applications, its quality and reliability start to raise concerns. Similar to the traditional…”
Získat plný text

The Logic of Graph Neural Networks Autor Grohe, Martin

“…Graph neural networks (GNNs) are deep learning architectures for machine learning problems on graphs. It has recently been shown that the expressiveness of…”
Získat plný text

EditSum: A Retrieve-and-Edit Framework for Source Code Summarization Autor Li, Jia Allen, Li, Yongmin, Li, Ge, Hu, Xing, Xia, Xin, Jin, Zhi

“…Existing studies show that code summaries help developers understand and maintain source code. Unfortunately, these summaries are often missing or outdated in…”
Získat plný text

Metamorphic Object Insertion for Testing Object Detection Systems Autor Wang, Shuai, Su, Zhendong

“…Recent advances in deep neural networks (DNNs) have led to object detectors (ODs) that can rapidly process pictures or videos, and recognize the objects that…”
Získat plný text

Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks Autor Boroumand, Amirali, Ghose, Saugata, Akin, Berkin, Narayanaswami, Ravi, Oliveira, Geraldo F., Ma, Xiaoyu, Shiu, Eric, Mutlu, Onur

“…Emerging edge computing platforms often contain machine learning (ML) accelerators that can accelerate inference for a wide range of neural network (NN)…”
Získat plný text