English
Related papers

Related papers: Sensitivity-Aware Finetuning for Accuracy Recovery…

200 papers

Training deep neural networks (DNNs) requires significantly more computation and memory than inference, making runtime adaptation of DNNs challenging on resource-limited IoT platforms. We propose InstantFT, an FPGA-based method for…

Machine Learning · Computer Science 2025-06-10 Keisuke Sugiura , Hiroki Matsutani

It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow…

Machine Learning · Computer Science 2021-05-03 Youjiang Xu , Linchao Zhu , Lu Jiang , Yi Yang

Optical Neural Networks (ONNs) promise significant advantages over traditional electronic neural networks, including ultrafast computation, high bandwidth, and low energy consumption, by leveraging the intrinsic capabilities of photonics.…

Neural and Evolutionary Computing · Computer Science 2025-06-30 Gianluca Kosmella , Ripalta Stabile , Jaron Sanders

Imaging systems' performance at low light intensity is affected by shot noise, which becomes increasingly strong as the power of the light source decreases. In this paper we experimentally demonstrate the use of deep neural networks to…

Image and Video Processing · Electrical Eng. & Systems 2018-12-19 Alexandre Goy , Kwabena Arthur , Shuai Li , George Barbastathis

Large-scale multilingual ASR models like Whisper excel in high-resource settings but face challenges in low-resource scenarios, such as rare languages and code-switching (CS), due to computational costs and catastrophic forgetting. We…

Computation and Language · Computer Science 2025-09-29 Hongli Yang , Yizhou Peng , Hao Huang , Sheng Li

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

Machine Learning · Statistics 2026-01-06 Hai-Vy Nguyen , Fabrice Gamboa , Sixin Zhang , Reda Chhaibi , Serge Gratton , Thierry Giaccone

Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images. Requiring a large collection of images and their associated annotations is one of the main bottlenecks limiting the adoption…

Computer Vision and Pattern Recognition · Computer Science 2019-08-22 Zahra Mirikharaji , Yiqi Yan , Ghassan Hamarneh

Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability for resource-constrained edge devices. While low-precision neural network…

Machine Learning · Computer Science 2025-07-01 Jingxiao Ma , Priyadarshini Panda , Sherief Reda

Detecting machine malfunctions at an early stage is crucial for reducing interruptions in operational processes within industrial settings. Recently, the deep learning approach has started to be preferred for the detection of failures in…

Sound · Computer Science 2023-12-05 Mustafa Yurdakul , Sakir Tasdemir

Analog Compute-In-Memory (CIM) architectures promise significant energy efficiency gains for neural network inference, but suffer from complex hardware-induced noise that poses major challenges for deployment. While noise-aware training…

Machine Learning · Computer Science 2025-08-19 Yuannuo Feng , Wenyong Zhou , Yuexi Lyu , Yixiang Zhang , Zhengwu Liu , Ngai Wong , Wang Kang

AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networks (PNNs), which use physical substrates for computation,…

Supervised fine-tuning (SFT) is a standard approach to adapting large language models (LLMs) to new domains. In this work, we improve the statistical efficiency of SFT by selecting an informative subset of training examples. Specifically,…

Machine Learning · Computer Science 2025-05-22 Rohan Deb , Kiran Thekumparampil , Kousha Kalantari , Gaurush Hiranandani , Shoham Sabach , Branislav Kveton

This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Satoshi Suzuki , Shin'ya Yamaguchi , Shoichiro Takeda , Sekitoshi Kanai , Naoki Makishima , Atsushi Ando , Ryo Masumura

Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating key parameters or subsets of data. Existing approaches…

Machine Learning · Computer Science 2026-03-11 Kai Yao , Zhenghan Song , Kaixin Wu , Mingjie Zhong , Danzhao Cheng , Zhaorui Tan , Yixin Ji , Penglei Gao

Quantization-aware training (QAT) schemes have been shown to achieve near-full precision accuracy. They accomplish this by training a quantized model for multiple epochs. This is computationally expensive, mainly because of the full…

Machine Learning · Computer Science 2024-11-19 Saleh Ashkboos , Bram Verhoef , Torsten Hoefler , Evangelos Eleftheriou , Martino Dazzi

Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities.…

Machine Learning · Computer Science 2026-01-06 Muxi Diao , Lele Yang , Wuxuan Gong , Yutong Zhang , Zhonghao Yan , Yufei Han , Kongming Liang , Weiran Xu , Zhanyu Ma

Spiking neural networks (SNNs) are a natural computational model for on-sensor and near-sensor vision, where event driven processors must operate under strict power budgets with hard binary spikes. However, models trained with surrogate…

Neural and Evolutionary Computing · Computer Science 2026-04-14 Maximilian Nicholson

Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Han Yang , Tianyu Wang , Xiaowei Hu , Chi-Wing Fu

Quantization is a critical step to enable efficient LLM serving under limited resource. However, previous research observes that certain weights in the LLM, known as outliers, are significantly sensitive to quantization noises. Existing…

Machine Learning · Computer Science 2025-03-18 Dongwei Wang , Huanrui Yang

Attention mechanisms have emerged as important tools that boost the performance of deep models by allowing them to focus on key parts of learned embeddings. However, current attention mechanisms used in speaker recognition tasks fail to…

Sound · Computer Science 2022-07-21 Amirhossein Hajavi , Ali Etemad
‹ Prev 1 3 4 5 6 7 10 Next ›