相关论文: Automatic Noise Filtering with Dynamic Sparse Trai…

Supervised fine-tuning (SFT) plays a crucial role in adapting large language models (LLMs) to specific domains or tasks. However, as demonstrated by empirical experiments, the collected data inevitably contains noise in practical…

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…

Traditional supervised denoising networks learn network weights through "black box" (pixel-oriented) training, which requires clean training labels. The uninterpretability nature of such denoising networks in addition to the requirement for…

This paper describes a novel technique for promoting sparsity in the modified filtered-x algorithms required for active noise control. The proposed algorithms are based on recent techniques incorporating approximations to the \ell_0-norm in…

Recent work on audio-visual navigation targets a single static sound in noise-free audio environments and struggles to generalize to unheard sounds. We introduce the novel dynamic audio-visual navigation benchmark in which an embodied AI…

We present a novel network pruning algorithm called Dynamic Sparse Training that can jointly find the optimal network parameters and sparse network structure in a unified optimization process with trainable pruning thresholds. These…

Machine learning is currently a trending topic in various science and engineering disciplines, and the field of geophysics is no exception. With the advent of powerful computers, it is now possible to train the machine to learn complex…

The notion of incremental learning is to train an ANN algorithm in stages, as and when newer training data arrives. Incremental learning is becoming widespread in recent times with the advent of deep learning. Noise in the training data…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

As our ability to sense increases, we are experiencing a transition from data-poor problems, in which the central issue is a lack of relevant data, to data-rich problems, in which the central issue is to identify a few relevant features in…

The strategy of combining diffusion-based generative models with classifiers continues to demonstrate state-of-the-art performance on adversarial robustness benchmarks. Known as adversarial purification, this exploits a diffusion model's…

We propose ARiSE, an auto-regressive algorithm for multi-channel speech enhancement. ARiSE improves existing deep neural network (DNN) based frame-online multi-channel speech enhancement models by introducing auto-regressive connections,…

Feature-mapping with deep neural networks is commonly used for single-channel speech enhancement, in which a feature-mapping network directly transforms the noisy features to the corresponding enhanced ones and is trained to minimize the…

Recent advancements in robotics, control, and machine learning have facilitated progress in the challenging area of object manipulation. These advancements include, among others, the use of deep neural networks to represent dynamics that…

Deepfake detectors face growing challenges in generalization as new image synthesis techniques emerge. In particular, deepfakes generated by diffusion models are highly photorealistic and often evade detectors trained on GAN-based…

Smart sensing provides an easier and convenient data-driven mechanism for monitoring and control in the built environment. Data generated in the built environment are privacy sensitive and limited. Federated learning is an emerging paradigm…

Deep Reinforcement Learning (DRL) solutions are becoming pervasive at the edge of the network as they enable autonomous decision-making in a dynamic environment. However, to be able to adapt to the ever-changing environment, the DRL…

The intelligibility of speech severely degrades in the presence of environmental noise and reverberation. In this paper, we propose a novel deep learning based system for modifying the speech signal to increase its intelligibility under the…

Machine learning, particularly deep neural network inference, has become a vital workload for many computing systems, from data centers and HPC systems to edge-based computing. As advances in sparsity have helped improve the efficiency of…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…