Related papers: Efficient Resource-Constrained Training of Transfo…

Modern AI practices all strive towards the same goal: better results. In the context of deep learning, the term "results" often refers to the achieved accuracy on a competitive problem set. In this paper, we adopt an idea from the emerging…

Seismic full waveform inversion (FWI) is a widely used technique in geophysics for inferring subsurface structures from seismic data. And InversionNet is one of the most successful data-driven machine learning models that is applied to…

This paper studies a WiFi indoor localisation technique based on using a deep learning model and its transfer strategies. We take CSI packets collected via the WiFi standard channel sounding as the training dataset and verify the CNN model…

Attention encoder-decoder model architecture is the backbone of several recent top performing foundation speech models: Whisper, Seamless, OWSM, and Canary-1B. However, the reported data and compute requirements for their training are…

Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks, and to recover the sparse structure of target functions. Although tremendous empirical successes have been achieved, most sparse deep…

Artificial Intelligence (AI) models for time-series in pervasive computing keep getting larger and more complicated. The Transformer model is by far the most compelling of these AI models. However, it is difficult to obtain the desired…

We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…

Autoregressively trained transformers have brought a profound revolution to the world, especially with their in-context learning (ICL) ability to address downstream tasks. Recently, several studies suggest that transformers learn a…

Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the…

Extraction of low-dimensional latent space from high-dimensional observation data is essential to construct a real-time robot controller with a world model on the extracted latent space. However, there is no established method for tuning…

Implicit Neural Representations (INRs) have been recently garnering increasing interest in various research fields, mainly due to their ability to represent large, complex data in a compact, continuous manner. Past work further showed that…

This paper considers opportunistic scheduler (OS) design using statistical channel state information~(CSI). We apply max-weight schedulers (MWSs) to maximize a utility function of users' average data rates. MWSs schedule the user with the…

Hyperspectral image (HSI) classification is one of the most active research topics and has achieved promising results boosted by the recent development of deep learning. However, most state-of-the-art approaches tend to perform poorly when…

Recent transformer-based ASR models have achieved word-error rates (WER) below 4%, surpassing human annotator accuracy, yet they demand extensive server resources, contributing to significant carbon footprints. The traditional server-based…

Subsurface property neural network reparameterized full waveform inversion (FWI) has emerged as an effective unsupervised learning framework, which can invert stably with an inaccurate starting model. It updates the trainable neural network…

Tensor decomposition is one of the well-known approaches to reduce the latency time and number of parameters of a pre-trained model. However, in this paper, we propose an approach to use tensor decomposition to reduce training time of…

We study efficient deep learning training algorithms that process received wireless signals, if a test Signal to Noise Ratio (SNR) estimate is available. We focus on two tasks that facilitate source identification: 1- Identifying the…

Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time. Therefore, reducing the energy consumption has…

A parametric adaptive physics-informed greedy Latent Space Dynamics Identification (gLaSDI) method is proposed for accurate, efficient, and robust data-driven reduced-order modeling of high-dimensional nonlinear dynamical systems. In the…

Neural networks are susceptible to adversarial examples-small input perturbations that cause models to fail. Adversarial training is one of the solutions that stops adversarial examples; models are exposed to attacks during training and…