Related papers: Machine Learning Models to Identify Promising Nest…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Neural architecture search (NAS) is an attractive approach to automate the design of optimized architectures but is constrained by high computational budget, especially when optimizing for multiple, important conflicting objectives. To…

Optical computing offers potential for ultra high-speed and low latency computation by leveraging the intrinsic properties of light. Here, we explore the use of highly nonlinear optical fibers (HNLFs) as platforms for optical computing…

Efficient audio feature extraction is critical for low-latency, resource-constrained speech recognition. Conventional preprocessing techniques, such as Mel Spectrogram, Perceptual Linear Prediction (PLP), and Learnable Spectrogram, achieve…

In this work, mechanical and optical characterization of a new type of suspended core fiber (SCF) has been performed. The proposed SCF along with additional central air holes exhibits an unusual property of fundamental mode cutoff at short…

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…

Energy efficiency and reliability have long been crucial factors for ensuring cost-effective and safe missions in autonomous systems computers. With the rapid evolution of industries such as space robotics and advanced air mobility, the…

Anomaly and missing data constitute a thorny problem in industrial applications. In recent years, deep learning enabled anomaly detection has emerged as a critical direction, however the improved detection accuracy is achieved with the…

Federated learning (FL) enables distributed training while preserving data privacy, but stragglers-slow or incapable clients-can significantly slow down the total training time and degrade performance. To mitigate the impact of stragglers,…

High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…

We implement a differentiable Neural Architecture Search (NAS) method inspired by FBNet for discovering neural networks that are heavily optimized for a particular target device. The FBNet NAS method discovers a neural network from a given…

Machine learning models differ in terms of accuracy, computational/memory complexity, training time, and adaptability among other characteristics. For example, neural networks (NNs) are well-known for their high accuracy due to the quality…

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing…

Simple structures are always a pursuit but sometimes not easily attainable. It took researchers nearly two decades for conceiving the structure of single-ring hollow-core negative curvature fiber (NCF). Recently NCF eventually approaches to…

Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. However, CNNs are typically very demanding computationally at…

Hierarchical feature discovery using non-spiking convolutional neural networks (CNNs) has attracted much recent interest in machine learning and computer vision. However, it is still not well understood how to create a biologically…

This paper proposes a hard-constrained unsupervised learning framework for rapidly solving the non-linear and non-convex AC optimal power flow (AC-OPF) problem in real-time operation. Without requiring ground-truth AC-OPF solutions,…

Efficient deployment of neural networks (NN) requires the co-optimization of accuracy and latency. For example, hardware-aware neural architecture search has been used to automatically find NN architectures that satisfy a latency constraint…

The MagNet Challenge 2023 calls upon competitors to develop data-driven models for the material-specific, waveform-agnostic estimation of steady-state power losses in toroidal ferrite cores. The following HARDCORE (H-field and power loss…

Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such…