Related papers: OptINC: Optical In-Network-Computing for Scalable …
The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and…
We introduce the $\textbf{O}$ne-shot $\textbf{P}$runing $\textbf{T}$echnique for $\textbf{I}$nterchangeable $\textbf{N}$etworks ($\textbf{OPTIN}$) framework as a tool to increase the efficiency of pre-trained transformer architectures…
Optical computing has reemerged as a promising alternative computing paradigm for providing energy-efficient information processing in the age of artificial intelligence. Among various photonic neural network platforms, diffractive optical…
We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers). We assume the communication network between the workers is synchronized and can be…
Deep learning for distribution grid optimization can be advocated as a promising solution for near-optimal yet timely inverter dispatch. The principle is to train a deep neural network (DNN) to predict the solutions of an optimal power flow…
Deep learning has been used in a wide range of areas and made a huge breakthrough. With the ever-increasing model size and train-ing data volume, distributed deep learning emerges which utilizes a cluster to train a model in parallel.…
In the evolution towards 6G, integrating Artificial Intelligence (AI) with advanced network infrastructure emerges as a pivotal strategy for enhancing network intelligence and resource utilization. Existing distributed learning frameworks…
Distributed learning is the problem of inferring a function in the case where training data is distributed among multiple geographically separated sources. Particularly, the focus is on designing learning strategies with low computational…
Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more…
The optical neural network (ONN) is a promising hardware platform for next-generation neurocomputing due to its high parallelism, low latency, and low energy consumption. Previous ONN architectures are mainly designed for general matrix…
To reduce uploading bandwidth and address privacy concerns, deep learning at the network edge has been an emerging topic. Typically, edge devices collaboratively train a shared model using real-time generated data through the Parameter…
Diffractive neural network (DNN), which can perform machine learning tasks based on the light propagation and diffraction, has recently emerged as a promising optical computing paradigm due to its high parallel processing speed and low…
Projection-based model reduction enables efficient simulation of complex dynamical systems by constructing low-dimensional surrogate models from high-dimensional data. The Operator Inference (OpInf) approach learns such reduced surrogate…
Realization of deep learning with coherent optical field has attracted remarkably attentions presently, which benefits on the fact that optical matrix manipulation can be executed at speed of light with inherent parallel computation as well…
Facing the upcoming era of Internet-of-Things and connected intelligence, efficient information processing, computation, and communication design becomes a key challenge in large-scale intelligent systems. Recently, Over-the-Air (OtA)…
Enabling large-scale energy-efficient Internet-of-things (IoT) connectivity is an essential step towards realization of networked society. While legacy wide-area wireless systems are highly dependent on network-side coordination, the level…
Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some…
Recent advancements in machine learning (ML) have enabled its deployment on resource-constrained edge devices, fostering innovative applications such as intelligent environmental sensing. However, these devices, particularly…
Fog computing promises to enable machine learning tasks to scale to large amounts of data by distributing processing across connected devices. Two key challenges to achieving this goal are heterogeneity in devices compute resources and…
In multicenter biomedical research, integrating data from multiple decentralized sites provides more robust and generalizable findings due to its larger sample size and the ability to account for the between-site heterogeneity. However,…