Related papers: Towards training digitally-tied analog blocks via …
To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…
Continuously adapting pre-trained models to local data on resource constrained edge devices is the $\emph{last mile}$ for model deployment. However, as models increase in size and depth, backpropagation requires a large amount of memory,…
Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an…
Current state-of-the-art generative models map noise to data distributions by matching flows or scores. A key limitation of these models is their inability to readily integrate available partial observations and additional priors. In…
Federated learning (FL) is an emerging paradigm for decentralized training of machine learning models on distributed clients, without revealing the data to the central server. The learning scheme may be horizontal, vertical or hybrid (both…
Energy harvesting (EH) IoT devices that operate intermittently without batteries, coupled with advances in deep neural networks (DNNs), have opened up new opportunities for enabling sustainable smart applications. Nevertheless, implementing…
Hybrid-electric propulsion systems powered by clean energy derived from renewable sources offer a promising approach to decarbonise the world's transportation systems. Effective energy management systems are critical for such systems to…
Energy management strategies (EMSs) are the most significant components in hybrid electric vehicles (HEVs) because they decide the potential of energy conservation and emission reduction. This work presents a transferred EMS for a parallel…
Transformer models have emerged as the leading approach for achieving state-of-the-art performance across various application domains, serving as the foundation for advanced large-scale deep learning (DL) models. However, efficiently…
Thanks to the low cost and power consumption, hybrid analog-digital architectures are considered as a promising energy-efficient solution for massive multiple-input multiple-output (MIMO) systems. The key idea is to connect one RF chain to…
Energy beamforming (EB) is a key technique for achieving efficient radio-frequency (RF) transmission enabled wireless energy transfer (WET). By optimally designing the waveforms from multiple energy transmitters (ETs) over the wireless…
The rapid adoption of low-precision arithmetic in artificial intelligence and edge computing has created a strong demand for energy-efficient and flexible floating-point multiply-accumulate (MAC) units. This paper presents a dual-precision…
Compute-in-memory (CIM) has shown significant potential in efficiently accelerating deep neural networks (DNNs) at the edge, particularly in speeding up quantized models for inference applications. Recently, there has been growing interest…
Recent studies from several hyperscalars pinpoint to embedding layers as the most memory-intensive deep learning (DL) algorithm being deployed in today's datacenters. This paper addresses the memory capacity and bandwidth challenges of…
Momentum based optimizers are central to a wide range of machine learning applications. These typically rely on an Exponential Moving Average (EMA) of gradients, which decays exponentially the present contribution of older gradients. This…
Power consumption has become the major concern in neural network accelerators for edge devices. The novel non-volatile-memory (NVM) based computing-in-memory (CIM) architecture has shown great potential for better energy efficiency.…
Integrated photonic neural networks (PNNs) have demonstrated significant potential to complement the digital electronic counterparts [1-3]. Nevertheless, robust and repeatable performance of scalable integrated PNNs is directly tied to the…
A recent take towards Federated Analytics (FA), which allows analytical insights of distributed datasets, reuses the Federated Learning (FL) infrastructure to evaluate the summary of model performances across the training devices. However,…
With mobile networks expected to support services with stringent requirements that ensure high-quality user experience, the ability to apply Feed-Forward Neural Network (FFNN) models to User Equipment (UE) use cases has become critical.…
We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the…