Related papers: Efficient attention guided 5G power amplifier digi…

We study differentially private (DP) machine learning algorithms as instances of noisy fixed-point iterations, in order to derive privacy and utility results from this well-studied framework. We show that this new perspective recovers…

We introduce a framework for linear precoder design over a massive multiple-input multiple-output downlink system in the presence of nonlinear power amplifiers (PAs). By studying the spatial characteristics of the distortion, we demonstrate…

Deep Neural Networks (DNNs) have shown excellent performance in a wide range of machine learning applications. Knowing the latency of running a DNN model or tensor program on a specific device is useful in various tasks, such as DNN graph-…

In addition to being extremely non-linear, modern problems require millions if not billions of parameters to solve or at least to get a good approximation of the solution, and neural networks are known to assimilate that complexity by…

As a well-known optimization framework, the Alternating Direction Method of Multipliers (ADMM) has achieved tremendous success in many classification and regression applications. Recently, it has attracted the attention of deep learning…

Counting objects in crowded scenes remains a challenge to computer vision. The current deep learning based approach often formulate it as a Gaussian density regression problem. Such a brute-force regression, though effective, may not…

In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…

Nowadays, one practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). It motivates researchers to develop algorithms that can adapt DNN model to multiple…

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…

The use of low numerical precision is a fundamental optimization included in modern accelerators for Deep Neural Networks (DNNs). The number of bits of the numerical representation is set to the minimum precision that is able to retain…

Predictive Process Monitoring (PPM) aims at leveraging historic process execution data to predict how ongoing executions will continue up to their completion. In recent years, PPM techniques for the prediction of the next activities have…

Learning-based model predictive control (MPC) is an approach designed to reduce the computational cost of MPC. In this paper, a constrained deep neural network (DNN) design is proposed to learn MPC policy for nonlinear systems. Using…

Compute-in-memory (PIM) mitigates the memory wall by performing computation within memory, reducing data movement and improving energy efficiency. DRAM-based PIM is particularly attractive due to its high density, mature manufacturing…

In this paper, conditional denoising diffusion probabilistic models (DDPMs) are proposed to enhance the data transmission and reconstruction over wireless channels. The underlying mechanism of DDPM is to decompose the data generation…

In this paper, an algorithm for approximate evaluation of back-propagation in DNN training is considered, which we term Approximate Outer Product Gradient Descent with Memory (Mem-AOP-GD). The Mem-AOP-GD algorithm implements an…

We propose an unsupervised deep learning algorithm for the motion-compensated reconstruction of 5D cardiac MRI data from 3D radial acquisitions. Ungated free-breathing 5D MRI simplifies the scan planning, improves patient comfort, and…

This paper considers the problem of distributed model fitting using the alternating directions method of multipliers (ADMM). ADMM splits the learning problem into several smaller subproblems, usually by partitioning the data samples. The…

We propose a co-design approach for compute-in-memory inference for deep neural networks (DNN). We use multiplication-free function approximators based on ell_1 norm along with a co-adapted processing array and compute flow. Using the…

Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model…

DNNs deployed on analog processing in memory (PIM) architectures are subject to fabrication-time variability. We developed a new joint variability- and quantization-aware DNN training algorithm for highly quantized analog PIM-based models…