Related papers: Improving Initial Transients of Online Learning Ec…
Performing machine learning with analog signals offers advantages in speed and energy efficiency, but sensitivity to component and measurement imperfections often foils training without a system-specific companion digital model. Here we…
Recent research shows that supervised learning can be an effective tool for designing near-optimal feedback controllers for high-dimensional nonlinear dynamic systems. But the behavior of neural network controllers is still not well…
Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal…
This paper proposes an Online Control-Informed Learning (OCIL) framework, which employs the well-established optimal control and state estimation techniques in the field of control to solve a broad class of learning tasks in an online…
Online Feedback Optimization (OFO) controllers steer a system to its optimal operating point by treating optimization algorithms as auxiliary dynamic systems. Implementation of OFO controllers requires setting the parameters of the…
Artificial neural networks (ANNs) have demonstrated outstanding performance in numerous tasks, but deployment in resource-constrained environments remains a challenge due to their high computational and memory requirements. Spiking neural…
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence…
Wireless sensor networks (WSN) acts as the backbone of Internet of Things (IoT) technology. In WSN, field sensing and fusion are the most commonly seen problems, which involve collecting and processing of a huge volume of spatial samples in…
Attention-based neural networks such as transformers have revolutionized various fields such as natural language processing, genomics, and vision. Here, we demonstrate the use of transformers for quantum feedback control through both a…
Deep neural networks (NNs) have exhibited considerable potential for efficiently balancing the performance and complexity of multiple-input and multiple-output (MIMO) detectors. We propose a receiver framework that enables efficient online…
In the present work, an embedded PI controller is designed for speed regulation of DC servomotor over a wireless network. The embedded controller integrates PI controller with a proposed time-delay estimator and an adaptive digital Smith…
It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…
DNNs are becoming less and less over-parametrised due to recent advances in efficient model design, through careful hand-crafted or NAS-based methods. Relying on the fact that not all inputs require the same amount of computation to yield a…
In recent years, distributed optimization is proven to be an effective approach to accelerate training of large scale machine learning models such as deep neural networks. With the increasing computation power of GPUs, the bottleneck of…
Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) algorithms struggle in POMDP environments because the state of…
Spiking Neural Networks (SNN) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge devices through asynchronous and sparse processing. However, being temporal models, SNNs depend…
This paper develops a persistently exciting input generating Online Feedback Optimization (OFO) controller that estimates the sensitivity of a process ensuring minimal deviations from the descent direction while converging. This eliminates…
Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…
This paper presents early work aiming at the development of a new framework for the design and analysis of algorithms for online learning based prediction and control. Firstly, we consider the task of predicting values of a function or time…
In this paper, we consider the problem of finding a meta-learning online control algorithm that can learn across the tasks when faced with a sequence of $N$ (similar) control tasks. Each task involves controlling a linear dynamical system…