Related papers: Optimisation challenge for superconducting adiabat…
Stochastic gradient descent (SGD) is the main approach for training deep networks: it moves towards the optimum of the cost function by iteratively updating the parameters of a model in the direction of the gradient of the loss evaluated on…
The backpropagation algorithm has experienced remarkable success in training large-scale artificial neural networks; however, its biological plausibility has been strongly criticized, and it remains an open question whether the brain…
We develop an online gradient algorithm for optimizing the performance of product-form networks through online adjustment of control parameters. The use of standard algorithms for finding optimal parameter settings is hampered by the…
Deep learning is able to functionally simulate the human brain and thus, it has attracted considerable interest. Optics-assisted deep learning is a promising approach to improve the forward-propagation speed and reduce the power…
We consider energy-efficient multi-user hybrid downlink beamforming (BF) and power allocation under imperfect channel state information (CSI) and probabilistic outage constraints. In this domain, classical optimization methods resort to…
The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…
In this paper we study the problem of learning a shallow artificial neural network that best fits a training data set. We study this problem in the over-parameterized regime where the number of observations are fewer than the number of…
In this paper, we consider the problem of joint antenna selection and analog beamformer design in downlink single-group multicast networks. Our objective is to reduce the hardware costs by minimizing the number of required phase shifters at…
We develop a weak adversarial approach to solving obstacle problems using neural networks. By employing (generalised) regularised gap functions and their properties we rewrite the obstacle problem (which is an elliptic variational…
In this paper, we propose a novel deep transfer learning method called deep implicit distribution alignment networks (DIDAN) to deal with cross-corpus speech emotion recognition (SER) problem, in which the labeled training (source) and…
Modern deep learning models are usually highly over-parameterized so that they can overfit the training data. Surprisingly, such overfitting neural networks can usually still achieve high prediction accuracy. To study this "benign…
Functional bilevel methods estimate a lower-level function and plug it into a hypergradient, but this plug-in gradient can retain first-order bias when the lower-level problem is learned nonparametrically. To remove this bias, we develop a…
Models with dominant advection always posed a difficult challenge for projection-based reduced order modelling. Many methodologies that have recently been proposed are based on the pre-processing of the full-order solutions to accelerate…
This paper introduces a new, highly energy-efficient, Adiabatic Capacitive Neuron (ACN) hardware implementation of an Artificial Neuron (AN) with improved functionality, accuracy, robustness and scalability over previous work. The paper…
In this study, we propose a novel machine learning based algorithm to improve the performance of beyond 5 generation (B5G) wireless communication system that is assisted by Orthogonal Frequency Division Multiplexing (OFDM) and…
Optimization of neural network (NN) significantly influenced by the transfer function used in its active nodes. It has been observed that the homogeneity in the activation nodes does not provide the best solution. Therefore, the…
We propose an algorithm to explore the global optimization method, using SAT solvers, for training a neural net. Deep Neural Networks have achieved great feats in tasks like-image recognition, speech recognition, etc. Much of their success…
A novel method for learning optimal, orthonormal wavelet bases for representing 1- and 2D signals, based on parallels between the wavelet transform and fully connected artificial neural networks, is described. The structural similarities…
In massive multiple-input multiple-output (MIMO) systems, hybrid analog-digital (AD) beamforming can be used to attain a high directional gain without requiring a dedicated radio frequency (RF) chain for each antenna element, which…
The vanilla fractional order gradient descent may oscillatively converge to a region around the global minimum instead of converging to the exact minimum point, or even diverge, in the case where the objective function is strongly convex.…