Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS), however, previous method...
The state-of-art approach for speaker verification consists of a neural network based embedding extractor along with a backend generative model such as the Probabilistic Linear Discriminant Analysis (PLDA). In this work, we propose a neural network a...
This paper proposes a new parametric level set method for topology optimization based on Deep Neural Network (DNN). In this method, the fully connected deep neural network is incorporated into the conventional level set methods to construct an effect...
We present a novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs. To justify the usage of neural networks, we prove that they are universal approximators of transport plans between pro...
Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to transfer valuab...
Topic modelling has been a successful technique for text analysis for almost twenty years. When topic modelling met deep neural networks, there emerged a new and increasingly popular research area, neural topic models, with over a hundred models deve...
Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a...
In this paper we propose a new approach to quantum neural networks. Our multi-layer architecture avoids the use of measurements that usually emulate the non-linear activation functions which are characteristic of the classical neural networks. Despit...
Objective: A model is presented to evaluate the viability of using electrical impedance tomography (EIT) with a nerve cuff to record neural activity in peripheral nerves. Approach: Established modelling approaches in neural-EIT are expanded on to be...
Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural vocoder. The gen...
In deep neural network modeling, the most common practice is to stack a number of recurrent, convolutional, or feed-forward layers in order to obtain high-quality continuous space representations which in turn improves the quality of the network's pr...
Proposing a neural network architecture capable of classifying protein organelle localization labels, the proposed model was able to reach an accuracy of 95 percent for test data and training data. The proposed model deals with the input of the proposed neural network as three-di…
Deep neural networks and the ENO procedure are both efficient frameworks for approximating rough functions. We prove that at any order, the ENO interpolation procedure can be cast as a deep ReLU neural network. This surprising fact enables the transf...
Background The sinking of the Titanic is one of the most infamous shipwrecks in history. On April 15, 1912, during her maiden voyage, the widely considered “unsinkable” RMS Titanic sank after colliding with an iceberg. Unfortunately, there weren’t enough lifeboats for everyone on…
With the popularity of implicit neural representations, or neural radiance fields (NeRF), there is a pressing need for editing methods to interact with the implicit 3D models for tasks like post-processing reconstructed scenes and 3D content creation...
Can engineering neural networks be approached in a disciplined way similar to how engineers build software for civil aircraft? We present nn-dependability-kit, an open-source toolbox to support safety engineering of neural networks for autonomous dri...
We introduce CN-DHF (Compact Neural Double-Height-Field), a novel hybrid neural implicit 3D shape representation that is dramatically more compact than the current state of the art. Our representation leverages Double-Height-Field (DHF) geometries, d...
Physics-informed neural networks (PINNs) have attracted attention as an alternative approach to solve partial differential equations using a deep neural network (DNN). Their simplicity and capability allow them to solve inverse problems for many appl...
Mar 8, 2018 · A convolutional neural network (CNN) is a neural network where one or more of the layers employs a convolution as the function applied to the output of the previous layer.
Mar 8, 2018 · A convolutional neural network (CNN) is a neural network where one or more of the layers employs a convolution as the function applied to the output of the previous layer.