Results 181 to 190 of about 298,507 (214)
Some of the next articles are maybe not open access.

Deep neural networks

2020
Deep learning (DL) is a family of machine learning methods capable of detecting multiple levels of latent representations from the data. This is achieved by combining consecutive layers of simple nonlinear transformations that allow the extraction of increasingly abstract features.
Vieira, Sandra   +3 more
openaire   +2 more sources

Deep Neural Networks

2019
In Chap. 1, our empirical analysis was based on neural networks with a single hidden layer. These networks, called shallow, are in theory universal approximators of any continuous function. Deep neural networks use instead a cascade of multiple layers of hidden neurons. Each successive layer uses the output from the previous layer as input.
Michel Denuit   +2 more
openaire   +1 more source

Deep Neural Networks-II

2019
We will implement a multi-layered neural network with different hyperparameters Hidden layer activations Hidden layer nodes Output layer activation Learning rate Mini-batch size Initialization Value of \(\beta \) Values of \(\beta _1\) Value of \(\beta _2\) Value of \(\epsilon \) Value of keep_prob
openaire   +1 more source

Deep Neural Networks for QSAR

2021
Quantitative structure-activity relationship (QSAR) models are routinely applied computational tools in the drug discovery process. QSAR models are regression or classification models that predict the biological activities of molecules based on the features derived from their molecular structures.
openaire   +2 more sources

Deep Neural Networks

2014
In this chapter, we introduce deep neural networks (DNNs)—multilayer perceptrons with many hidden layers. DNNs play an important role in the modern speech recognition systems, and are the focus of the rest of the book. We depict the architecture of DNNs, describe the popular activation functions and training criteria, illustrate the famous ...
Dong Yu, Li Deng
openaire   +1 more source

Manifold regularized deep neural networks

Interspeech 2014, 2014
Deep neural networks (DNNs) have been successfully applied to a variety of automatic speech recognition (ASR) tasks, both in discriminative feature extraction and hybrid acoustic modeling scenarios. The development of improved loss functions and regularization approaches have resulted in consistent reductions in ASR word error rates (WERs).
Vikrant Singh Tomar, Rose, Richard C.
openaire   +1 more source

P–nets: Deep Polynomial Neural Networks

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Accepted in CVPR ...
Chrysos, Grigorios G.   +5 more
openaire   +1 more source

Deep Neural Networks

2023
Christopher M. Bishop, Hugh Bishop
openaire   +1 more source

Deep Eutectic Solvents: A Review of Fundamentals and Applications

Chemical Reviews, 2021
Brian Chen, Yong Zhang, Jeffrey M Klein
exaly  

Home - About - Disclaimer - Privacy