Results 21 to 30 of about 827,210 (276)

Evolving Deep Neural Networks [PDF]

, 2019
The success of deep learning depends on finding an architecture to fit the task. As deep learning has scaled up to more challenging tasks, the architectures have become difficult to design by hand. This paper proposes an automated method, CoDeepNEAT, for optimizing deep learning architectures through evolution.
Risto Miikkulainen, Jason Zhi Liang, Elliot Meyerson, Aditya Rawal, Daniel Fink 0003, Olivier Francon, Bala Raju, Hormoz Shahrzad, Arshak Navruzyan, Nigel Duffy, Babak Hodjat   +10 more
openaire   +2 more sources

Enhanced gradient learning for deep neural networks

IET Image Processing, 2022
Deep neural networks have achieved great success in both computer vision and natural language processing tasks. How to improve the gradient flows is crucial in training very deep neural networks. To address this challenge, a gradient enhancement approach
Ming Yan, Jianxi Yang, Cen Chen, Joey Tianyi Zhou, Yi Pan, Zeng Zeng   +5 more
doaj   +1 more source

Explaining deep neural networks

CoRR, 2020
Deep neural networks are becoming more and more popular due to their revolutionary success in diverse areas, such as computer vision, natural language processing, and speech recognition. However, the decision-making processes of these models are generally not interpretable to users.
openaire   +5 more sources

Evaluation of Deep Learning Models for Multi-Step Ahead Time Series Prediction

IEEE Access, 2021
Time series prediction with neural networks has been the focus of much research in the past few decades. Given the recent deep learning revolution, there has been much attention in using deep learning models for time series prediction, and hence it is ...
Rohitash Chandra, Shaurya Goyal, Rishabh Gupta   +2 more
doaj   +1 more source

Deep neural networks outperform human expert's capacity in characterizing bioleaching bacterial biofilm composition

Biotechnology Reports, 2019
Background: Deep neural networks have been successfully applied to diverse fields of computer vision. However, they only outperform human capacities in a few cases.
Antoine Buetti-Dinh, Vanni Galli, Sören Bellenberg, Olga Ilie, Malte Herold, Stephan Christel, Mariia Boretska, Igor V. Pivkin, Paul Wilmes, Wolfgang Sand, Mario Vera, Mark Dopson   +11 more
doaj   +1 more source

Deep Sequential Neural Network

CoRR, 2014
Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process.
Denoyer, Ludovic, Gallinari, Patrick
openaire   +4 more sources

Deep Net Tree Structure for Balance of Capacity and Approximation Ability

Frontiers in Applied Mathematics and Statistics, 2019
Deep learning has been successfully used in various applications including image classification, natural language processing and game theory. The heart of deep learning is to adopt deep neural networks (deep nets for short) with certain structures to ...
Charles K. Chui, Charles K. Chui, Shao-Bo Lin, Shao-Bo Lin, Ding-Xuan Zhou   +4 more
doaj   +1 more source

Frequency Response Mode Prediction of Power System After Large Disturbances Based on Deep Belief Neural Network

IEEE Access, 2023
The power system frequency is an important indicator that reflects the power system’s operating status. Through real-time detection or prediction, it can effectively ensure stable power system operation.
Wenzhuo Wang, Zhiwei Wang, Xin Liu, Wujing Li, Qiufang Li, Yagang Zhang, Qianchang Chen, Shuyu Guo, Zhi Xu   +8 more
doaj   +1 more source

On Numerosity of Deep Neural Networks

CoRR, 2020
Accepted to NeurIPS ...
Xi Zhang 0019, Xiaolin Wu 0001
openaire   +3 more sources

An Interactive Visualization for Feature Localization in Deep Neural Networks

Frontiers in Artificial Intelligence, 2020
Deep artificial neural networks have become the go-to method for many machine learning tasks. In the field of computer vision, deep convolutional neural networks achieve state-of-the-art performance for tasks such as classification, object detection, or ...
Martin Zurowietz, Tim W. Nattkemper
doaj   +1 more source