Results 211 to 220 of about 6,478,030 (244)

Training neural networks with policy gradient

2017 International Joint Conference on Neural Networks (IJCNN), 2017
Neural networks are a powerful function approximation tool which has the ability to model any function with arbitrary precision. For any function as a black box, it is able to reconstruct the function given the target and the input data. However, there are problems where the target is at least partially unknown.
Sourabh Bose, Manfred Huber
openaire   +1 more source

Manifold Neural Network with Non-Gradient Optimization

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient
Rui Zhang 0017, Ziheng Jiao, Hongyuan Zhang 0001, Xuelong Li 0001   +3 more
openaire   +3 more sources

Inversion of neural networks by gradient descent

Parallel Computing, 1990
Abstract Inversion answers the question of which input patterns to a trained multilayer neural network approximate a given output target. This method is a tool for visualization of the information processing capability of a network stored in its weights. This knowledge about the network enables one to make informed decisions on the improvement of
Jörg Kindermann, Alexander Linden 0002
openaire   +2 more sources

Regularizing Neural Networks with Gradient Monitoring

2019
Neural networks are the most evolving artificial intelligence method in recent times and have been used for the most complex cognitive tasks. The success of these models has re-scripted many of the benchmark tests in a wide array of fields such as image recognition, natural language processing and speech recognition.
Gavneet Singh Chadha, Elnaz Meydani, Andreas Schwung   +2 more
openaire   +1 more source

Diagrammatic Derivation of Gradient Algorithms for Neural Networks

Neural Computation, 1996
Deriving gradient algorithms for time-dependent neural network structures typically requires numerous chain rule expansions, diligent bookkeeping, and careful manipulation of terms. In this paper, we show how to derive such algorithms via a set of simple block diagram manipulation rules.
Eric A. Wan, Françoise Beaufays
openaire   +1 more source

Gradient Boosting with Neural Networks

2019
Gradient boosting machines form a family of powerful machine learning techniques that have been applied with success in a wide range of practical applications. Ensemble techniques rely on simple averaging of models in the ensemble. The family of boosting methods adopts a different strategy to construct ensembles.
Michel Denuit, Donatien Hainaut, Julien Trufin   +2 more
openaire   +1 more source

Overfitting and neural networks: conjugate gradient and backpropagation

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, 2000
Methods for controlling the bias/variance tradeoff typically assume that overfitting or overtraining is a global phenomenon. For multi-layer perceptron (MLP) neural networks, global parameters such as the training time, network size, or the amount of weight decay are commonly used to control the bias/variance tradeoff.
Steve Lawrence, C. Lee Giles
openaire   +1 more source

Gradient Learning Algorithm for Ensembling Neural Network

2006 9th International Conference on Control, Automation, Robotics and Vision, 2006
Aimed at similarity between neural network ensemble and simple neural network, a novel gradient learning algorithm for ensemble (GLAENN) is presented based on the gradient descent method. The new algorithm can improve the generalization error by modifying subnet weights after the ensemble subnets are trained individually.
Jiang Meng, Kun An
openaire   +2 more sources

Structural optimization by gradient-based neural networks

International Journal for Numerical Methods in Engineering, 1999
Summary: We present a neurocomputing strategy which combines data processing capabilities of neural networks and numerical structural optimization. In this strategy, we use an improved counterpropagation neural network. Two artificial neural networks are trained, one for the constraints and the other for the gradients of the constraints, and structural
Ibranmanesh, A., Kaveh, A.
openaire   +2 more sources

Bistable Gradient Neural Networks: Their Computational Properties

2001
A novel type of gradient attractor neural network is described that is characterized by bistable dynamics of nodes and their linear coupling. In contrast to the traditional perceptron-based neural networks which are plagued by spurious states it is found that this Bistable Gradient Network (BGN) is virtually free from spurious states.
Vladimir Chinarov, Michael Menzinger
openaire   +1 more source