Efficient and effective algorithms for training single-hidden-layer neural networks
70 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Electrical and Electronic Engineering
Citations in the corpus
- Deep Learning: Methods and Applications (2014, methodology): “we can derive batch-mode gradient descent learning algorithm where the gradient takes the following form (Deng and Yu, 2011; Yu and Deng, 2012):”
- Accelerated Parallelizable Neural Network Learning Algorithm for Speech Recognition (2011, methodology): “The weighted accelerated algorithm performs the best, achieving recognition accuracy of 98.9% when the deep belief network (DBN) pretraining algorithm is used to initialize the lower-level neural network weights [13].”
- A deep architecture with bilinear modeling of hidden representations: Applications to phonetic recognition (2012, methodology): “The lower-layer weight matrix W can be optimized using an accelerated gradient descent [7, 8] algorithm to minimize the squared error”
- Enhanced image classification with a fast-learning shallow convolutional neural network (2015, methodology): “N E ] 16 M a r 2015 performance on SVHN. Improved performance on CIFAR-10 is likely to be obtained by better filter selection and introduction of training data augmentation.”
- Trends in extreme learning machines: A review (2015, background): “Yu and Deng (2012) proposed to reduce the size of ELM network by performing gradient descend on θ , i.e., the parameters of the hidden layer.”
- Speech emotion recognition using deep neural network and extreme learning machine (2014, methodology): “Since the number of training utterances is small we use a recently developed classifier, called extreme learning machine (ELM) [6, 18] for this purpose.”