Training algorithms for convolutional neural networks
نویسندگان
چکیده
منابع مشابه
Towards dropout training for convolutional neural networks
Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this...
متن کاملSemi-Supervised Training of Convolutional Neural Networks
In this paper we discuss a method for semi-supervised training of CNNs. By using auto-encoders to extract features from unlabeled images, we can train CNNs to accurately classify images with only a small set of labeled images. We show our method’s results on a shallow CNN using the CIFAR-10 dataset, and some preliminary results on a VGG-16 network using the STL-10 dataset.
متن کاملImplementation of Training Convolutional Neural Networks
Deep learning refers to a shining branch of machine learning that is based on learning levels of representations. Convolutional Neural Networks (CNN) is one kind of deep neural network. It can study concurrently. In this article, we use convolutional neural network to implement the typical face recognition problem which can overcome the influence of pose or resolution in face recognition. Then,...
متن کاملIncremental Training of Deep Convolutional Neural Networks
We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initialization. We demonstrate that our incremental approach reaches the reference netw...
متن کاملEffective training algorithms for RBF-neural networks
New structure and training algorithms of the RBF-type neural network are proposed. An extra neuron layer is added to realize the principal component method. A novel training algorithm is designed for training each separate neuron in the hidden layer, which guarantees the efficiency and finiteness of the training procedure. Results were obtained for a variety of problems. In particular, the resu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Yugra State University Bulletin
سال: 2019
ISSN: 2078-9114,1816-9228
DOI: 10.17816/byusu20190141-54