On a Generative Baseline for Modeling Clinical Trials – Converting a single model to a multiple model learning problem is a very challenging algorithm in practice. In contrast, an appropriate solution is a multi-model problem, which combines two distinct types of problems: a multi-view case over the whole problem and a multi-view case over each instance, each with its own set of desirable properties. In this paper, we extend both approaches to the same problem, where the underlying multi-view case is a case over two distinct views. We provide a formal language for such a task, for which a multi-view model is more than a single view, and show how to construct an improved one from scratch. We provide computational examples of the problem in a dataset of 60,000 patients as well as a benchmark problem with similar sample size using both models. We demonstrate that the proposed language can be very useful for this situation.
Although there are many approaches to learning image models, most models focus on image labels for training purposes. In this paper, we propose to transfer learning of the image semantic labels to the training of the feature vectors into a novel learning framework, using the same label learning framework. We demonstrate several applications of our method using different data sets for different tasks: (i) a CNN with feature vectors of varying dimensionality, and (ii) a fully-convolutional network trained with a neural network. We compare our methods to the state-of-the-art image semantic labeling methods, including the recently proposed neural network or CNN learning in ImageNet and ResNet-15K and our method has outperformed them for both tasks. We conclude with a comparison of our network with many state-of-the-art CNN and ResNet-15K datasets.
Sparse Deep Structured Prediction with Latent Variables
Using the Multi-dimensional Bilateral Distribution for Textual Discrimination
On a Generative Baseline for Modeling Clinical Trials
Learning from Continuous Events with the Gated Recurrent Neural Network
Determining Point Process with Convolutional Kernel Networks Using the Dropout MethodAlthough there are many approaches to learning image models, most models focus on image labels for training purposes. In this paper, we propose to transfer learning of the image semantic labels to the training of the feature vectors into a novel learning framework, using the same label learning framework. We demonstrate several applications of our method using different data sets for different tasks: (i) a CNN with feature vectors of varying dimensionality, and (ii) a fully-convolutional network trained with a neural network. We compare our methods to the state-of-the-art image semantic labeling methods, including the recently proposed neural network or CNN learning in ImageNet and ResNet-15K and our method has outperformed them for both tasks. We conclude with a comparison of our network with many state-of-the-art CNN and ResNet-15K datasets.