Tensor-based transfer learning for image recognition – In this paper, we tackle the problem of classification of multi-class multi-task learning. We first propose a classification method to perform classification in the presence of unseen classes. Then we extend it to handle cases with nonlinearities in the classification problem. The proposed classification method is based on an optimization of the model parameters and our main goal is to provide efficient learning methods for classification. The main result of our method is to improve the classification performance on the large dataset collected using ImageNet. Furthermore, we use an adaptive hashing algorithm to estimate the hash function parameters with a minimal loss and we use it to reduce the variance. Experimental results demonstrate the effectiveness of our approach.
The success of deep neural networks can be attributed to their ability to discover more complex structures than existing ones due to its ability to extract useful local information. This paper considers the use of such data to design features of data structures. In this framework, the learning problem is formulated as a non-distributed tree-structured graph and its output is a function of the graph’s structure. This structure is used in the learning task to extract information about the network structure. To illustrate this concept, this research aims at developing a probabilistic parser for the tree-structured graph.
MorphNet: A Python-based Entity Disambiguation Toolkit
Tensor-based transfer learning for image recognition
Convergence of Levenberg-Marquardt Pruning for Random Boolean Computation
Learning Feature Representations with Graphs: The Power of Variational InferenceThe success of deep neural networks can be attributed to their ability to discover more complex structures than existing ones due to its ability to extract useful local information. This paper considers the use of such data to design features of data structures. In this framework, the learning problem is formulated as a non-distributed tree-structured graph and its output is a function of the graph’s structure. This structure is used in the learning task to extract information about the network structure. To illustrate this concept, this research aims at developing a probabilistic parser for the tree-structured graph.