Learning with a Hybrid CRT Processor – While traditional CRT processors are designed to work with a single linear model, hybrid CRT processors provide a fully integrated model that can be generalized in any way. To overcome the problem of model selection, we suggest using a hybrid CRT model for the tasks of model selection and training. As input to the hybrid CRT model is the number of attributes, we propose a discriminative CRT model that can identify the most discriminative attributes for a CRT model, which can be used for selection. We demonstrate that the proposed CRT model can generalize well to different domains and models.
Deep neural networks (DNNs) have become the standard tool for many tasks, like image recognition and semantic clustering. However, the quality of the results obtained using the DNNs and their performance is often limited due to their high power. In this work, we show that the power-hungry DNNs perform better than others at several tasks. In particular, by using a simple and efficient DNN, we demonstrate that even a small sample of a DNN outperforms the best DNN in performance, and is comparable to the best DNN in performance in state-of-the-art ImageNet benchmark.
A Novel Fuzzy Logic Algorithm for the Decision-Logic Task
Learning with a Hybrid CRT Processor
Learning Deep Transform Architectures using Label Class Regularized Deep Convolutional Neural NetworksDeep neural networks (DNNs) have become the standard tool for many tasks, like image recognition and semantic clustering. However, the quality of the results obtained using the DNNs and their performance is often limited due to their high power. In this work, we show that the power-hungry DNNs perform better than others at several tasks. In particular, by using a simple and efficient DNN, we demonstrate that even a small sample of a DNN outperforms the best DNN in performance, and is comparable to the best DNN in performance in state-of-the-art ImageNet benchmark.