Learning to Generate Compositional Color Words and Phrases from Speech – This paper evaluates the performance of speech recognition systems to generate compositional phonemes from a set of given words and phrases, i.e., words with a similar meaning and phrases with similar meanings. We used three distinct speech recognition models for each model, and analyzed the performance of the model on the corpus of 10,000 word sentences. The performance of the neural system on these tasks was evaluated using two different speech recognition models, one trained and one untrained, and the performance of the neural system on the corpus was compared with the test corpus. Based on these results, we propose a novel method to generate sentences in these models based on word-by-word similarity.

We present an end-of-the-art multi-view, multi-stream video reconstruction pipeline based on Deep Learning. Our deep learning is based on using an encoder-decoder architecture to embed a multi-view convolutional network and feed it to the multi-view convolutional network to reconstruct videos. Since the output of the multi-view convolutional network can be different from the outputs of the deep network, it is more sensitive to occlusion, which prevents the reconstruction from using the full range image features. To improve the robustness of the reconstruction task, the convolutional layers are built from a multi-dimensional embedding, which is able to embed both the output and the reconstruction parameters. Experimental results show the proposed method can reconstruct well the full range of images.

The Multidimensional Scaling Solution Revisited: Algorithm and Algorithm Improvement for Graphical Models

Deep Learning of Sentences with Low Dimensionality

Learning to Generate Compositional Color Words and Phrases from Speech

Randomized Convolutional Features Affect Prediction of Cognitive Function

Mapping Images and Video Summaries to Event-PathsWe present an end-of-the-art multi-view, multi-stream video reconstruction pipeline based on Deep Learning. Our deep learning is based on using an encoder-decoder architecture to embed a multi-view convolutional network and feed it to the multi-view convolutional network to reconstruct videos. Since the output of the multi-view convolutional network can be different from the outputs of the deep network, it is more sensitive to occlusion, which prevents the reconstruction from using the full range image features. To improve the robustness of the reconstruction task, the convolutional layers are built from a multi-dimensional embedding, which is able to embed both the output and the reconstruction parameters. Experimental results show the proposed method can reconstruct well the full range of images.