Reconstructing the Human Mind – We present an in-depth analysis of the human cognition of the artificial brain, which is achieved through the design of a new architecture called The Cognitive Software Module . The architecture is an intelligent computer-based system that can use the knowledge conveyed by human brains to construct a human-like computer. We first investigate the different aspects of Human Cognitive Software . Some of them include the design of a functional and efficient human brain, the ability to use knowledge from the human brain to form an intelligent computer. In our application, we implemented a prototype and evaluated the implementation process on the IBM Watson-100 platform, where it was tested on three tasks (thinking, reasoning and problem solving, with all objects in a given category and categories being represented by a set of data, in order to generate some meaningful and informative suggestions), such as human categorization. From the performance of our approach, we conclude that this functional architecture is more suitable for a human-like system.
A new technique called negative image enhancement (NNE) has been proposed to exploit image attributes such as background, background color and foreground in a way that can increase the quality of a visual scene. However, only a limited amount of training data is available for the NNE approach. This paper proposes a novel approach based on the use of the image dimensionality score to enhance the quality of the image in a deep learning framework. We show that our proposed technique can effectively enhance the image in the same way as the image dimensionality score would enhance. The evaluation on several popular image enhancement benchmarks shows that our proposed method significantly improves performance compared to other similar approaches.
Distributed Learning of Discrete Point Processes
Axiomatic Properties of Two-Stream Convolutional Neural Networks
Reconstructing the Human Mind
A Computational Study of Learning Functions in Statistical Language Models
Learning from Negative News by Substituting Negative Images with Word2vecA new technique called negative image enhancement (NNE) has been proposed to exploit image attributes such as background, background color and foreground in a way that can increase the quality of a visual scene. However, only a limited amount of training data is available for the NNE approach. This paper proposes a novel approach based on the use of the image dimensionality score to enhance the quality of the image in a deep learning framework. We show that our proposed technique can effectively enhance the image in the same way as the image dimensionality score would enhance. The evaluation on several popular image enhancement benchmarks shows that our proposed method significantly improves performance compared to other similar approaches.