A team of researchers at Google's DeepMind Technologies has been working on a means to increase the capabilities of computers by combining aspects of data processing and artificial intelligence and have come up with what they are calling a differentiable neural computer (DNC.) In their paper published in the journal Nature, they describe the work they are doing and where they believe it is headed. To make the work more accessible to the public team members, Alexander Graves and Greg Wayne have posted an explanatory page on the DeepMind website. [13]

Convolutional Neural Network를 이용한 한국어 영화평 감성 분석

The eyes are very important senses in human life. If the eyes experience interference, it will be fatal to human life. Although each type of eye disease has its own specific characteristics and symptoms, early detection with a deeper recognition of eye disease symptoms should be done. Knowledge-based information systems are systems that attempt to convert human knowledge into computers so that computers can solve problems as is usually done by experts. produce conclusions or goals. The aim of this study is to design applications for early detection of fourteen types of eye diseases. This detection uses a knowledge-based system that uses the Forward Chaining method. This study produced an output in the form of the possibility of the disease the user suffered based on fifty-three selected symptoms. This system indicates how much confidence the user has in the symptoms of possible eye diseases.

Knowledge based information system for detecting early eye diseases

Open-source OSs like Linux provide us means to remove certain features from the guest OS in order to increase its performance manifold, which leads to our own fine-tuned version of guest OS. This paper is aimed at studying the parameters affecting performance of guest OS and editing those features to produce its efficient version.

Performance Evaluation of Guest Operating System Following Obliteration of Pre-installed Features

With the ever growing size of image databases today and the increasing demand for search and recommendations from within those databases, it is becoming more and more critical to find efficient image search techniques. This paper proposes a fast approach for extracting the most similar image to a given query image from a database such that the extracted images are most similar semantically. This involves reducing the dimensions of the images by encoding them uniquely to lower dimensional vector using CNN and then applying locality sensitive hashing along with euclidean distance similarity to find the most similar images.

Large Scale Image Retrieval with Locality Sensitive Hashing

A deep learning approach has been proposed for the classification of cluster instances as being intrusive or not intrusive. Mini-batch Adam optimizer was used due to a large number of hidden layers in the model. Massive amounts of data accumulated for training prevented the model from overfitting. After extensive testing of data with various algorithms, it was found that deep learning model with Adam optimizer outperformed others.

Prateek Singh

Papers

Performance Evaluation of Guest Operating System Following Obliteration of Pre-installed Features

Large Scale Image Retrieval with Locality Sensitive Hashing

Deep Network for Network Intrusion with Concept Drift