Adversarial attack has cast a shadow on the massive success of deep neural networks. Despite being almost visually identical to the clean data, the adversarial images can fool deep neural networks into wrong predictions with very high confidence. In this paper, however, we show that we can build a simple binary classifier separating the adversarial apart from the clean data with accuracy over 9...

The idea of using artificial neural network has proved useful for hyperspectral image classification. However, the high dimensionality of hyperspectral images usually leads to the failure of constructing an effective neural network classifier. To improve the performance of neural network classifier, wavelet-based feature extraction algorithms are applied to extract useful features for hyperspec...

The aim of this paper is to develop the design of classifier using Artificial Neural Network for patients survival analysis based on echocardiography dataset. Survival analysis can be considered a classification problem in which the application of machine learning methods is appropriate. Survival analysis plays an important role not only for health care policy markers, but also for the clinicia...

Artificial Intelligence (AI) methods are used to build classifiers that give different levels of accuracy and solution explication. The intent of this paper is to provide a way of building a hierarchical classifier composed of several artificial neural networks (ANN’s) organised in a tree-like fashion. Such method of construction allows for partition of the original problem into several sub-pro...

In this paper the problem of complex event detection in the continuous domain (i.e. events with unknown starting and ending locations) is addressed. Existing event detection methods are limited to features that are extracted from the local spatial or spatio-temporal patches from the videos. However, this makes the model vulnerable to the events with similar concepts e.g. “Open drawer” and “Open...

We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifiers by determining how sensitive each parameter in the model is to noise. The true error rate of the stochastic classifier found with the sensitivity analysis can then be tightly bounded using a PAC-Bayes bound. In this ...

Between the various biometric methods, Face Recognition has become one of the most burning topic tasks in the pattern recognition field during the past decades. In This Work a Face Recognition System has been developed By applying different multiple classifier selection schemes on the output of three different classification methods namely Artificial Neural Network, Genetic Algorithm And Euclid...

The Intelligent Model for Stock Investment with Buffett Strategy, Classifier System, Neural Network and Linear Programming” was studied for developing an intelligent model which can learn more knowledge regarding to stock investment with artificial intelligence technology. Classifier system, neural network, fundamental financial investment factors and linear programming are the fundamental comp...

Previous results have shown disappointing performance when porting a parser trained on one domain to another domain where only a small amount of data is available. We propose the use of data-defined kernels as a way to exploit statistics from a source domain while still specializing a parser to a target domain. A probabilistic model trained on the source domain (and possibly also the target dom...