Medical datasets often have a skewed class distribution and a lack of high-quality annotated images. However, deep learning methods require a large amount of labeled data for classification. In this study, we present ...
详细信息
A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifer network. The results of a series of benchmarking studies based upon artif...
详细信息
A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifer network. The results of a series of benchmarking studies based upon artificial statistical pattern recognition tasks indicate that the proposed architecture performs significantly better than conventional feedforward classifer networks when the decision regions are disjoint. This is attributed to the fact that the self-organization process allows internal units in the succeeding classifer network to be sensitive to a specific set of features in the input space at the outset of training.
Reinforcement learning is the problem of generating optimal behavior in a sequential decision-making environment given the opportunity of interacting with it. Many algorithms for solving reinforcement-learning problem...
详细信息
Reinforcement learning is the problem of generating optimal behavior in a sequential decision-making environment given the opportunity of interacting with it. Many algorithms for solving reinforcement-learning problems work by computing improved estimates of the optimal value function. We extend prior analyses of reinfarcement-learning algorithms and present a powerful new theorem that can provide a unified analysis of such value-function-based reinforcement-learning algorithms. The usefulness of the theorem lies in how it allows the convergence of a complex asynchronous reinforcement-learning algorithm to be proved by verifying that a simpler synchronous algorithm converges. We illustrate the application of the theorem by analyzing the convergence of Q-learning, model-based reinforcement learning, Q-learning with multistate updates, Q-learning for Markov games, and risk-sensitive reinforcement learning.
The focus of this paper is to compare several common machine learning classification algorithms for Optical Character Recognition of CAPTCHA codes. The main part of a research focuses on the comparative study of Neura...
详细信息
Plants are thought of to be crucial just like the stock of vitality offer to people. Plant sicknesses will affect the leaf whenever among planting and suspect that winds up in tremendous misfortune on the get together...
详细信息
In today's date data analysis is need for every data analytics to examine the sets of data to extract the useful information from it and to draw conclusion according to the information. Data analytics techniques a...
详细信息
In this paper two agglomerative learning algorithms based on new similarity measures defined for hyperbox fuzzy sets are proposed. They are presented in a context of clustering and classification problems tackled usin...
详细信息
In this paper two agglomerative learning algorithms based on new similarity measures defined for hyperbox fuzzy sets are proposed. They are presented in a context of clustering and classification problems tackled using a general fuzzy min-max (GFMM) neural network. The proposed agglomerative schemes have shown robust behaviour in presence of noise and outliers and insensitivity to the order of training patterns presentation. The emphasis is also put on the complimentary features to the previously presented incremental learning scheme more suitable for on-line adaptation and dealing with large training data sets. The performance and other properties of the agglomerative schemes are illustrated using a number of artificial and real-world data sets.
Traditional motor function assessment for stroke patients involves subjective scoring by rehabilitation physicians, a process that is time-consuming, expensive, and subject to variability. By utilizing sensors (marker...
详细信息
Understanding large data sets is one of the most important and challenging problems in the modern days. Exploration of genetic data sets composed of high dimensional feature vectors can be treated as a leading example...
详细信息
Understanding large data sets is one of the most important and challenging problems in the modern days. Exploration of genetic data sets composed of high dimensional feature vectors can be treated as a leading example in this context. A better understanding of large, multivariate data sets can be achieved through exploration and extraction of their structure. Collinear patterns can be an important part of a given data set structure. Collinear (flat) pattern exists in a given set of feature vectors when many of these vectors are located on (or near) some plane in the feature space. Discovered flat patterns can reflect various types of interaction in an explored data set. The presented paper compares basis exchange algorithms with learning algorithms in the task of flat patterns extraction.
Mobile-waste is a growing problem in India. One of the factors that mobile has shorter life is rapidly changing technology. Most of the people throw their unwanted mobiles into scrap. Such scraped mobiles are hazardou...
详细信息
暂无评论