Heart Disease is one of the leading diseases that causes enormous loss of lives all over the world. There are happened many works to diagnosis heart disease. In this paper, we are considered some unusual approaches to...
详细信息
Emotion recognition is one of the key steps towards emotional intelligence in advanced human-machine interaction. Recently, emotion recognition using physiological signals has been performed by various machine learnin...
详细信息
Using large training datasets enhances the generalization capabilities of neural networks. Semi-supervised learning (SSL) is useful when there are few labeled data and a lot of unlabeled data. SSL methods that use dat...
详细信息
作者：
Neri, FilippoDIETI
University of Naples via Claudio 21 Naples80100 Italy
The paper describes a novel methodology to compare learning algorithms by exploiting their performance maps. A performance map enhances the comparison of a learner across learning contexts and it also provides insight...
详细信息
In this paper, we describe proximal gradient temporal difference learning, which provides a principled way for designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how grad...
详细信息
In this paper, we describe proximal gradient temporal difference learning, which provides a principled way for designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD) reinforcement learning methods can be formally derived, not with respect to their original objective functions as previously attempted, but rather with respect to primal-dual saddle-point objective functions. We also conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Previous analyses of this class of algorithms use stochastic approximation techniques to prove asymptotic convergence, and no finite-sample analysis had been attempted. An accelerated algorithm is also proposed, namely GTD2-MP, which use proximal "mirror maps" to yield acceleration. The results of our theoretical analysis imply that the GTD family of algorithms are comparable and may indeed be preferred over existing least squares TD methods for off-policy learning, due to their linear complexity. We provide experimental results showing the improved performance of our accelerated gradient TD methods.
learning during backtrack search is a space-intensive process that records information (such as additional constraints) in order to avoid redundant work. In this paper, we analyze the effects of polynomial-space-bound...
详细信息
learning during backtrack search is a space-intensive process that records information (such as additional constraints) in order to avoid redundant work. In this paper, we analyze the effects of polynomial-space-bounded learning on runtime complexity of backtrack search. One space-bounded learning scheme records only those constraints with limited size, and another records arbitrarily large constraints but deletes those that become irrelevant to the portion of the search space being explored. We find that relevance-bounded learning allows better runtime bounds than size-bounded learning on structurally restricted constraint satisfaction problems. Even when restricted to linear space, our relevance-bounded learning algorithm has runtime complexity near that of unrestricted (exponential space-consuming) learning schemes.
The financial forecasting of different firms in the area of financial status aims to determine whether the company will go bankrupt in the near future or not. This is a critical problem for these companies. Several co...
详细信息
The traditional solutions of weight training were various derivation method in Chaotic Diagonal Recurrent Neural Networks model and its momentum gradient learning algorithm. But its deduced the precise of all the weig...
详细信息
In this paper we present a new terminology extraction system based on supervised statistical learning algorithms, which are characterized by having a training phase with a controlled exposure to both positive and nega...
详细信息
ISBN:
(纸本)9788469543337
In this paper we present a new terminology extraction system based on supervised statistical learning algorithms, which are characterized by having a training phase with a controlled exposure to both positive and negative examples prior to the actual categorization. Contrary to the vast majority of the term extractors reported in the literature, our proposal is based on implicit knowledge rather than handcrafted explicit rules. Given a list of terms from some domain and language plus a general language reference corpus, we developed a methodology for terminology extraction and implemented it as a web application that is already available online. This tool is flexible enough to operate in different languages and domains and, as a sort of lifelong learning algorithm, it turns terminology extraction into a collaborative effort, where all users benefit from the training conducted by each individual.
Breast cancer (BC) is a pervasive issue that leads to countless fatalities among women worldwide, and metastatic breast cancer is responsible for most of these deaths. Early detection of metastatic BC is essential for...
详细信息
暂无评论