Serwis Infona wykorzystuje pliki cookies (ciasteczka). Są to wartości tekstowe, zapamiętywane przez przeglądarkę na urządzeniu użytkownika. Nasz serwis ma dostęp do tych wartości oraz wykorzystuje je do zapamiętania danych dotyczących użytkownika, takich jak np. ustawienia (typu widok ekranu, wybór języka interfejsu), zapamiętanie zalogowania. Korzystanie z serwisu Infona oznacza zgodę na zapis informacji i ich wykorzystanie dla celów korzytania z serwisu. Więcej informacji można znaleźć w Polityce prywatności oraz Regulaminie serwisu. Zamknięcie tego okienka potwierdza zapoznanie się z informacją o plikach cookies, akceptację polityki prywatności i regulaminu oraz sposobu wykorzystywania plików cookies w serwisie. Możesz zmienić ustawienia obsługi cookies w swojej przeglądarce.
Most of the prior works summarize videos by either exploring different heuristically designed criteria in an unsupervised way or developing fully supervised algorithms by leveraging human-crafted training data in form of video-summary pairs or importance annotations. However, unsupervised methods are blind to the video category and often fail to produce semantically meaningful video summaries. On...
The enhancement of speech degraded with the non-stationary noise types that typify real-world conditions has remained a challenging problem for several decades. However, recent use of data driven methods for this task has brought great performance improvements. In this paper, we develop a speech enhancement framework based on the extreme learning machine. Experimental results show that the proposed...
A convolution neural network (CNN) based classification method for broadband DOA estimation is proposed, where the phase component of the short-time Fourier transform coefficients of the received microphone signals are directly fed into the CNN and the features required for DOA estimation are learned during training. Since only the phase component of the input is used, the CNN can be trained with...
Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to collect for certain applications (consider, for example, satellite stereo imaging). The main contribution of our work is a new weakly supervised method for learning...
Artificial intelligence (AI) agent created with Deep Q-Networks (DQN) can defeat human agents in video games. Despite its high performance, DQN often exhibits odd behaviors, which could be immersion-breaking against the purpose of creating game AI. Moreover, DQN is capable of reacting to the game environment much faster than humans, making itself invincible (thus not fun to play with) in certain types...
This paper aims to compare classification methods in order to learn the strengths of each method. We will introduce the fusion of classifiers technique by using the theory of belief functions, particularly the transferable belief model. We will propose different ways of fusion in medical diagnosis of diabetes analysis problem as an application of this work.
An infrastructure-less indoor localization system is proposed based on fingerprints of light signals acquired at high frequencies. In contrast to other systems that modulate lights, the proposed system distinguishes lights by learning from training samples. Due to slight differences in the electronic components used in the construction of compact fluorescent light (CFL) and light emitting diode (LED)...
This paper addresses a problem in which we learn a regression model from sets of training data. Each of the sets has an only single label, and only one of the training data in the set reflects the label. This is particularly the case when the label is attached to a group of data, such as time-series data. The label is not attached to the point of the sequence but rather attached to particular time...
AdaBoost is an iterative algorithm to construct classifier ensembles. It quickly achieves high accuracy by focusing on objects that are difficult to classify. Because of this, AdaBoost tends to overfit when subjected to noisy datasets. We observe that this can be partially prevented with the use of validation sets, taken from the same noisy training set. But using less than the full dataset for training...
In this paper, a Sequential Fuzzy Indexing Tables classifier is proposed for problems that require fast online operation. Its base idea comes from fuzzy hypermatrices (which are specialized versions of fuzzy look-up tables) that realize nearest-neighbor classification in order to recognize patterns similar to known ones. It is done by mapping the problem space into the memory in form of multidimensional...
A new method for separating the feature automatically with supervised nonnegative matrix factorization (NMF) is proposed for fault diagnosis. Because of the shortage of lacking prior knowledge in existed NMF, a supervised NMF combined statistical model for fault diagnosis is proposed. The basis matrix achieved in training stage is treated as the sources' features. Besides, Gaussian Mixture Model is...
Document Categorization is an area of important research over the last couple of decades. The basic task in document categorization is classifying a given document in some predefined classes. Bengali is among the top ten most spoken languages in the world and is spoken by more than 200 million people, but the candid truth is, it still lacks significant research efforts in the area of Bengali Document...
The localness inference problem is to identify whether a person is a local resident in a city or not and the likelihood of a venue to attract local people. This information is critical for many applications such as targeted ads of local business, urban planning, localized news and travel recommendations. While there are prior work on geo-locating people in a city using supervised learning approaches,...
The recognition and extraction of biomedical names is an essential task for the biomedical information extraction. However, the preparation of large annotated corpora hinders the training of the Named Entity Recognition (NER) systems. Active learning is reducing the needed manual annotation work in supervised learning task. In this work, we propose a novel clustering based active learning method for...
It is well known that feed-forward neural networks can be learnt from symbolic data although the learnt networks usually have poor performance. This paper explores the ability of a recently popular feed-forward neural network, i.e., Extreme Learning Machine (ELM) for modeling symbolic data. An experimental study is conducted to compare C4.5 (a very popular algorithm of learning from symbolic data)...
Big data processing is the new challenge for analytical, machine learning techniques. Many efforts are needed to scale both classic, advanced methods to the the mass of the provided data. Evolutionary learning algorithms (EAL) are robust, effective methods in solving a wide variety of complex learning problems. This paper discusses how to tune the active sampling techniques for EAL to deal with very...
Semi-supervised learning is a topic of practical importance because of the difficulty of obtaining numerous labeled data. In this paper, we apply an extension of adversarial autoencoder to semi-supervised learning tasks. In attempt to separate style and content, we divide the latent representation of the autoencoder into two parts. We regularize the autoencoder by imposing a prior distribution on...
Support Vector Machines (SVM's) are supervised learning algorithms which can be used for analyzing patterns and classifying data. This supervised algorithm is applicable for binary class as well as multiclass classification. The core idea is to build a hyperplane which can easily separate the training examples. For binary class, SVM constructs a hyper-plane which can easily separate d-dimensional...
Recent years have witnessed the significant success of representation learning and deep learning in various prediction and recognition applications. Most of these previous studies adopt the two-phase procedures, namely the first step of representation learning and then the second step of supervised learning. In this process, to fit the training data the initial model weights, which inherits the good...
In this paper we advocate that market mechanisms inspired by economics in conjunction with intelligent data selection is the key to fulfilling learning tasks in the presence of big data subject to privacy concerns of users. We design a market of private data that are gathered towards building a classifier. Each data owner has a private cost that quantifies his discomfort for providing data to the...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.