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.
We present a novel technique to detect objects from panoramic images using existing object detectors trained from perspective images. By leveraging existing object detectors, we save the cost of training a new detector which requires tedious and time consuming training data collection and labeling. The core of our technique is learning a feature transform which is represented by Gaussian Process Regression...
The goal of this research is to enable mobile robots to navigate through crowded environments such as indoor shopping malls, airports, or downtown side walks. The key research question addressed in this paper is how to learn planners that generate human-like motion behavior. Our approach uses inverse reinforcement learning (IRL) to learn human-like navigation behavior based on example paths. Since...
A hierarchical reinforcement learning method based on heuristic reward function is proposed to solve the problem of “curse of dimensionality”, that is the states space will grow exponentially in the number of features, and low convergence speed. The method can reduce state spaces greatly and can enhance the speed of the study. Choose actions with favorable purpose and efficiency so as to optimize...
A major problem with previous object tracking approaches is adapting object representations depending on scene context to account for changes in illumination, viewpoint changes, etc. To adapt our previous approach to deal with background changes, here we first derive some clusters from a training sequence and the corresponding object representations for those clusters. Next, for each frame of a separate...
This paper presents a new methodology of feature extraction of sleep and wake stages of a freely behaving rat based on Continuous Wavelet Transform (CWT). The automatic separation of those stages is very useful for experiments related to learning and memory consolidation since recent scientific evidence indicates that sleep is strongly involved with offline reprocessing of acquired information during...
Due to the magnitude and complexity of design and manufacturing processes, it is unrealistic to expect that models and simulations can predict all aspects of silicon behavior accurately. When unexpected behavior is observed in the post-silicon stage, one desires to identify the causes and consequently identify the fixes. This paper studies one formulation of the design-silicon mismatch problem. To...
In spite of all the progress known frequently by the computer vision field, the user intervention stays always necessary. In all images processing tasks, it is to the user to adjust the parameters of the vision operators in order to reach the desired result. The manually adjustment of these parameters isn't an easy work, it becomes more tedious with complicated vision applications such as texture...
Aiming at the problem of the "semantic gap" and the "dimensionality curse", this paper discussed the model of cross-media retrieval. The methods of feature extraction and fusion of multimedia were given for processing high-dimensional data, and a nonlinear hybrid classifier based on support vector hidden Markov models was design for implementation semantic mapping and learning...
In this paper, we present an active boosting algorithm to learn the object detector. This algorithm is to find good features from a confidential map instead of brute-force searching the predefined feature set. The confidential map is computed from the importance re-sampled data. A new feature is created by the linear combination of blocks that are selected from different segmented regions. In addition,...
Feature selection is an important challenge in machine learning. Unfortunately, most methods for automating feature selection are designed for supervised learning tasks and are thus either inapplicable or impractical for reinforcement learning. This paper presents a new approach to feature selection specifically designed for the challenges of reinforcement learning. In our method, the agent learns...
In this paper, we propose an example-based facial sketch hallucination approach. Given a face image, its sketch image will be automatically hallucinated by learning from a training set, which includes a lot of face images and their corresponding sketch images. Our algorithm involves three stages. In the first stage which is called ??feature extracting??, we create the feature pyramid for each face...
In this paper, we present a novel face detection architecture based on the boosted cascade algorithm. A reduced two-field feature extraction scheme for integral image calculation is proposed. Based on this scheme, the required memory for storing integral images is reduced from 400 Kbits to 2.016 Kbits for a 160??120 gray scale image. The range of the feature size and location is also reduced so the...
Most of the previous works in the field of extraction pattern are based on the usage of syntactic analyzer and semantic tagger to create a pattern that could extract relevant information from free text documents or more structured documents like Web pages. In this paper, we propose an approach to create a set of extraction pattern by combining a particular part of speech (POS) tagger and grammatical...
Learning and relearning ability is important to partner robots. From this point of view, here we propose an intelligent learning system with voice instruction recognition and action learning function. Transient-SOM (T-SOM), an advanced self-organizing map proposed by our previous work for hand gesture recognition and memorization is adopted and improved to be Parameter-Less T-SOM (PL-T-SOM) with an...
The influence of the feature vector (FV) content on the CBIR (content-based image retrieval) system efficiency was considered. By using two different FVs and applying three different learning methods, it was shown that the efficiency of retrieving depends on both the FV content and the learning method, independently.
Since humanoid robots have similar body structures to humans, a humanoid robot is expected to perform various dynamic tasks including object manipulation. This research focuses on issues related to learning and performing object manipulation. Basic motion primitives for tasks are learned from observation of human's behaviors. An object manipulation task is divided into two types of motion primitives,...
This paper addresses the question of how to extract the relevance among the learning concepts in an intelligent tutoring system using the mathematical modeling of the search engines. To test the proposed approach, two learning domains have been selected from mathematics. For each domain, five distinct chapters have been quoted from the books written by various authors. After extracting candidate concepts,...
The talk presents theoretical foundations and practical applications of intelligent information processing systems inspired by information principles in Nature. That includes neuronal-, genetic-, and quantum information principles. First, the paper reviews the main principles of information processing at neuronal-, genetic-, and quantum information levels. Each of these levels has already inspired...
In this paper, authors propose a new learning based method for medical image retrieval which is based on fusing different features by linearly combining different similarities. Considering the abundant classes of medical images, this paper avoid to train a classifier for each class by using large amount training data. Instead, by using optimization method to combine different features' similarity,...
Bayesian network is a powerful tool of feature subset selection. Feature subset selection based on Bayesian network is to build the Markov blanket of class variable. In this paper, feature subset selection is done based on local dependency analysis method. First, basic dependency relationships between variables, basic structures between nodes, dependency separation criterion and the Markov blanket...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.