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.
Explosive naval mines pose a threat to ocean and sea faring vessels, both military and civilian. This work applies deep neural network (DNN) methods to the problem of detecting minelike objects (MLO) on the seafloor in side-scan sonar imagery. We explored how the DNN depth, memory requirements, calculation requirements, and training data distribution affect detection efficacy. A visualization technique...
Recently, deep learning has enjoyed a great deal of success for computer vision problems due to its capability to model highly complex tasks, such as image classification, object detection, face recognition, among many others. Although these neural networks are nowadays very powerful, there is a huge amount of parameters (i.e. the model) that need to be learned and require considerable storage space...
Collaborative filtering is widely used in recommender systems. When training data are extremely sparse, neighbor selection methods work ineffectively. To address this issue, this paper proposes a distributed representation model that represents users as low-dimensional vectors for neighbor selection by considering the chronological order of users' ratings. Experiments show that the proposed method...
We consider the problem of anomaly localization in a sensor network for multivariate time-series data by computing anomaly scores for each variable separately. To estimate the sparse Gaussian graphical models (GGMs) learned from different sliding windows of the dataset, we propose a new model wherein we constrain sparsity directly through L0 constraint and apply an additional L2 regularization in...
Virtual Reality (VR) has as goal the creation of digital three dimensional environments to run in real time interactive and realistic experiences. The experiences can be augmented by the use of haptic systems, able to provide sense of touch in virtual objects. The anesthesia procedure is present in all surgeries to keep stable the patient physiology. The use of VR based simulators for anesthesia training...
Thanks to recent advances in the field of genomics, it is now possible to create a comprehensive atlas of the basic units of life—cells. In this paper, we present a frame work for single cell genomics research which employs several new machine learning models such as convolutional neural networks, deep auto-encoder, recurrent neural networks etc. With these effective learning models on multi-source...
Gene fusions are widely observed in the RNA-seq data, many of which are formed by cancer susceptibility genes. The fusion gene is formed by chromosomal mutations and is an important factor in causing cancer. Studies have shown that only a small number of identified fusion genes play a role in the carcinogenesis process. Identifying those genes is important for the study and treatment of cancer. There...
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the emergent (as opposed to agent) behavior is easier from a demonstration perspective. Without the involvement of manual behavior specification via code or reliance on...
Given an undirected network where some of the nodes are labeled, how can we classify the unlabeled nodes with high accuracy? Loopy Belief Propagation (LBP) is an inference algorithm widely used for this purpose with various applications including fraud detection, malware detection, web classification, and recommendation. However, previous methods based on LBP have problems in modeling complex structures...
Given a collection of basic customer demographics (e.g., age and gender) andtheir behavioral data (e.g., item purchase histories), how can we predictsensitive demographics (e.g., income and occupation) that not every customermakes available?This demographics prediction problem is modeled as a classification task inwhich a customer's sensitive demographic y is predicted from his featurevector x. So...
In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks...
Modern drug discovery organizations generate large volumes of SAR data. A promising methodology that can be used to mine this chemical data to identify novel structure-activity relationships is the matched molecular pair (MMP) methodology. However, before the full potential of the MMP methodology can be utilized, a MMP identification method that is capable of identifying all MMPs in large chemical...
Currently, literature points out the lack of studies about collaborative virtual environments with intelligent tools capable of providing automatic evaluation feedback of different collaborative procedures (e.g., surgical, military training). In addition, there is a lack of classifications and methodologies for the implementation of CVEs with simultaneous evaluation of multiple users, making it difficult...
Extending from limited domain to a new domain is crucial for Natural Language Generation in Dialogue, especially when there are sufficient annotated data in the source domain, but there is little labeled data in the target domain. This paper studies the performance and domain adaptation of two different Neural Network Language Generators in Spoken Dialogue Systems: a gating-based Recurrent Neural...
The hashtag recommendation problem addresses recommending (suggesting) one or more hashtags to explicitly tag a post made on a given social network platform, based upon the content and context of the post. In this work, we propose a novel methodology for hashtag recommendation for microblog posts, specifically Twitter. The methodology, EmTaggeR, is built upon a training-testing framework that builds...
We propose a novel personalized recommendation model for social network users based on location computing. The novelty of our model is that we deal with the location based recommendation by combing logistic regression with collaborative filtering method. The logistic regression is used to train the weights of items' features, i.e., the recommendation sort list. On the other hand, the collaborative...
Convolutional neural network (CNN) extracts features from big data by using the multilayer network structure. Due to the high effectiveness, CNN has achieved great successes in many fields such as computer vision and speech analysis. However, CNN training is quite challenging because computing the gradients through multiple layers is time consuming. In this paper, we propose to accelerate the computation...
Joint sparse representation (JSR) models have been widely applied into the field of hyperspectral image (HSI) classification. However, most of JSR-based models adopt the Frobenius norm to measure the reconstruction error, which ignores the structural information of the small patch. In this paper, we propose a nuclear-norm joint sparse representation (NuJSR) model for hyperspectral image classification...
A new methodology for image synthesis based on two cooperative training ConvNets is proposed. Two generative ConvNets and unsupervised joint learning are designed to effectively reflect the characteristics of real scenery and image pattern. Every ConvNet is directly derived from the discriminate ConvNet and has the potential to learn from big unlabeled data, either by contrastive divergence. One ConvNet...
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively...
Podaj zakres dat dla filtrowania wyświetlonych wyników. Możesz podać datę początkową, końcową lub obie daty. Daty możesz wpisać ręcznie lub wybrać za pomocą kalendarza.