803 results about "Semi-supervised learning" patented technology

A process and device for detecting colon cancer by classifying and annotating clinical features in video data containing colonoscopic features by applying a probabilistic analysis to intra-frame and inter-frame relationships between colonoscopic features in spatially and temporally neighboring portions of video frames, and classifying and annotating as clinical features any of the colonoscopic features that satisfy the probabilistic analysis as clinical features. Preferably the probabilistic analysis is Hidden Markove Model analysis, and the process is carried out by a computer trained using semi supervised learning from labeled and unlabeled examples of clinical features in video containing colonoscopic features.

Framework may be implemented for transferring knowledge from an external agent to a robotic controller. In an obstacle avoidance / target approach application, the controller may be configured to determine a teaching signal based on a sensory input, the teaching signal conveying information associated with target action consistent with the sensory input, the sensory input being indicative of the target / obstacle. The controller may be configured to determine a control signal based on the sensory input, the control signal conveying information associated with target approach / avoidance action. The controller may determine a predicted control signal based on the sensory input and the teaching signal, the predicted control conveying information associated with the target action. The control signal may be combined with the predicted control in order to cause the robotic apparatus to execute the target action.

The invention relates to the technical field of image information processing, in particular to a multiclass image classification method based on active learning and semi-supervised learning. The method comprises five steps: initial sample selection and classifier model training, BvSB active learning sample selection, CST semi-supervised learning, training sample set and classifier model updating and assorting process iteration. Through the operations of BvSB active learning sample selection, CST semi-supervised learning and SVM classification, the invention has efficient image classification effect under the condition of less manual tagging, does not increase overmuch computation burden, can quickly provide classification effects and also can take consideration of the demand of a classification system on the computation complexity.

A computerized system and method for large scale semi-supervised learning is provided. The training set comprises a mix of labeled and unlabeled examples. Linear classifiers based on support vector machine principles are built using these examples. One embodiment uses a fast design of a linear transductive support vector machine using multiple switching. In another embodiment, mean field annealing is used to form a very effective semi-supervised support vector machine. For both these embodiments, the finite Newton method is used as the base method for achieving fast training

The invention discloses a semi-supervised image classification method based on a generative adversarial network, which mainly solves the problems that the existing unsupervised learning classificationprecision is low and semi-supervised learning needs a large number of accurate labels, and comprises the following implementation steps of: 1) selecting and downloading a standard image training sample and a test sample; 2) setting relevant parameters of network supervised learning, and establishing a generative adversarial network consisting of a generator network, a discriminator network and anauxiliary classifier in parallel; 3) training the generative adversarial network by using a random gradient descent method; and 4) inputting the test sample to be classified into the trained generative adversarial network model, and outputting the category of the image to be detected. The method improves the image classification precision of unsupervised learning, can obtain a very good image classification effect on a sample set only containing a small amount of accurate annotation samples, and can be used for target classification in an actual scene.

The invention provides a semi-supervised X-ray automatic labeling method based on a generative adversarial network. A traditional training method is improved on the basis of an existing generative adversarial network method, and a semi-supervised training method combining supervised loss and unsupervised loss is used for carrying out image classification recognition based on a small number of labeled samples. The problem of data scarcity annotation of the X-ray image is studied. The method comprises: firstly, on the basis of a traditional unsupervised generative adversarial network, using a softmax for replacing a final output layer; expanding the X-ray image into a semi-supervised generative adversarial network, defining additional category label guide training for the generated sample, optimizing network parameters by adopting the semi-supervised training, and finally, automatically labeling the X-ray image by adopting a trained discriminant network. Compared with traditional supervised learning and other semi-supervised learning algorithms, the method has the advantage that in the aspect of medical X-ray image automatic labeling, the performance is improved.

A local-neighborhood Laplacian Eigenmap (LNLE) algorithm is provided for methods and systems for semi-supervised learning on manifolds of data points in a high-dimensional space. In one embodiment, an LNLE based method includes building an adjacency graph over a dataset of labelled and unlabelled points. The adjacency graph is then used for finding a set of local neighbors with respect to an unlabelled data point to be classified. An eigen decomposition of the local subgraph provides a smooth function over the subgraph. The smooth function can be evaluated and based on the function evaluation the unclassified data point can be labelled. In one embodiment, a transductive inference (TI) algorithmic approach is provided. In another embodiment, a semi-supervised inductive inference (SSII) algorithmic approach is provided for classification of subsequent data points. A confidence determination can be provided based on a number of labeled data points within the local neighborhood. Experimental results comparing LNLE and simple LE approaches are presented.

The invention discloses a semi-supervised classification method of unbalance data, which is mainly used for solving the problem of low classification precision of a minority of data which have fewer marked samples and high degree of unbalance in the prior art. The method is implemented by the following steps: (1) initializing a marked sample set and an unmarked sample set; (2) initializing a cluster center; (3) implementing fuzzy clustering; (4) updating the marked sample set and unmarked sample set according to the result of the clustering; (5) performing the self-training based on a support vector machine (SVM) classifier; (6) updating the marked sample set and unmarked sample set according to the result of the self-training; (7) performing the classification of support vector machines Biased-SVM based on penalty parameters; and (8) estimating a classification result and outputting the result. For unbalance data which have fewer marked samples, the method improves the classification precision of a minority of data. And the method can be used for classifying and identifying unbalance data having few training samples.

The invention relates to a graph-based semi-supervised high-spectral remote sensing image classification method. The method comprises the following steps: extracting the features of an input image; randomly sampling M points from an unlabeled sample, constructing a set S with L marked points, constructing a set R with the rest of the points; calculating K adjacent points of the points in the sets S and R in the set S by use of a class probability distance; constructing two sparse matrixes WSS and WSR by a linear representation method; using label propagation to obtain a label function F<*><S>, and calculating the label prediction function F<*><R> of the sample points in the set R to determine the labels of all the pixel points of the input image. According to the method, the adjacent points of the sample points can be calculated by use of the class probability distance, and the accurate classification of high-spectral images can be achieved by utilizing semi-supervised conduction, thus the calculation complexity is greatly reduced; in addition, the problem that the graph-based semi-supervised learning algorithm can not be used for large-scale data processing is solved, and the calculation efficiency can be improved by at least 20-50 times within the per unit time when the method provided by the invention is used, and the visual effects of the classified result graphs are good.

The invention discloses an image classification method and device based on semi-supervised deep learning and a storage medium. The method includes: acquiring label training image samples and non-labeltraining image samples, and obtaining a label training set; combining deep learning and semi-supervised learning to carry out training of a convolutional neural network (CNN) on the label training set, and establishing a unified model of semi-supervised deep learning and unlabeled-sample class estimation; and carrying out image recognition / classification on the basis of the model of semi-supervised deep learning and unlabeled sample class estimation. According to the method, distinguishing information hidden in non-label training data can be utilized, high separability of current deep features can also be utilized at the same time, the unlabeled samples can be more efficiently and accurately utilized, and thus better image recognition performance can be obtained.

A method for classification of image regions by probabilistic merging of a class probability map and a cluster probability map includes the steps of a) extracting one or more features from an input image composed of image pixels; b) performing unsupervised learning based on the extracted features to obtain a cluster probability map of the image pixels; c) performing supervised learning based on the extracted features to obtain a class probability map of the image pixels; and d) combining the cluster probability map from unsupervised learning and the class probability map from supervised learning to generate a modified class probability map to determine the semantic class of the image regions. In one embodiment the extracted features include color and textual features.

A system and method are disclosed for providing semi-supervised learning for a spoken language understanding module using semantic role labeling. The method embodiment relates to a method of generating a spoken language understanding module. Steps in the method comprise selecting at least one predicate / argument pair as an intent from a set of the most frequent predicate / argument pairs for a domain, labeling training data using mapping rules associated with the selected at least one predicate / argument pair, training a call-type classification model using the labeled training data, re-labeling the training data using the call-type classification model and iteratively several of the above steps until training set labels converge.

The invention discloses an image classification method based on a confrontation network generated through feature recalibration. The image classification method based on the confrontation network generated through feature recalibration is suitable for the field of machine learning and comprises the steps that to-be-classified image data are input into a confrontation network model for network training; a generator and a discriminator which are constituted by a convolutional network are constructed; random noise is initialized and input into the generator; the random noise is subjected to multilevel deconvolution operation in the generator through the convolutional network, and finally, generated samples are obtained; the generated samples and authentic samples are input into the discriminator; and the input samples are subjected to convolution and pooling operation in the discriminator through the convolutional network, thus a feature graph is obtained, a compressed and activated SENetmodule is imported into an intermediate layer of the convolutional network to calibrate the feature graph, thus the calibrated feature graph is obtained, global average pooling is used, and finally,image data classification is output. The SENet module is imported into the intermediate layer of the discriminator, the importance degree of each feature channel is automatically learned, useful features relevant to a task are extracted, features irrelevant to the task are restrained, and thus semi-supervised learning performance is improved.

The invention belongs to the technical field of computers, and discloses a machine translation method and system based on a generative adversarial neural network. The method comprises the following steps that: on the basis of an original machine translation generation network, a discrimination network which generates network countermeasure with the original machine translation generation network is imported; a translation used for judging a target language is from a training parallel corpus and is a network machine translation result of the original machine translation generation network; and the discrimination network adopts a multi-layer sensor feedforward neural network model to realize binary classification. The system comprises the discrimination network, a generation network, a mono-lingual corpus and a parallel corpus. While manually annotated bilingual parallel corpus resources are fully utilized, and mono-lingual corpus resources also can be fully utilized to carry out semi-supervised learning; and the mono-lingual corpus resources are very rich and can be easily obtained, and the problem that required training corpora required by the neural network machine translation model are not sufficient is solved.

The present teaching relates to method system, and medium for generating knowledge for a chat bot. Training data are used to learn and generating knowledge and are received with at least some labeled training seeds and unlabeled conversation data. The training data are parsed and various linguistic elements are extracted therefrom. Such linguistic elements are then used to perform automated learning in accordance with at least one label used in labeling the training seeds. Based on the automated learning, at least one model associated with the at least one label is generated from the training data.

The invention especially discloses a training method of an SVM (Support Vector Machine) classifier based on semi-supervised learning. The training method comprises the following steps of: step 1, training an initial SVM classifier through an initial labelled sample set; step 2, looking for samples with high classifying confidence degrees from an unlabelled sample set U to constitute a sample set S with high confidence degree; step 3, judging an amount of information of each sample in the sample set S with high confidence degrees according to a method described in the graph 3, removing the samples from the sample set S with high confidence degrees if the amount of information is large , and placing the samples back into the unlabelled sample set U; step 4, adding the samples with high confidence degrees and large amount of information after the samples are automatically labeled by a machine in the sample set S into a labeled sample set L of the SVM classifier; step 5, using the renewed labeled sample set L to retrain the SVM classifier; and step 6, judging whether the SVM classifier either exists a loop or continuously iterates according to a stopping criterion.

The invention discloses an automatic image annotation method based on semi-supervised learning. The method comprises the steps that a data set is divided into a training data set, an unlabeled data set and a test set; the SIFT feature and the HOG feature of a training sample are extracted to train an LDA_SVM classifier; color and texture features are extracted to train a neural network; unlabeleddata are used to enable two classifiers to label and predict the same unlabeled sample simultaneously; according to the contribution of the classifiers to the unlabeled sample classification accuracy,the classification results of two classifiers are weighted and fused by an adaptive weighted fusion policy, so as to acquire the final prediction label probability vector of the sample; and finally two classifiers are updated by the sample with high confidence and the predictive label thereof until the preset maximum number of iterations is reached. According to the invention, the method can makefull use of the unlabeled sample to excavate the inherent law of the image feature; the number of annotation samples required for the classifier training is effectively reduced; the annotation effectis great.

The invention relates to a multi-feature fusion phishing webpage detection method, which comprises two parts such as a training process and a detection process. The multi-feature fusion phishing webpage detection method integrates three views of phishing webpage characteristics by combining a semi-supervised learning tri-training method, and mainly solves a problem that the existing phishing webpage detection methods mostly need to perform classification model training by using supervised learning through a large amount of annotation data. The method provided by the invention mainly combines a coordinated training algorithm, starts from webpage URL characteristics, webpage information characteristics and webpage search information characteristics, applies the idea of multiple views and multiple classifiers to phishing webpage detection, and achieves the purposes of reducing the total numbers of manual annotation training samples and timely recognizing a phishing webpage through coordinated training and learning of different classifiers.

The invention provides an image object detection method. The image object detection method is capable of achieving good detection performance in a large image data set. The method includes the steps that multiple sample images are marked according to the priorities of information amounts, so that corresponding marked images are obtained; regions containing objects or regions highest in probability of object existence are extracted from the marked images, and candidate windows are generated; feature expressions of the candidate windows are extracted from a convolution neural network and form a candidate set, the candidate set is fitted through semi-supervised learning, and therefore a target function of an image detection model is obtained; the region containing a target object or the region highest in probability of target object existence is extracted from an image to be detected, a window to be detected is generated, the feature expression of the window to be detected is extracted and detected, and the candidate window highest in the probability of target object existence is obtained. The method can rapidly and accurately detect the target object in the large data set.

A computer implemented method detects intrusions using a computer by analysing network traffic. The method includes a semi-supervised learning module connected to a network node. The learning module uses labeled and unlabeled data to train a semi-supervised machine learning sensor. The method records events that include a feature set made up of unauthorized intrusions and benign computer requests. The method identifies at least some of the benign computer requests that occur during the recording of the events while treating the remainder of the data as unlabeled. The method trains the semi-supervised learning module at the network node in-situ, such that the semi-supervised learning modules may identify malicious traffic without relying on specific rules, signatures, or anomaly detection.

The invention relates to a large-length voice full-automatic segmentation method which is a zero-labeling sentence automatic segmentation algorithm having higher accuracy. The algorithm enables a Force-alignment non-supervision algorithm and a semi-supervised learning method based on an HMM to be blended, automatic expansion is carried out on a few precise labeling sets provided for the zero-labeling sentence segmentation algorithm by a semi-supervised learning minimization labeling sentence segmentation algorithm through establishment of an iteration mechanism based on a timer shaft, the purpose of the maximization of the precise labeling sets is realized, and then according to obtained correct periods, voice of an original length is cut into smaller paragraphs or sets of sentences. According to the method, a Force-aligned method under the HMM and a Co_training method in semi-supervised learning are blended together, so the facts that in a large-length voice sentence segmentation process, manual intervention is not needed, and segmentation accuracy is high are guaranteed. The large-length voice full-automatic segmentation method can be applied to rapid and automatic construction of a voice corpus.

The invention discloses a multi-class image semi-supervised classifying method and system. The method comprises the steps that firstly, similarity learning is conducted on image samples with tags and image samples without tags in a training set, and similar neighbor images and normalized weights are constructed and used for representing sample similarities; secondly, a class tag matrix is initialized, L2,1-norm regularization is introduced to effectively reduce the influence of mixed signals in prediction tags F of flexible class tags on results, constrains which are not negative and are one in column sum are applied to F at the same time, and thus it is ensured that estimated flexible tags meet the probability definition and non-negativity; finally, parameters are used for balancing the influences of similarity measurement, initial class tags and L2,1-norm regularization on classification, semi-supervised learning modeling is completed, the maximum value of similarity probabilities is taken to be used for image class identification, and classification results are obtained. Due to the fact that the L2,1-norm regularization is introduced, the influence of the mixed signals on the classification is reduced, and thus the classification accuracy is improved. In addition, data outside the training set can be effectively classified, and the expansibility is good.

The invention discloses an enterprise industry classification method. According to the method, main business keywords of enterprises are effectively extracted by utilizing semi-supervised learning-based image split clustering algorithm, the extracted keywords are used as features on the basis of a gradient enhancement decision-making tree, and a training cascade classifier is used for classifyingthe enterprises according to industries, so that the problem that artificial classification is tedious is solved. The method specifically comprises the following steps of: 1) extracting main businesskeywords of enterprises by utilizing a word vector and a semi-supervised image split clustering algorithm, getting rid of junk words and constructing a keyword library; and 2) inputting the extractedkeywords which are taken as features into a training cascade classifier, the enterprises are classified by each level of classifier, and the unclassified enterprises are classified according to the next level of classifier. According to the method, keywords can be automatically constructed, updated and classified, the problem of classifying millions and millions of enterprise industries is solved,and the problem of artificial labelling is effectively solved.

The invention belongs to the technical field of image processing, discloses a method for identifying and positioning power transmission line insulators in unmanned aerial vehicle aerial images, and solves the problems in the prior art that the detection precision of an identification algorithm of the insulators is not high, the robustness is low, and the identification algorithm is easy to be affected by sample number. A group of Gabor wavelet basis with different sizes and different directions and training sample images are taken as convolutions so as to form a group of characteristic vectors which accurately describe sample image texture characteristics. A random forest machine learning algorithm with a semi-supervised learning mode is used to train sample data sets of the known category and the unknown category so as to obtain an insulator identification model. Through the mode from left to right and from top to bottom, a detection window with the same size as the training sample traverses the input images with different sizes. The detection window combining the identification model detects and positions the positions of the insulators in the input images with different sizes. And finally the accurate positions of the insulators in the input image with the original size are determined by using a non-maximum inhibition method.

The invention discloses an image target detection method based on weak supervised learning, and belongs to the technical field of machine vision. The method comprises the following steps: firstly, collecting an image data set, and training a constructed deep convolutional neural network model based on a multi-scale feature map by adopting a multi-example learning method; inputting an actual image,and extracting a category thermodynamic diagram of the actual image through the deep convolutional neural network model; and finally, outputting a bounding box of a target in the category thermodynamic diagram by adopting a binarization image connected region analysis method to obtain a target detection result. According to the method, an image target detection task is realized based on a weak supervised learning method. The target detection task can be completed only by using the image-level classification annotation information in annotation in convolutional neural network model training, which is different from the target bounding box annotation information required in the prior art, so that the work of manually annotating the target in the image is greatly reduced, and the completionof the image target detection task has more economic benefits.

The invention discloses a semi-supervised learning facial expression recognition method based on fuzzy training samples. First, data in a face database is preprocessed; then, facial expressions are recognized using an improved SVM algorithm; and finally, unknown expression images are recognized. Under the condition that a same number of labeled samples are used, the expression recognition rate is improved by 3-7% by adding a large number of unlabeled samples. Under the condition that a few labeled samples are used, the recognition rate is improved using an STSVM algorithm to a level equivalent to the recognition rate of an SVM classifier obtained by using a large number of labeled samples.

The invention provides a hypergraph convolutional network model and a semi-supervised classification method thereof. The method comprises the following steps: 1, carrying out sparse coding on sample data features of a non-Euclidean structure to form a sample representation coefficient matrix; 2, constructing a hyperedge according to the similarity of the samples, calculating a hyperedge weight, and constructing a hyper-graph model; 3, by means of a hypergraph theory, defining convolution operation on a hypergraph, and constructing a hypergraph convolution network model; 4, defining a semi-supervised learning method on the hypergraph convolutional network, designing a loss function, and predicting category labels of all samples by using category information of a small number of calibrationsamples; 5, respectively making a semi-given label matrix for training, verifying and testing, setting network hyper-parameters, training a network model, and learning a convolution kernel and a regularity factor parameter of the network according to a random gradient descent algorithm; and 6, for given data, predicting an unknown sample category by using the trained model to realize semi-supervised classification.

A target tracking method based on semi-supervised learning and a random fern classifier relates to a target tracking method and solves the different problems that an existing target tracking method is large in calculated amount and high in complexity, cannot meet real time processing requirements, is poor in effects on large angle rotation and hyperplane rotation and the like. The target tracking method can solve the difficult problems target scale change, rotation, hyperplane rotation, noise, shading, bonding, camera vibration, dim and the like in scene to form a stable target track and a full-view online model of the target. The tracking method comprises the steps of initializing the online model to generate and standardize positive examples; initializing a detector; training a detection; tracking a short-term tracker; tracking validity evolution; detecting the detector; combining detection and track; and learning and upgrading training sets. The target tracking method is a complete target tracking solution and is widely applied to fields of actual video monitoring, behavior analysis, intelligent transportation, electronic police, precision guidance and the like.

The invention relates to a semi-supervised learning-based multi-gesture facial expression recognition algorithm which comprises the steps of acquiring n front expression images and n side expression images of n persons to form a training set X and a testing set S, segmenting face regions of the front expression images and the side expression images, and carrying out illumination compensation on the face regions by using a histogram equalization method; then extracting expression characteristics of the images by adopting a linear discriminant analysis method, carrying out expression recognition on samples in the testing set S; marking each unmarked sample in the training set X by using marked samples in the training set X by adopting an Euclidean distance nearest neighbour method; re-sampling the training set X by adopting a round-robin mode to obtain a new training set Xr; scheduling a basic classifying device to calculate a mark ht of each sample in the training set X at the tth circle by using the new training set Xr, and calculating a mark ft of each sample in the testing set S at the tth circle by using the new training set Xr; and finally, calculating a classifying error rate epsilon t of the basic classifying device to side samples in the training set, and updating weights of all training samples in the training set X until reaching the circle ending condition.