Set Of Negative Examples Research Articles

Generalized Planning with Positive and Negative Examples

Generalized planning aims at computing an algorithm-like structure (generalized plan) that solves a set of multiple planning instances. In this paper we define negative examples for generalized planning as planning instances that must not be solved by a generalized plan. With this regard the paper extends the notion of validation of a generalized plan as the problem of verifying that a given generalized plan solves the set of input positives instances while it fails to solve a given input set of negative examples. This notion of plan validation allows us to define quantitative metrics to asses the generalization capacity of generalized plans. The paper also shows how to incorporate this new notion of plan validation into a compilation for plan synthesis that takes both positive and negative instances as input. Experiments show that incorporating negative examples can accelerate plan synthesis in several domains and leverage quantitative metrics to evaluate the generalization capacity of the synthesized plans.

An evolutionary‐based approach for dealing with numerical and categorical attributes in ILP

AbstractInductive logic programming (ILP) induces concepts from a set of positive examples, a set of negative examples, and background knowledge. ILP has been applied on tasks such as natural language processing, finite element mesh design, network mining, robotics, and drug discovery. These data sets usually contain numerical and multivalued categorical attributes; however, only a few relational learning systems are capable of handling them in an efficient way. In this paper, we present an evolutionary approach, called Grouping and Discretization for Enriching the Background Knowledge (GDEBaK), to deal with numerical and multivalued categorical attributes in ILP. This method uses evolutionary operators to create and test numerical splits and subsets of categorical values in accordance with a fitness function. The best subintervals and subsets are added to the background knowledge before constructing candidate hypotheses. We implemented GDEBaK embedded in Aleph and compared it to lazy discretization in Aleph and discretization in Top‐down Induction of Logical Decision Trees (TILDE) systems. The results obtained showed that our method improves accuracy and reduces the number of rules in most cases. Finally, we discuss these results and possible lines for future work.

Genome-wide pre-miRNA discovery from few labeled examples.

Although many machine learning techniques have been proposed for distinguishing miRNA hairpins from other stem-loop sequences, most of the current methods use supervised learning, which requires a very good set of positive and negative examples. Those methods have important practical limitations when they have to be applied to a real prediction task. First, there is the challenge of dealing with a scarce number of positive (well-known) pre-miRNA examples. Secondly, it is very difficult to build a good set of negative examples for representing the full spectrum of non-miRNA sequences. Thirdly, in any genome, there is a huge class imbalance (1: 10 000) that is well-known for particularly affecting supervised classifiers. To enable efficient and speedy genome-wide predictions of novel miRNAs, we present miRNAss, which is a novel method based on semi-supervised learning. It takes advantage of the information provided by the unlabeled stem-loops, thereby improving the prediction rates, even when the number of labeled examples is low and not representative of the classes. An automatic method for searching negative examples to initialize the algorithm is also proposed so as to spare the user this difficult task. MiRNAss obtained better prediction rates and shorter execution times than state-of-the-art supervised methods. It was validated with genome-wide data from three model species, with more than one million of hairpin sequences each, thereby demonstrating its applicability to a real prediction task. An R package can be downloaded from https://cran.r-project.org/package=miRNAss. In addition, a web-demo for testing the algorithm is available at http://fich.unl.edu.ar/sinc/web-demo/mirnass. All the datasets that were used in this study and the sets of predicted pre-miRNA are available on http://sourceforge.net/projects/sourcesinc/files/mirnass. cyones@sinc.unl.edu.ar. Supplementary data are available at Bioinformatics online.

NegGOA: negative GO annotations selection using ontology structure.

Predicting the biological functions of proteins is one of the key challenges in the post-genomic era. Computational models have demonstrated the utility of applying machine learning methods to predict protein function. Most prediction methods explicitly require a set of negative examples-proteins that are known not carrying out a particular function. However, Gene Ontology (GO) almost always only provides the knowledge that proteins carry out a particular function, and functional annotations of proteins are incomplete. GO structurally organizes more than tens of thousands GO terms and a protein is annotated with several (or dozens) of these terms. For these reasons, the negative examples of a protein can greatly help distinguishing true positive examples of the protein from such a large candidate GO space. In this paper, we present a novel approach (called NegGOA) to select negative examples. Specifically, NegGOA takes advantage of the ontology structure, available annotations and potentiality of additional annotations of a protein to choose negative examples of the protein. We compare NegGOA with other negative examples selection algorithms and find that NegGOA produces much fewer false negatives than them. We incorporate the selected negative examples into an efficient function prediction model to predict the functions of proteins in Yeast, Human, Mouse and Fly. NegGOA also demonstrates improved accuracy than these comparing algorithms across various evaluation metrics. In addition, NegGOA is less suffered from incomplete annotations of proteins than these comparing methods. The Matlab and R codes are available at https://sites.google.com/site/guoxian85/neggoa gxyu@swu.edu.cn Supplementary data are available at Bioinformatics online.

High Class-Imbalance in pre-miRNA Prediction: A Novel Approach Based on deepSOM

The computational prediction of novel microRNA within a full genome involves identifying sequences having the highest chance of being a miRNA precursor (pre-miRNA). These sequences are usually named candidates to miRNA. The well-known pre-miRNAs are usually only a few in comparison to the hundreds of thousands of potential candidates to miRNA that have to be analyzed, which makes this task a high class-imbalance classification problem. The classical way of approaching it has been training a binary classifier in a supervised manner, using well-known pre-miRNAs as positive class and artificially defining the negative class. However, although the selection of positive labeled examples is straightforward, it is very difficult to build a set of negative examples in order to obtain a good set of training samples for a supervised method. In this work, we propose a novel and effective way of approaching this problem using machine learning, without the definition of negative examples. The proposal is based on clustering unlabeled sequences of a genome together with well-known miRNA precursors for the organism under study, which allows for the quick identification of the best candidates to miRNA as those sequences clustered with known precursors. Furthermore, we propose a deep model to overcome the problem of having very few positive class labels. They are always maintained in the deep levels as positive class while less likely pre-miRNA sequences are filtered level after level. Our approach has been compared with other methods for pre-miRNAs prediction in several species, showing effective predictivity of novel miRNAs. Additionally, we will show that our approach has a lower training time and allows for a better graphical navegability and interpretation of the results. A web-demo interface to try deepSOM is available at http://fich.unl.edu.ar/sinc/web-demo/deepsom/.

Approximation-oriented Fuzzy Rough Set Approaches

In this paper we focus on generalizations of the classical ro ugh set approach to fuzzy environments. There are two aspects of rough set approaches: classification and approximation. In the classification aspect, by rough set approaches we can cla ssify objects into positive and negative examples of a class. On the other hand, in the approximation aspect, by rough set approaches we obtain the lower and upper approximations of a class. The former model works better in the attribute reduction while the latter model works better in the rule induction. In the setting of the classical rough set approach, the lower approximation is nothing but the set of positive examples and the upper approximation is the complementary set of negative examples. However, these equalities do not always hold in the generalized settings. Most of fuzzy rough set models proposed earlier are defined in the classification aspect. The approaches based on those models do not always work well in approximating fuzzy subsets. In this paper we define t he fuzzy rough set models in the approximation aspect. We investigate their fundamental properties and demonstrate the advantages of fuzzy set approximation. Finally we consider attribute r eduction based on the proposed fuzzy rough set models.

High-Dimensional Image Data Sets Retrieval: Improving Accuracy Using a Weighted Relevance Feedback

The user's interaction with the retrieval engines, while seeking a particular image (or set of images) in large-scale databases, defines better his request. This interaction is essentially provided by a relevance feedback step. In fact, the semantic gap is increasing in a remarkable way due to the application of approximate nearest neighbor (ANN) algorithms aiming at resolving the curse of dimensionality. Therefore, an additional step of relevance feedback is necessary in order to get closer to the user's expectations in the next few retrieval iterations. In this context, this paper details a classification of the different relevance feedback techniques related to region-based image retrieval applications. Moreover, a technique of relevance feedback based on re-weighting regions of the query-image by selecting a set of negative examples is elaborated. Furthermore, the general context to carry out this technique which is the large-scale heterogeneous image collections indexing and retrieval is presented. In fact, the main contribution of the proposed work is affording efficient results with the minimum number of relevance feedback iterations for high dimensional image databases. Experiments and assessments are carried out within an RBIR system for "Wang" data set in order to prove the effectiveness of the proposed approaches.

Learn with SAT to Minimize Büchi Automata

We describe a minimization procedure for nondeterministic B\"uchi automata (NBA). For an automaton A another automaton A_min with the minimal number of states is learned with the help of a SAT-solver. This is done by successively computing automata A' that approximate A in the sense that they accept a given finite set of positive examples and reject a given finite set of negative examples. In the course of the procedure these example sets are successively increased. Thus, our method can be seen as an instance of a generic learning algorithm based on a "minimally adequate teacher" in the sense of Angluin. We use a SAT solver to find an NBA for given sets of positive and negative examples. We use complementation via construction of deterministic parity automata to check candidates computed in this manner for equivalence with A. Failure of equivalence yields new positive or negative examples. Our method proved successful on complete samplings of small automata and of quite some examples of bigger automata. We successfully ran the minimization on over ten thousand automata with mostly up to ten states, including the complements of all possible automata with two states and alphabet size three and discuss results and runtimes; single examples had over 100 states.

A partially supervised classification approach to dominant and recessive human disease gene prediction

The discovery of the genes involved in genetic diseases is a very important step towards the understanding of the nature of these diseases. In-lab identification is a difficult, time-consuming task, where computational methods can be very useful. In silico identification algorithms can be used as a guide in future studies. Previous works in this topic have not taken into account that no reliable sets of negative examples are available, as it is not possible to ensure that a given gene is not related to any genetic disease. In this paper, this feature of the nature of the problem is considered, and identification is approached as a partially supervised classification problem. In addition, we have performed a more specific method to identify disease genes by classifying, for the first time, genes causing dominant and recessive diseases independently. We base this separation on previous results that show that these two types of genes present differences in their sequence properties. In this paper, we have applied a new model averaging algorithm to the identification of human genes associated with both dominant and recessive Mendelian diseases.

DATA FLOW COHERENCE CONSTRAINTS FOR PRUNING THE SEARCH SPACE IN ILP TOOLS

In this paper we present a new method that uses data-flow coherence constraints in definite logic program generation. We outline three main advantages of these constraints supported by our results: i) drastically pruning the search space (around 90%), ii) reducing the set of positive examples and reducing or even removing the need for the set of negative examples, and iii) allowing the induction of predicates that are difficult or even impossible to generate by other methods. Besides these constraints, the approach takes into consideration the program termination condition for recursive predicates. The paper outlines some theoretical issues and implementation aspects of our system for automatic logic program induction.

Logical analysis of data with decomposable structures

In such areas as knowledge discovery, data mining and logical analysis of data, methodologies to find relations among attributes are considered important. In this paper, given a data set (T,F) where T⊆{0,1} n denotes a set of positive examples and F⊆{0,1} n denotes a set of negative examples, we propose a method to identify decomposable structures among the attributes of the data. We first study computational complexity of the problem of finding decomposable Boolean extensions. Since the problem turns out to be intractable (i.e., NP-complete), we propose a heuristic algorithm in the second half of the paper. Our method searches a decomposable partition of the set of all attributes by using the error sizes of almost-fit decomposable extensions as a guiding measure, and then finds structural relations among the attributes in the obtained partition. Some results of numerical experiment on randomly generated data sets are also reported.

Learning of Short Boolean Conjunctions from Negative Examples

Learning from examples in the presence of overwhelmingly many irrelevant variables has been studied in the field of machine learning theory, where the learner is required to derive as succinct hypotheses as possible. In this paper, we consider the following computational learning problem: Given a set of negative examples in n Boolean variables, the learner is required to find O(log n) relevant variables whose conjunction gives a consistent hypothesis. This problem belongs to a complexity class called β2. We prove that this problem is equivalent, by probabilistic log-space Turing reduction, to the problem of finding satisfiable assignments for polynomial-size -circuits with O(log2 n) inputs. As a consequence, we can show that learning of O(log n)-length Boolean conjunctions from negative examples is neither β2-hard unless P ⊆ POLYLOG-SPACE, nor polynomial-time computable unless NP ⊆ DTIME(2O(√n)). In this paper, we also discuss the polynomial-time learnability of an O(log n)-length monotone Boolean conjunction from negative examples, when the examples are drawn from the uniform distribution. © 2001 Scripta Technica, Syst Comp Jpn, 33(1): 1–7, 2002

Generalization with Precision: The Role of Negative Teaching Examples in the Instruction of Generalized Grocery Item Selection

For generalization to be functional, it must occur with a precision that results in acquired responses occurring under appropriate, nontrained conditions, and acquired responses not occurring under inappropriate, nontrained conditions. This study examines the effect of differing types of negative teaching examples on the precision with which generalized grocery item selection is learned. Within a split-multiple baseline design, six young adults identified as mildly, moderately, or severely mentally retarded were trained to select or to reject grocery items using picture cards as cues. The dependent variables were correct selection of 10 trained “positive” grocery items and the correct rejection of 20 nontrained “negative” grocery items in a nontrained grocery store. Participants were trained in a grocery store to select 10 positive grocery examples matching their picture cards and to reject either (a) a set of negative examples that were maximally different from the positive examples, or (b) a set of negative examples that were minimally different from the positive examples. Both training sets resulted in participants correctly selecting the 10 positive items in a nontrained store. Training with the “minimally different” negative examples was functionally related to improved rejection of nontrained negative items in the nontrained store. The implications of teaching with minimally different, negative examples are discussed.