Use Of Training Examples Research Articles

A Deep Neural Network-Based Yoruba Intelligent Chatbot System

Two Artificial Intelligence software systems, Bot and Chatbot have recently debuted on the internet. This initiate a communication between the user and a virtual agent. The modeling and performance in deep learning (DL) computation for an Assistant Conversational Agent are presented in this research (Chatbot). The deep neural network (DNN) technique is used to respond to a large number of tokens in an input sentence with more appropriate dialogue. The model was created to do Yoruba-to-Yoruba translations. The major goal of this project is to improve the model's perplexity and learning rate, as well as to find a blue score for translation in the same language. Kares is used to run the experiments, which is written in Python. The data was trained using a deep learning-based algorithm. With the use of training examples, a collection of Yoruba phrases with various intentions was produced. The results demonstrate that the system can communicate in basic Yoruba terms and that it would be able to learn simple Yoruba words. The study result when evaluated showed that the system had 80% accuracy rate. Keywords: Chatbot, Natural Language Processing, Deep Learning, Artificial Neural Network, Yoruba Language

Whole-body uptake classification and prostate cancer staging in 68Ga-PSMA-11 PET/CT using dual-tracer learning

PurposeIn PSMA-ligand PET/CT imaging, standardized evaluation frameworks and image-derived parameters are increasingly used to support prostate cancer staging. Clinical applicability remains challenging wherever manual measurements of numerous suspected lesions are required. Deep learning methods are promising for automated image analysis, typically requiring extensive expert-annotated image datasets to reach sufficient accuracy. We developed a deep learning method to support image-based staging, investigating the use of training information from two radiotracers.MethodsIn 173 subjects imaged with 68Ga-PSMA-11 PET/CT, divided into development (121) and test (52) sets, we trained and evaluated a convolutional neural network to both classify sites of elevated tracer uptake as nonsuspicious or suspicious for cancer and assign them an anatomical location. We evaluated training strategies to leverage information from a larger dataset of 18F-FDG PET/CT images and expert annotations, including transfer learning and combined training encoding the tracer type as input to the network. We assessed the agreement between the N and M stage assigned based on the network annotations and expert annotations, according to the PROMISE miTNM framework.ResultsIn the development set, including 18F-FDG training data improved classification performance in four-fold cross validation. In the test set, compared to expert assessment, training with 18F-FDG data and the development set yielded 80.4% average precision [confidence interval (CI): 71.1–87.8] for identification of suspicious uptake sites, 77% (CI: 70.0–83.4) accuracy for anatomical location classification of suspicious findings, 81% agreement for identification of regional lymph node involvement, and 77% agreement for identification of metastatic stage.ConclusionThe evaluated algorithm showed good agreement with expert assessment for identification and anatomical location classification of suspicious uptake sites in whole-body 68Ga-PSMA-11 PET/CT. With restricted PSMA-ligand data available, the use of training examples from a different radiotracer improved performance. The investigated methods are promising for enabling efficient assessment of cancer stage and tumor burden.

Selective Weakly Supervised Human Detection under Arbitrary Poses

In this paper we study the problem of weakly supervised human detection under arbitrary poses within the framework of multi-instance learning (MIL). Our contributions are threefold: (1) we first show that in the context of weakly supervised learning, some commonly used bagging tools in MIL such as the Noisy-OR model or the ISR model tend to suffer from the problem of gradient magnitude reduction when the initial instance-level detector is weak and/or when there exist large number of negative proposals, resulting in extremely inefficient use of training examples. We hence advocate the use of more robust and simple max-pooling rule or average rule under such circumstances; (2) we propose a new Selective Weakly Supervised Detection (SWSD) algorithm, which is shown to outperform several previous state-of-the-art weakly supervised methods; (3) finally, we identify several crucial factors that may significantly influence the performance, such as the usefulness of a small amount of supervision information, the need of relatively higher RoP (Ratio of Positive Instances), and so on – these factors are shown to benefit the MIL-based weakly supervised detector but are less studied in the previous literature. We also annotate a new large-scale data set called LSP/MPII-MPHB (Multiple Poses Human Body), in which and another popular benchmark dataset we demonstrate the superiority of the proposed method compared to several previous state-of-the-art methods.

Converting Taxonomic Descriptions to New Digital Formats

Abstract.--The majority of taxonomic descriptions is currently in print format. The majority of digital descriptions are in formats such as DOC, HTML, or PDF and for human readers. These formats do not convey rich semantics in taxonomic descriptions for computer-aided process. Newer digital formats such as XML and RDF accommodate semantic annotations that allow computers to process the rich semantics on human's behalf, thus open up opportunities for a wide range of innovative usages of taxonomic descriptions, such as searching in more precise and flexible ways, integrating with gnomic and geographic information, generating taxonomic keys automatically, and text data mining and information visualization etc. This paper discusses the challenges in automated conversion of multiple collections of descriptions to XML format and reports an automated system, MARTT. MARTT is a machine-learning system that makes use of training examples to tag new descriptions into XML format. A number of utilities are implemented as solutions to the challenges. The utilities are used to reduce the effort for training example preparation, to facilitate the creation of a comprehensive schema, and to predict system performance on a new collection of descriptions. The system has been tested with several plant and alga taxonomic publications including Flora of China and Flora of North America.

Bayesian detection of periodic mRNA time profiles without use of training examples

BackgroundDetection of periodically expressed genes from microarray data without use of known periodic and non-periodic training examples is an important problem, e.g. for identifying genes regulated by the cell-cycle in poorly characterised organisms. Commonly the investigator is only interested in genes expressed at a particular frequency that characterizes the process under study but this frequency is seldom exactly known. Previously proposed detector designs require access to labelled training examples and do not allow systematic incorporation of diffuse prior knowledge available about the period time.ResultsA learning-free Bayesian detector that does not rely on labelled training examples and allows incorporation of prior knowledge about the period time is introduced. It is shown to outperform two recently proposed alternative learning-free detectors on simulated data generated with models that are different from the one used for detector design. Results from applying the detector to mRNA expression time profiles from S. cerevisiae showsthat the genes detected as periodically expressed only contain a small fraction of the cell-cycle genes inferred from mutant phenotype. For example, when the probability of false alarm was equal to 7%, only 12% of the cell-cycle genes were detected. The genes detected as periodically expressed were found to have a statistically significant overrepresentation of known cell-cycle regulated sequence motifs. One known sequence motif and 18 putative motifs, previously not associated with periodic expression, were also over represented.ConclusionIn comparison with recently proposed alternative learning-free detectors for periodic gene expression, Bayesian inference allows systematic incorporation of diffuse a priori knowledge about, e.g. the period time. This results in relative performance improvements due to increased robustness against errors in the underlying assumptions. Results from applying the detector to mRNA expression time profiles from S. cerevisiae include several new findings that deserve further experimental studies.

Maximizing Theory Accuracy Through Selective Reinterpretation

Existing methods for exploiting flawed domain theories depend on the use of a sufficiently large set of training examples for diagnosing and repairing flaws in the theory. In this paper, we offer a method of theory reinterpretation that makes only marginal use of training examples. The idea is as follows: Often a small number of flaws in a theory can completely destroy the theory's classification accuracy. Yet it is clear that valuable information is available even from such flawed theories. For example, an instance with severalindependent proofs in a slightly flawed theory is certainly more likely to be correctly classified as positive than an instance with only a single proof. This idea can be generalized to a numerical notion of “degree of provedness” which measures the robustness of proofs or refutations for a given instance. This “degree of provedness” can be easily computed using a “soft” interpretation of the theory. Given a ranking of instances based on the values so obtained, all that is required to classify instances is to determine some cutoff threshold above which instances are classified as positive. Such a threshold can be determined on the basis of a small set of training examples. For theories with a few localized flaws, we improve the method by “rehardening”: interpreting only parts of the theory softly, while interpreting the rest of the theory in the usual manner. Isolating those parts of the theory that should be interpreted softly can be done on the basis of a small number of training examples. Softening, with or without rehardening, can be used by itself as a quick way of handling theories with suspected flaws where few training examples are available. Additionally softening and rehardening can be used in conjunction with other methods as a meta-algorithm for determining which theory revision methods are appropriate for a given theory.