scholarly journals Certifying the True Error: Machine Learning in Coq with Verified Generalization Guarantees

2019 ◽  
Vol 33 ◽  
pp. 2662-2669 ◽  
Author(s):  
Alexander Bagnall ◽  
Gordon Stewart
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Open Source ◽  
Theorem Prover ◽  
True Error ◽  
Data Set ◽  
Test Error ◽  
Generalization Bounds ◽  
Executable Code ◽  
Proof Checker

We present MLCERT, a novel system for doing practical mechanized proof of the generalization of learning procedures, bounding expected error in terms of training or test error. MLCERT is mechanized in that we prove generalization bounds inside the theorem prover Coq; thus the bounds are machine checked by Coq’s proof checker. MLCERT is practical in that we extract learning procedures defined in Coq to executable code; thus procedures with proved generalization bounds can be trained and deployed in real systems. MLCERT is well documented and open source; thus we expect it to be usable even by those without Coq expertise. To validate MLCERT, which is compatible with external tools such as TensorFlow, we use it to prove generalization bounds on neural networks trained using TensorFlow on the extended MNIST data set.

scholarly journals Generation of geometric interpolations of building types with deep variational autoencoders

2020 ◽  
Vol 6 ◽  
Author(s):  
Jaime de Miguel Rodríguez ◽  
Maria Eugenia Villafañe ◽  
Luka Piškorec ◽  
Fernando Sancho Caparrini
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Large Data ◽  
Learning Model ◽  
Large Data Sets ◽  
Data Sets ◽  
Connectivity Map ◽  
Data Set ◽  
3D Objects ◽  
Machine Learning Model

Abstract This work presents a methodology for the generation of novel 3D objects resembling wireframes of building types. These result from the reconstruction of interpolated locations within the learnt distribution of variational autoencoders (VAEs), a deep generative machine learning model based on neural networks. The data set used features a scheme for geometry representation based on a ‘connectivity map’ that is especially suited to express the wireframe objects that compose it. Additionally, the input samples are generated through ‘parametric augmentation’, a strategy proposed in this study that creates coherent variations among data by enabling a set of parameters to alter representative features on a given building type. In the experiments that are described in this paper, more than 150 k input samples belonging to two building types have been processed during the training of a VAE model. The main contribution of this paper has been to explore parametric augmentation for the generation of large data sets of 3D geometries, showcasing its problems and limitations in the context of neural networks and VAEs. Results show that the generation of interpolated hybrid geometries is a challenging task. Despite the difficulty of the endeavour, promising advances are presented.

scholarly journals Determination of Body Parts in Holstein Friesian Cows Comparing Neural Networks and k Nearest Neighbour Classification

Animals ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 50
Author(s):  
Jennifer Salau ◽  
Jan Henning Haas ◽  
Wolfgang Junge ◽  
Georg Thaller
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Body Parts ◽  
Nearest Neighbour ◽  
Data Set ◽  
3D Data ◽  
Holstein Friesian ◽  
Knn Classification ◽  
Friesian Cows

Machine learning methods have become increasingly important in animal science, and the success of an automated application using machine learning often depends on the right choice of method for the respective problem and data set. The recognition of objects in 3D data is still a widely studied topic and especially challenging when it comes to the partition of objects into predefined segments. In this study, two machine learning approaches were utilized for the recognition of body parts of dairy cows from 3D point clouds, i.e., sets of data points in space. The low cost off-the-shelf depth sensor Microsoft Kinect V1 has been used in various studies related to dairy cows. The 3D data were gathered from a multi-Kinect recording unit which was designed to record Holstein Friesian cows from both sides in free walking from three different camera positions. For the determination of the body parts head, rump, back, legs and udder, five properties of the pixels in the depth maps (row index, column index, depth value, variance, mean curvature) were used as features in the training data set. For each camera positions, a k nearest neighbour classifier and a neural network were trained and compared afterwards. Both methods showed small Hamming losses (between 0.007 and 0.027 for k nearest neighbour (kNN) classification and between 0.045 and 0.079 for neural networks) and could be considered successful regarding the classification of pixel to body parts. However, the kNN classifier was superior, reaching overall accuracies 0.888 to 0.976 varying with the camera position. Precision and recall values associated with individual body parts ranged from 0.84 to 1 and from 0.83 to 1, respectively. Once trained, kNN classification is at runtime prone to higher costs in terms of computational time and memory compared to the neural networks. The cost vs. accuracy ratio for each methodology needs to be taken into account in the decision of which method should be implemented in the application.

scholarly journals Exploiting node metadata to predict interactions in large networks using graph embedding and neural networks

2021 ◽  
Author(s):  
Rogini Runghen ◽  
Daniel B Stouffer ◽  
Giulio Valentino Dalla Riva
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Link Prediction ◽  
Graph Embedding ◽  
Feature Space ◽  
Machine Learning Techniques ◽  
Large Networks ◽  
Data Set ◽  
Learning Techniques ◽  
Low Dimensional

Collecting network interaction data is difficult. Non-exhaustive sampling and complex hidden processes often result in an incomplete data set. Thus, identifying potentially present but unobserved interactions is crucial both in understanding the structure of large scale data, and in predicting how previously unseen elements will interact. Recent studies in network analysis have shown that accounting for metadata (such as node attributes) can improve both our understanding of how nodes interact with one another, and the accuracy of link prediction. However, the dimension of the object we need to learn to predict interactions in a network grows quickly with the number of nodes. Therefore, it becomes computationally and conceptually challenging for large networks. Here, we present a new predictive procedure combining a graph embedding method with machine learning techniques to predict interactions on the base of nodes' metadata. Graph embedding methods project the nodes of a network onto a---low dimensional---latent feature space. The position of the nodes in the latent feature space can then be used to predict interactions between nodes. Learning a mapping of the nodes' metadata to their position in a latent feature space corresponds to a classic---and low dimensional---machine learning problem. In our current study we used the Random Dot Product Graph model to estimate the embedding of an observed network, and we tested different neural networks architectures to predict the position of nodes in the latent feature space. Flexible machine learning techniques to map the nodes onto their latent positions allow to account for multivariate and possibly complex nodes' metadata. To illustrate the utility of the proposed procedure, we apply it to a large dataset of tourist visits to destinations across New Zealand. We found that our procedure accurately predicts interactions for both existing nodes and nodes newly added to the network, while being computationally feasible even for very large networks. Overall, our study highlights that by exploiting the properties of a well understood statistical model for complex networks and combining it with standard machine learning techniques, we can simplify the link prediction problem when incorporating multivariate node metadata. Our procedure can be immediately applied to different types of networks, and to a wide variety of data from different systems. As such, both from a network science and data science perspective, our work offers a flexible and generalisable procedure for link prediction.

A Review of Machine Learning Techniques for Anomaly Detection in Static Graphs

2020 ◽  
pp. 146-162
Author(s):  
Hesham M. Al-Ammal
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Anomaly Detection ◽  
Real Life ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Methods ◽  
Data Set ◽  
Learning Techniques ◽  
Vector Machines

Detection of anomalies in a given data set is a vital step in several applications in cybersecurity; including intrusion detection, fraud, and social network analysis. Many of these techniques detect anomalies by examining graph-based data. Analyzing graphs makes it possible to capture relationships, communities, as well as anomalies. The advantage of using graphs is that many real-life situations can be easily modeled by a graph that captures their structure and inter-dependencies. Although anomaly detection in graphs dates back to the 1990s, recent advances in research utilized machine learning methods for anomaly detection over graphs. This chapter will concentrate on static graphs (both labeled and unlabeled), and the chapter summarizes some of these recent studies in machine learning for anomaly detection in graphs. This includes methods such as support vector machines, neural networks, generative neural networks, and deep learning methods. The chapter will reflect the success and challenges of using these methods in the context of graph-based anomaly detection.

scholarly journals Natural language processing systems for data extraction and mapping on the basis of unstructured text blocks

2020 ◽  
Vol 26 (3) ◽  
pp. 53-61
Author(s):  
Pavel Kikin ◽  
Alexey Kolesnikov ◽  
Alexey Portnov ◽  
Denis Grischenko
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Mathematical Models ◽  
Optimal Algorithm ◽  
The State ◽  
Gradient Boosting ◽  
Learning Methods ◽  
Data Set ◽  
Machine Learning Methods ◽  
Spatio Temporal

The state of ecological systems, along with their general characteristics, is almost always described by indicators that vary in space and time, which leads to a significant complication of constructing mathematical models for predicting the state of such systems. One of the ways to simplify and automate the construction of mathematical models for predicting the state of such systems is the use of machine learning methods. The article provides a comparison of traditional and based on neural networks, algorithms and machine learning methods for predicting spatio-temporal series representing ecosystem data. Analysis and comparison were carried out among the following algorithms and methods: logistic regression, random forest, gradient boosting on decision trees, SARIMAX, neural networks of long-term short-term memory (LSTM) and controlled recurrent blocks (GRU). To conduct the study, data sets were selected that have both spatial and temporal components: the values of the number of mosquitoes, the number of dengue infections, the physical condition of tropical grove trees, and the water level in the river. The article discusses the necessary steps for preliminary data processing, depending on the algorithm used. Also, Kolmogorov complexity was calculated as one of the parameters that can help formalize the choice of the most optimal algorithm when constructing mathematical models of spatio-temporal data for the sets used. Based on the results of the analysis, recommendations are given on the application of certain methods and specific technical solutions, depending on the characteristics of the data set that describes a particular ecosystem

scholarly journals In Silico Prediction of siRNA Ionizable-Lipid Nanoparticles in vivo Efficacy: Machine Learning Modeling Based on Formulation and Molecular Descriptors

2021 ◽  
Author(s):  
Abdelkader A Metwally ◽  
Amira A Nayel ◽  
Rania M Hathout
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
In Silico ◽  
Molecular Descriptors ◽  
Lipid Nanoparticles ◽  
Data Set ◽  
In Vivo Efficacy ◽  
Artificial Neural

In silico prediction of the in vivo efficacy of siRNA ionizable-lipid nanoparticles is desirable yet never achieved before. This study aims to computationally predict siRNA nanoparticles in vivo efficacy, which saves time and resources. A data set containing 120 entries was prepared by combining molecular descriptors of the ionizable lipids together with two nanoparticles formulation characteristics. Input descriptor combinations were selected by an evolutionary algorithm. Artificial neural networks, support vector machines and partial least squares regression were used for QSAR modeling. Depending on how the data set is split, two training sets and two external validation sets were prepared. Training and validation sets contained 90 and 30 entries respectively. The results showed the successful predictions of validation set log(dose) with R2val = 0.86 – 0.89 and 0.75 – 80 for validation sets one and two respectively. Artificial neural networks resulted in the best R2val for both validation sets. For predictions that have high bias, improvement of R2val from 0.47 to 0.96 was achieved by selecting the training set lipids lying within the applicability domain. In conclusion, in vivo performance of siRNA nanoparticles was successfully predicted by combining cheminformatics with machine learning techniques.

scholarly journals Introducing the Prototypical Stimulus Characteristics Toolbox: Protosc

2021 ◽  
Author(s):  
S. M. Stuit ◽  
C. L. E. Paffen ◽  
S. Van der Stigchel
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Predictive Value ◽  
Methodological Approach ◽  
Ground Truth ◽  
Image Features ◽  
Natural Images ◽  
Learning Performance ◽  
Behavioral Differences ◽  
Data Set

AbstractMany studies use different categories of images to define their conditions. Since any difference between these categories is a valid candidate to explain category-related behavioral differences, knowledge about the objective image differences between categories is crucial for the interpretation of the behaviors. However, natural images vary in many image features and not every feature is equally important in describing the differences between the categories. Here, we provide a methodological approach to find as many of the image features as possible, using machine learning performance as a tool, that have predictive value over the category the images belong to. In other words, we describe a means to find the features of a group of images by which the categories can be objectively and quantitatively defined. Note that we are not aiming to provide a means for the best possible decoding performance; instead, our aim is to uncover prototypical characteristics of the categories. To facilitate the use of this method, we offer an open-source, MATLAB-based toolbox that performs such an analysis and aids the user in visualizing the features of relevance. We first applied the toolbox to a mock data set with a ground truth to show the sensitivity of the approach. Next, we applied the toolbox to a set of natural images as a more practical example.

scholarly journals Adaptive Machine Learning for Robust Diagnostics and Control of Time-Varying Particle Accelerator Components and Beams

2021 ◽  
Author(s):  
Alexander Scheinker
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Adaptive Control ◽  
Surrogate Models ◽  
Particle Accelerator ◽  
Time Varying ◽  
Actual System ◽  
Data Set ◽  
Beam Position ◽  
Model Independent

Machine learning (ML) is growing in popularity for various particle accelerator applications including anomaly detection such as faulty beam position monitor or RF fault identification, for non-invasive diagnostics, and for creating surrogate models. ML methods such as neural networks (NN) are useful because they can learn input-output relationships in large complex systems based on large data sets. Once they are trained, methods such as NNs give instant predictions of complex phenomenon, which makes their use as surrogate models especially appealing for speeding up large parameter space searches which otherwise require computationally expensive simulations. However, quickly time varying systems are challenging for ML-based approaches because the actual system dynamics quickly drifts away from the description provided by any fixed data set, degrading the predictive power of any ML method, and limits their applicability for real time feedback control of quickly time-varying accelerator components and beams. In contrast to ML methods, adaptive model-independent feedback algorithms are by design robust to un-modeled changes and disturbances in dynamic systems, but are usually local in nature and susceptible to local extrema. In this work, we propose that the combination of adaptive feedback and machine learning, adaptive machine learning (AML), is a way to combine the global feature learning power of ML methods such as deep neural networks with the robustness of model-independent control. We present an overview of several ML and adaptive control methods, their strengths and limitations, and an overview of AML approaches. A simple code for the adaptive control algorithm used here can be downloaded from: https://github.com/alexscheinker/ES_adaptive_optimization

Sign in / Sign up

Export Citation Format

Share Document