Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

International Joint Conference on Neural Networks

Abstract Class imbalance is often a problem in various real-world data sets, where one class (i.e. the minority class) contains a small number of data points and the other (i.e. the majority class) contains a large number of data points. It is notably difficult to develop an effective model using current data mining and machine learning algorithms without considering data preprocessing to balance the imbalanced data sets. Random undersampling and oversampling have been used in numerous studies to ensure that the different classes contain the same number of data points. A classifier ensemble (i.e. a structure containing several classifiers) can be trained on several different balanced data sets for later classification purposes. In this paper, we introduce two undersampling strategies in which a clustering technique is used during the data preprocessing step. Specifically, the number of clusters in the majority class is set to be equal to the number of data points in the minority class. The first strategy uses the cluster centers to represent the majority class, whereas the second strategy uses the nearest neighbors of the cluster centers. A further study was conducted to examine the effect on performance of the addition or deletion of 5 to 10 cluster centers in the majority class. The experimental results obtained using 44 small-scale and 2 large-scale data sets revealed that the clustering-based undersampling approach with the second strategy outperformed five state-of-the-art approaches. Specifically, this approach combined with a single multilayer perceptron classifier and C4.5 decision tree classifier ensembles delivered optimal performance over both small- and large-scale data sets.

分群式取樣法於類別不平衡問題之研究;Clustering-Based Under-sampling in Class Imbalanced Data

Graph matching, which refers to a class of computational problems of finding an optimal correspondence between the vertices of graphs to minimize (maximize) their node and edge disagreements (affinities), is a fundamental problem in computer science and relates to many areas such as combinatorics, pattern recognition, multimedia and computer vision. Compared with the exact graph (sub)isomorphism often considered in a theoretical setting, inexact weighted graph matching receives more attentions due to its flexibility and practical utility. A short review of the recent research activity concerning (inexact) weighted graph matching is presented, detailing the methodologies, formulations, and algorithms. It highlights the methods under several key bullets, e.g. how many graphs are involved, how the affinity is modeled, how the problem order is explored, and how the matching procedure is conducted etc. Moreover, the research activity at the forefront of graph matching applications especially in computer vision, multimedia and machine learning is reported. The aim is to provide a systematic and compact framework regarding the recent development and the current state-of-the-arts in graph matching.

A Short Survey of Recent Advances in Graph Matching

Celesstin, a system that converts mechanical engineering drawings into a format suitable for CAD, is described. Celesstin integrates several modules in a blackboard-based interpretation system. Once a drawing has been digitized, a first processing step separates the text and the dimensioning lines from the pure graphics part. Celesstin vectorizes the graphics part and assembles the resulting lines into blocks, the basic elements for the technical entities that it creates. The result is transferred to the CAD system. Celesstin tries to match the extracted entities with the corresponding models from the CAD library. It puts the remaining blocks and lines into different layers of the CAD description. The system is based on the assumption that even when the vectorized drawing is distorted, it can be correctly interpreted by using knowledge about the representation rules used in technical drawings and about the manufacturing technology associated with the represented objects. >

Celesstin: CAD conversion of mechanical drawings

Throughout the last 30 years, several methods have been presented to perform error-tolerant graph matching. All of these methods assume there are some given weights that gauge the importance of each of attributes on nodes or edges. These weights are supposed to be manually validated and little research have been done to automatically learn the best combination of weights such that the resulting graph matching problem best matches the expected solution than an expert (human or artificial) would provide. We present an optimisation function (Loss function and Regularisation term) to automatically find these weights. Our practical evaluation reveals that our method properly learns these weights since applying the learned weights, the automatically obtained labelling between nodes is closer to the oracle’s labelling than applying the non-learned weights.

Learning Graph-Matching Substitution Costs Based on the Optimality of the Oracle’s Correspondence

Significant progress has been achieved in objects detection applications such as Face Detection. This mainly due to the latest development in deep learning-based approaches and especially in the computer vision domain. However, deploying deep-learning methods require huge computational power such as graphical processing units. These computational requirements make using such methods unsuitable for deployment on platforms with limited resources, such as edge devices. In this paper, we present an experimental framework to reduce the model’s size systematically, aiming at obtaining a small-size model suitable for deployment in a resource-limited environment. This was achieved by systematic layer removal and filter resizing. Extensive experiments were carried out using the “You Only Look Once” model (YOLO v3-tiny). For evaluation purposes, we used two public datasets to assess the impact of the model’s size reduction on a common computer vision task such as face detection. Results show clearly that, a significant reduction in the model’s size, has a very marginal impact on the overall model’s performance. These results open new directions towards further investigation and research to accelerate the use of deep learning models on edge-devices.

Face Detection with YOLO on Edge

The Graph Edit Distance is the most used distance between Attributed Graphs and it is composed of three main costs on nodes and arcs: Insertion, Deletion and Substitution. We present a method to learn the Insertion and Deletion costs of nodes and edges defined in the Graph Edit Distance, whereas, we define the Edit Cost Substitution data dependent and without parameters (for instance the Euclidean distance). In some applications, the ground truth of the correspondence between some pairs of graphs is available or can be easily deducted. The aim of the method we present is the learning process depends on these few available ground truth correspondences and not to the classification set that in some applications is not available. To learn these costs, the optimisation algorithm tends to minimise the Hamming distance between the ground truth correspondences and the automatically extracted node correspondences. We believe that minimising the Hamming distance makes the matching algorithm to find a good correspondence and so, to increase the recognition ratio of the classification algorithm in a pattern recognition application.

Carlos Francisco Moreno-García

Papers

Learning Graph-Matching Substitution Costs Based on the Optimality of the Oracle’s Correspondence

Face Detection with YOLO on Edge

Ground Truth Correspondence Between Nodes to Learn Graph-Matching Edit-Costs

AGREE: A Feature Attribution Aggregation Framework to Address Explainer Disagreements with Alignment Metrics