scholarly journals Learning Deep Attention Network from Incremental and Decremental Features for Evolving Features

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Chuxin Wang ◽  
Haoran Mo
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Real World ◽  
Learning Problems ◽  
Data Sets ◽  
Attention Network ◽  
Benchmark Data ◽  
Multiple Cross ◽  
Feature Attention ◽  
The Cross

In many real-world machine learning problems, the features are changing along the time, with some old features vanishing and some other new features augmented, while the remaining features survived. In this paper, we propose the cross-feature attention network to handle the incremental and decremental features. This network is composed of multiple cross-feature attention encoding-decoding layers. In each layer, the data samples are firstly encoded by the combination of other samples with vanished/augmented features and weighted by the attention weights calculated by the survived features. Then, the samples are encoded by the combination of samples with the survived features weighted by the attention weights calculated from the encoded vanished/augmented feature data. The encoded vanished/augmented/survived features are then decoded and fed to the next cross-feature attention layer. In this way, the incremental and decremental features are bridged by paying attention to each other, and the gap between data samples with a different set of features are filled by the attention mechanism. The outputs of the cross-feature attention network are further concatenated and fed to the class-specific attention and global attention network for the purpose of classification. We evaluate the proposed network with benchmark data sets of computer vision, IoT, and bio-informatics, with incremental and decremental features. Encouraging experimental results show the effectiveness of our algorithm.

Validation-Based Sparse Gaussian Process Classifier Design

2009 ◽  
Vol 21 (7) ◽  
pp. 2082-2103 ◽  
Author(s):  
Shirish Shevade ◽  
S. Sundararajan
Keyword(s):  
Bayesian Methods ◽  
Real World ◽  
Basis Vector ◽  
Data Sets ◽  
Training Set ◽  
Classifier Design ◽  
Set Size ◽  
Benchmark Data ◽  
Regression Problems ◽  
Classification And Regression

Gaussian processes (GPs) are promising Bayesian methods for classification and regression problems. Design of a GP classifier and making predictions using it is, however, computationally demanding, especially when the training set size is large. Sparse GP classifiers are known to overcome this limitation. In this letter, we propose and study a validation-based method for sparse GP classifier design. The proposed method uses a negative log predictive (NLP) loss measure, which is easy to compute for GP models. We use this measure for both basis vector selection and hyperparameter adaptation. The experimental results on several real-world benchmark data sets show better or comparable generalization performance over existing methods.

SeisBench: A toolbox for benchmarking and applying machine learning in seismology.

2021 ◽  
Author(s):  
Jack Woollam ◽  
Jannes Münchmeyer ◽  
Carlo Giunchi ◽  
Dario Jozinovic ◽  
Tobias Diehl ◽  
...  
Keyword(s):  
Machine Learning ◽  
Model Comparison ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Quality Data ◽  
Data Sets ◽  
Waveform Data ◽  
Detection Techniques ◽  
Benchmark Data

<p>Machine learning methods have seen widespread adoption within the seismological community in recent years due to their ability to effectively process large amounts of data, while equalling or surpassing the performance of human analysts or classic algorithms. In the wider machine learning world, for example in imaging applications, the open availability of extensive high-quality datasets for training, validation, and the benchmarking of competing algorithms is seen as a vital ingredient to the rapid progress observed throughout the last decade. Within seismology, vast catalogues of labelled data are readily available, but collecting the waveform data for millions of records and assessing the quality of training examples is a time-consuming, tedious process. The natural variability in source processes and seismic wave propagation also presents a critical problem during training. The performance of models trained on different regions, distance and magnitude ranges are not easily comparable. The inability to easily compare and contrast state-of-the-art machine learning-based detection techniques on varying seismic data sets is currently a barrier to further progress within this emerging field. We present SeisBench, an extensible open-source framework for training, benchmarking, and applying machine learning algorithms. SeisBench provides access to various benchmark data sets and models from literature, along with pre-trained model weights, through a unified API. Built to be extensible, and modular, SeisBench allows for the simple addition of new models and data sets, which can be easily interchanged with existing pre-trained models and benchmark data. Standardising the access of varying quality data, and metadata simplifies comparison workflows, enabling the development of more robust machine learning algorithms. We initially focus on phase detection, identification and picking, but the framework is designed to be extended for other purposes, for example direct estimation of event parameters. Users will be able to contribute their own benchmarks and (trained) models. In the future, it will thus be much easier to compare both the performance of new algorithms against published machine learning models/architectures and to check the performance of established algorithms against new data sets. We hope that the ease of validation and inter-model comparison enabled by SeisBench will serve as a catalyst for the development of the next generation of machine learning techniques within the seismological community. The SeisBench source code will be published with an open license and explicitly encourages community involvement.</p>

scholarly journals On the data set’s ruins

AI & Society ◽  
2020 ◽  
Author(s):  
Nicolas Malevé
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
High Speed ◽  
Large Population ◽  
Active Role ◽  
The Internet ◽  
Data Sets ◽  
Specific Character ◽  
Unlimited Access

Abstract Computer vision aims to produce an understanding of digital image’s content and the generation or transformation of images through software. Today, a significant amount of computer vision algorithms rely on techniques of machine learning which require large amounts of data assembled in collections, or named data sets. To build these data sets a large population of precarious workers label and classify photographs around the clock at high speed. For computers to learn how to see, a scale articulates macro and micro dimensions: the millions of images culled from the internet with the few milliseconds given to the workers to perform a task for which they are paid a few cents. This paper engages in details with the production of this scale and the labour it relies on: its elaboration. This elaboration does not only require hands and retinas, it also crucially zes mobilises the photographic apparatus. To understand the specific character of the scale created by computer vision scientists, the paper compares it with a previous enterprise of scaling, Malraux’s Le Musée Imaginaire, where photography was used as a device to undo the boundaries of the museum’s collection and open it to an unlimited access to the world’s visual production. Drawing on Douglas Crimp’s argument that the “musée imaginaire”, a hyperbole of the museum, relied simultaneously on the active role of the photographic apparatus for its existence and on its negation, the paper identifies a similar problem in computer vision’s understanding of photography. The double dismissal of the role played by the workers and the agency of the photographic apparatus in the elaboration of computer vision foreground the inherent fragility of the edifice of machine vision and a necessary rethinking of its scale.

scholarly journals A Systematic Methodology on Class Imbalanced Problems involved in the Classification of Real-World Datasets

2019 ◽  
Vol 8 (3) ◽  
pp. 7071-7081
Keyword(s):  
Machine Learning ◽  
Real World ◽  
Imbalanced Data ◽  
Past Research ◽  
Future Research ◽  
Data Sets ◽  
Time Data ◽  
Real World Data ◽  
The Past ◽  
Research Studies

Current generation real-world data sets processed through machine learning are imbalanced by nature. This imbalanced data enables the researchers with a challenging scenario in the context of perdition for both the machine learning and data mining algorithms. It is observed from the past research studies most of the imbalanced data sets consists of the major classes and minor classes and the major class leads the minor class. Several standards and hybrid prediction algorithms are proposed in various application domains but in most of the real-time data sets analyzed in the studies are imbalanced by nature thereby affecting the accuracy of the prediction. This paper presents a systematic survey of the past research studies to analyze intrinsic data characteristics and techniques utilized for handling class-imbalanced data. In addition, this study reveals the research gaps, trends and patterns in existing studies and discusses briefly on future research directions

scholarly journals Applications of MaxSAT in Data Analysis

10.29007/3qkh ◽  
2019 ◽  
Author(s):  
Jeremias Berg ◽  
Antti Hyttinen ◽  
Matti Järvisalo
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Real World ◽  
Optimization Problems ◽  
Learning Problems ◽  
Integral Role ◽  
Benchmark Sets

We highlight important real-world optimization problems arising from data analysis and machine learning, representing somewhat atypical applications of SAT-based solver technology, to which the SAT community could focus more attention on. To address the problem of current lack of heterogeneity in benchmark sets available for evaluating MaxSAT solvers, we provide a benchmark library of MaxSAT instances encoding different data analysis and machine learning problems. By doing so, we also advocate extending MaxSAT solvers to accept real-valued weights for soft clauses as input via the presented problem domains in which the use of real-valued costs plays an integral role.

scholarly journals Learning to Follow Directions in Street View

2020 ◽  
Vol 34 (07) ◽  
pp. 11773-11781 ◽  
Author(s):  
Karl Moritz Hermann ◽  
Mateusz Malinowski ◽  
Piotr Mirowski ◽  
Andras Banki-Horvath ◽  
Keith Anderson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Reinforcement Learning ◽  
Real World ◽  
Real World Data ◽  
Simulated Environments ◽  
Extensive Analysis ◽  
Street View ◽  
Generalisation Ability ◽  
Real Places

Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision. We propose an instruction-following task that requires all of the above, and which combines the practicality of simulated environments with the challenges of ambiguous, noisy real world data. StreetNav is built on top of Google Street View and provides visually accurate environments representing real places. Agents are given driving instructions which they must learn to interpret in order to successfully navigate in this environment. Since humans equipped with driving instructions can readily navigate in previously unseen cities, we set a high bar and test our trained agents for similar cognitive capabilities. Although deep reinforcement learning (RL) methods are frequently evaluated only on data that closely follow the training distribution, our dataset extends to multiple cities and has a clean train/test separation. This allows for thorough testing of generalisation ability. This paper presents the StreetNav environment and tasks, models that establish strong baselines, and extensive analysis of the task and the trained agents.

scholarly journals Lifelong Machine Learning for Regional-Based Image Classification in Open Datasets

Symmetry ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 2094
Author(s):  
Hashem Alyami ◽  
Abdullah Alharbi ◽  
Irfan Uddin
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Open Data ◽  
Research Field ◽  
Learning Problems ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Open Datasets

Deep Learning algorithms are becoming common in solving different supervised and unsupervised learning problems. Different deep learning algorithms were developed in last decade to solve different learning problems in different domains such as computer vision, speech recognition, machine translation, etc. In the research field of computer vision, it is observed that deep learning has become overwhelmingly popular. In solving computer vision related problems, we first take a CNN (Convolutional Neural Network) which is trained from scratch or some times a pre-trained model is taken and further fine-tuned based on the dataset that is available. The problem of training the model from scratch on new datasets suffers from catastrophic forgetting. Which means that when a new dataset is used to train the model, it forgets the knowledge it has obtained from an existing dataset. In other words different datasets does not help the model to increase its knowledge. The problem with the pre-trained models is that mostly CNN models are trained on open datasets, where the data set contains instances from specific regions. This results into predicting disturbing labels when the same model is used for instances of datasets collected in a different region. Therefore, there is a need to find a solution on how to reduce the gap of Geo-diversity in different computer vision problems in developing world. In this paper, we explore the problems of models that were trained from scratch along with models which are pre-trained on a large dataset, using a dataset specifically developed to understand the geo-diversity issues in open datasets. The dataset contains images of different wedding scenarios in South Asian countries. We developed a Lifelong CNN that can incrementally increase knowledge i.e., the CNN learns labels from the new dataset but includes the existing knowledge of open data sets. The proposed model demonstrates highest accuracy compared to models trained from scratch or pre-trained model.

Learning attitudinal decision model through pair-wise preferences

Kybernetes ◽  
2018 ◽  
Vol 47 (8) ◽  
pp. 1569-1584
Author(s):  
Manish Aggarwal
Keyword(s):  
Machine Learning ◽  
Design Methodology ◽  
Decision Model ◽  
Choice Model ◽  
Weight Vector ◽  
Preference Learning ◽  
Learning Approach ◽  
Data Sets ◽  
Content Type ◽  
Benchmark Data

Purpose This paper aims to learn a decision-maker’s (DM’s) decision model that is characterized in terms of the attitudinal character and the attributes weight vector, both of which are specific to the DM. The authors take the learning information in the form of the exemplary preferences, given by a DM. The learning approach is formalized by bringing together the recent research in the choice models and machine learning. The study is validated on a set of 12 benchmark data sets. Design/methodology/approach The study includes emerging preference learning algorithms. Findings Learning of a DM’s attitudinal choice model. Originality/value Preferences-based learning of a DM’s attitudinal decision model.

Sign in / Sign up

Export Citation Format

Share Document