PyTorchKR Papers

최신 논문

총 9,382편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2205.10325

Classifying Human Activities using Machine Learning and Deep Learning Techniques

Human Activity Recognition (HAR) describes the machines ability to recognize human actions. Nowadays, most people on earth are health conscious, so people are more interested in tracking their daily activities using Smartphones or Smart Watches, which can help them manage their daily routines in a healthy way. With this objective, Kaggle has conducted a competition to classify 6 different human activities distinctly based on the inertial signals obtained from 30 volunteers smartphones. The main challenge in HAR is to overcome the difficulties of separating human activities based on the given data such that no two activities overlap. In this experimentation, first, Data visualization is done on expert generated features with the help of t distributed Stochastic Neighborhood Embedding followed by applying various Machine Learning techniques like Logistic Regression, Linear SVC, Kernel SVM, Decision trees to better classify the 6 distinct human activities. Moreover, Deep Learning techniques like Long Short-Term Memory (LSTM), Bi-Directional LSTM, Recurrent Neural Network (RNN), and Gated Recurrent Unit (GRU) are trained using raw time series data. Finally, metrics like Accuracy, Confusion matrix, precision and recall are used to evaluate the performance of the Machine Learning and Deep Learning models. Experiment results proved that the Linear Support Vector Classifier in machine learning and Gated Recurrent Unit in Deep Learning provided better accuracy for human activity recognition compared to other classifiers.

arXiv:2205.09813

A Novel Weighted Ensemble Learning Based Agent for the Werewolf Game

Werewolf is a popular party game throughout the world, and research on its significance has progressed in recent years. The Werewolf game is based on conversation, and in order to win, participants must use all of their cognitive abilities. This communication game requires the playing agents to be very sophisticated to win. In this research, we generated a sophisticated agent to play the Werewolf game using a complex weighted ensemble learning approach. This research work aimed to estimate what other agents/players think of us in the game. The agent was developed by aggregating strategies of different participants in the AI Wolf competition and thereby learning from them using machine learning. Moreover, the agent created was able to perform much better than other competitors using very basic strategies to show the approach's effectiveness in the Werewolf game. The machine learning technique used here is not restricted to the Werewolf game but may be extended to any game that requires communication and action depending on other participants.

arXiv:2205.09986

SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning

Secure multiparty computation (MPC) has been proposed to allow multiple mutually distrustful data owners to jointly train machine learning (ML) models on their combined data. However, by design, MPC protocols faithfully compute the training functionality, which the adversarial ML community has shown to leak private information and can be tampered with in poisoning attacks. In this work, we argue that model ensembles, implemented in our framework called SafeNet, are a highly MPC-amenable way to avoid many adversarial ML attacks. The natural partitioning of data amongst owners in MPC training allows this approach to be highly scalable at training time, provide provable protection from poisoning attacks, and provably defense against a number of privacy attacks. We demonstrate SafeNet's efficiency, accuracy, and resilience to poisoning on several machine learning datasets and models trained in end-to-end and transfer learning scenarios. For instance, SafeNet reduces backdoor attack success significantly, while achieving $39\times$ faster training and $36 \times$ less communication than the four-party MPC framework of Dalskov et al. Our experiments show that ensembling retains these benefits even in many non-iid settings. The simplicity, cheap setup, and robustness properties of ensembling make it a strong first choice for training ML models privately in MPC.

arXiv:2205.09841

Single-cell Subcellular Protein Localisation Using Novel Ensembles of Diverse Deep Architectures

Unravelling protein distributions within individual cells is key to understanding their function and state and indispensable to developing new treatments. Here we present the Hybrid subCellular Protein Localiser (HCPL), which learns from weakly labelled data to robustly localise single-cell subcellular protein patterns. It comprises innovative DNN architectures exploiting wavelet filters and learnt parametric activations that successfully tackle drastic cell variability. HCPL features correlation-based ensembling of novel architectures that boosts performance and aids generalisation. Large-scale data annotation is made feasible by our "AI-trains-AI" approach, which determines the visual integrity of cells and emphasises reliable labels for efficient training. In the Human Protein Atlas context, we demonstrate that HCPL defines state-of-the-art in the single-cell classification of protein localisation patterns. To better understand the inner workings of HCPL and assess its biological relevance, we analyse the contributions of each system component and dissect the emergent features from which the localisation predictions are derived.

arXiv:2205.09760

Identifying outliers in astronomical images with unsupervised machine learning

Astronomical outliers, such as unusual, rare or unknown types of astronomical objects or phenomena, constantly lead to the discovery of genuinely unforeseen knowledge in astronomy. More unpredictable outliers will be uncovered in principle with the increment of the coverage and quality of upcoming survey data. However, it is a severe challenge to mine rare and unexpected targets from enormous data with human inspection due to a significant workload. Supervised learning is also unsuitable for this purpose since designing proper training sets for unanticipated signals is unworkable. Motivated by these challenges, we adopt unsupervised machine learning approaches to identify outliers in the data of galaxy images to explore the paths for detecting astronomical outliers. For comparison, we construct three methods, which are built upon the k-nearest neighbors (KNN), Convolutional Auto-Encoder (CAE)+ KNN, and CAE + KNN + Attention Mechanism (attCAE KNN) separately. Testing sets are created based on the Galaxy Zoo image data published online to evaluate the performance of the above methods. Results show that attCAE KNN achieves the best recall (78%), which is 53% higher than the classical KNN method and 22% higher than CAE+KNN. The efficiency of attCAE KNN (10 minutes) is also superior to KNN (4 hours) and equal to CAE+KNN(10 minutes) for accomplishing the same task. Thus, we believe it is feasible to detect astronomical outliers in the data of galaxy images in an unsupervised manner. Next, we will apply attCAE KNN to available survey datasets to assess its applicability and reliability.

arXiv:2205.10250공식 코드 · Papers with Code

Explanatory machine learning for sequential human teaching

The topic of comprehensibility of machine-learned theories has recently drawn increasing attention. Inductive Logic Programming (ILP) uses logic programming to derive logic theories from small data based on abduction and induction techniques. Learned theories are represented in the form of rules as declarative descriptions of obtained knowledge. In earlier work, the authors provided the first evidence of a measurable increase in human comprehension based on machine-learned logic rules for simple classification tasks. In a later study, it was found that the presentation of machine-learned explanations to humans can produce both beneficial and harmful effects in the context of game learning. We continue our investigation of comprehensibility by examining the effects of the ordering of concept presentations on human comprehension. In this work, we examine the explanatory effects of curriculum order and the presence of machine-learned explanations for sequential problem-solving. We show that 1) there exist tasks A and B such that learning A before B has a better human comprehension with respect to learning B before A and 2) there exist tasks A and B such that the presence of explanations when learning A contributes to improved human comprehension when subsequently learning B. We propose a framework for the effects of sequential teaching on comprehension based on an existing definition of comprehensibility and provide evidence for support from data collected in human trials. Empirical results show that sequential teaching of concepts with increasing complexity a) has a beneficial effect on human comprehension and b) leads to human re-discovery of divide-and-conquer problem-solving strategies, and c) studying machine-learned explanations allows adaptations of human problem-solving strategy with better performance.

arXiv:2205.10020

Neural Additive Models for Nowcasting

Deep neural networks (DNNs) are one of the most highlighted methods in machine learning. However, as DNNs are black-box models, they lack explanatory power for their predictions. Recently, neural additive models (NAMs) have been proposed to provide this power while maintaining high prediction performance. In this paper, we propose a novel NAM approach for multivariate nowcasting (NC) problems, which comprise an important focus area of machine learning. For the multivariate time-series data used in NC problems, explanations should be considered for every input value to the variables at distinguishable time steps. By employing generalized additive models, the proposed NAM-NC successfully explains each input value's importance for multiple variables and time steps. Experimental results involving a toy example and two real-world datasets show that the NAM-NC predicts multivariate time-series data as accurately as state-of-the-art neural networks, while also providing the explanatory importance of each input value. We also examine parameter-sharing networks using NAM-NC to decrease their complexity, and NAM-MC's hard-tied feature net extracted explanations with good performance.

arXiv:2205.09930공식 코드 · Papers with Code

BayesPCN: A Continually Learnable Predictive Coding Associative Memory

Associative memory plays an important role in human intelligence and its mechanisms have been linked to attention in machine learning. While the machine learning community's interest in associative memories has recently been rekindled, most work has focused on memory recall ($read$) over memory learning ($write$). In this paper, we present BayesPCN, a hierarchical associative memory capable of performing continual one-shot memory writes without meta-learning. Moreover, BayesPCN is able to gradually forget past observations ($forget$) to free its memory. Experiments show that BayesPCN can recall corrupted i.i.d. high-dimensional data observed hundreds to a thousand ``timesteps'' ago without a large drop in recall ability compared to the state-of-the-art offline-learned parametric memory models.

arXiv:2205.09840

A toolbox for idea generation and evaluation: Machine learning, data-driven, and contest-driven approaches to support idea generation

The significance and abundance of data are increasing due to the growing digital data generated from social media, sensors, scholarly literature, patents, different forms of documents published online, databases, product manuals, etc. Various data sources can be used to generate ideas, yet, in addition to bias, the size of the available digital data is a major challenge when it comes to manual analysis. Hence, human-machine interaction is essential for generating valuable ideas where machine learning and data-driven techniques generate patterns from data and serve human sense-making. However, the use of machine learning and data-driven approaches to generate ideas is a relatively new area. Moreover, it is also possible to stimulate innovation using contest-driven idea generation and evaluation. The results and contributions of this thesis can be viewed as a toolbox of idea-generation techniques, including a list of data-driven and machine learning techniques with corresponding data sources and models to support idea generation. In addition, the results include two models, one method and one framework, to better support data-driven and contest- driven idea generation. The beneficiaries of these artefacts are practitioners in data and knowledge engineering, data mining project managers, and innovation agents. Innovation agents include incubators, contest organizers, consultants, innovation accelerators, and industries. Since the proposed artefacts consist of process models augmented with AI techniques, human-centred AI is a promising area of research that can contribute to the artefacts' further development and promote creativity.

arXiv:2205.09510

An Introduction to Quantum Machine Learning for Engineers

In the current noisy intermediate-scale quantum (NISQ) era, quantum machine learning is emerging as a dominant paradigm to program gate-based quantum computers. In quantum machine learning, the gates of a quantum circuit are parametrized, and the parameters are tuned via classical optimization based on data and on measurements of the outputs of the circuit. Parametrized quantum circuits (PQCs) can efficiently address combinatorial optimization problems, implement probabilistic generative models, and carry out inference (classification and regression). This monograph provides a self-contained introduction to quantum machine learning for an audience of engineers with a background in probability and linear algebra. It first describes the necessary background, concepts, and tools necessary to describe quantum operations and measurements. Then, it covers parametrized quantum circuits, the variational quantum eigensolver, as well as unsupervised and supervised quantum machine learning formulations.

arXiv:2205.09488

PSI Draft Specification

This document presents the draft specification for delivering machine learning services over HTTP, developed as part of the Protocols and Structures for Inference project, which concluded in 2013. It presents the motivation for providing machine learning as a service, followed by a description of the essential and optional components of such a service.

arXiv:2205.09353

Physics Informed LSTM Network for Flexibility Identification in Evaporative Cooling Systems

In energy intensive industrial systems, an evaporative cooling process may introduce operational flexibility. Such flexibility refers to a systems ability to deviate from its scheduled energy consumption. Identifying the flexibility, and therefore, designing control that ensures efficient and reliable operation presents a great challenge due to the inherently complex dynamics of industrial systems. Recently, machine learning models have attracted attention for identifying flexibility, due to their ability to model complex nonlinear behavior. This research presents machine learning based methods that integrate system dynamics into the machine learning models (e.g., Neural Networks) for better adherence to physical constraints. We define and evaluate physics informed long-short term memory networks (PhyLSTM) and physics informed neural networks (PhyNN) for the identification of flexibility in the evaporative cooling process. These physics informed networks approximate the time-dependent relationship between control input and system response while enforcing the dynamics of the process in the neural network architecture. Our proposed PhyLSTM provides less than 2% system response estimation error, converges in less than half iterations compared to a baseline Neural Network (NN), and accurately estimates the defined flexibility metrics. We include a detailed analysis of the impact of training data size on the performance and optimization of our proposed models.

arXiv:2205.09301

Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography

Many researchers have used machine learning models to control artificial hands, walking aids, assistance suits, etc., using the biological signal of electromyography (EMG). The use of such devices requires high classification accuracy of machine learning models. One method for improving the classification performance of machine learning models is normalization, such as z-score. However, normalization is not used in most EMG-based motion prediction studies, because of the need for calibration and fluctuation of reference value for calibration (cannot re-use). Therefore, in this study, we proposed a normalization method that combines sliding-window analysis and z-score normalization, that can be implemented in real-time processing without need for calibration. The effectiveness of this normalization method was confirmed by conducting a single-joint movement experiment of the elbow and predicting its rest, flexion, and extension movements from the EMG signal. The proposed normalization method achieved a mean accuracy of 64.6%, an improvement of 15.0% compared to the non-normalization case (mean of 49.8%). Furthermore, to improve practical applications, recent research has focused on reducing the user data required for model learning and improving classification performance in models learned from other people's data. Therefore, we investigated the classification performance of the model learned from other's data. Results showed a mean accuracy of 56.5% when the proposed method was applied, an improvement of 11.1% compared to the non-normalization case (mean of 44.1%). These two results showed the effectiveness of the simple and easy-to-implement method, and that the classification performance of the machine learning model could be improved.

arXiv:2205.09414

Machine learning applications for noisy intermediate-scale quantum computers

Quantum machine learning has proven to be a fruitful area in which to search for potential applications of quantum computers. This is particularly true for those available in the near term, so called noisy intermediate-scale quantum (NISQ) devices. In this Thesis, we develop and study three quantum machine learning applications suitable for NISQ computers, ordered in terms of increasing complexity of data presented to them. These algorithms are variational in nature and use parameterised quantum circuits (PQCs) as the underlying quantum machine learning model. The first application area is quantum classification using PQCs, where the data is classical feature vectors and their corresponding labels. Here, we study the robustness of certain data encoding strategies in such models against noise present in a quantum computer. The second area is generative modelling using quantum computers, where we use quantum circuit Born machines to learn and sample from complex probability distributions. We discuss and present a framework for quantum advantage for such models, propose gradient-based training methods and demonstrate these both numerically and on the Rigetti quantum computer up to 28 qubits. For our final application, we propose a variational algorithm in the area of approximate quantum cloning, where the data becomes quantum in nature. For the algorithm, we derive differentiable cost functions, prove theoretical guarantees such as faithfulness, and incorporate state of the art methods such as quantum architecture search. Furthermore, we demonstrate how this algorithm is useful in discovering novel implementable attacks on quantum cryptographic protocols, focusing on quantum coin flipping and key distribution as examples.

arXiv:2205.09402

Predictive Maintenance using Machine Learning

Predictive maintenance (PdM) is a concept, which is implemented to effectively manage maintenance plans of the assets by predicting their failures with data driven techniques. In these scenarios, data is collected over a certain period of time to monitor the state of equipment. The objective is to find some correlations and patterns that can help predict and ultimately prevent failures. Equipment in manufacturing industry are often utilized without a planned maintenance approach. Such practise frequently results in unexpected downtime, owing to certain unexpected failures. In scheduled maintenance, the condition of the manufacturing equipment is checked after fixed time interval and if any fault occurs, the component is replaced to avoid unexpected equipment stoppages. On the flip side, this leads to increase in time for which machine is non-functioning and cost of carrying out the maintenance. The emergence of Industry 4.0 and smart systems have led to increasing emphasis on predictive maintenance (PdM) strategies that can reduce the cost of downtime and increase the availability (utilization rate) of manufacturing equipment. PdM also has the potential to bring about new sustainable practices in manufacturing by fully utilizing the useful lives of components.

arXiv:2205.09199공식 코드 · Papers with Code

A False Sense of Security? Revisiting the State of Machine Learning-Based Industrial Intrusion Detection

Anomaly-based intrusion detection promises to detect novel or unknown attacks on industrial control systems by modeling expected system behavior and raising corresponding alarms for any deviations.As manually creating these behavioral models is tedious and error-prone, research focuses on machine learning to train them automatically, achieving detection rates upwards of 99%. However, these approaches are typically trained not only on benign traffic but also on attacks and then evaluated against the same type of attack used for training. Hence, their actual, real-world performance on unknown (not trained on) attacks remains unclear. In turn, the reported near-perfect detection rates of machine learning-based intrusion detection might create a false sense of security. To assess this situation and clarify the real potential of machine learning-based industrial intrusion detection, we develop an evaluation methodology and examine multiple approaches from literature for their performance on unknown attacks (excluded from training). Our results highlight an ineffectiveness in detecting unknown attacks, with detection rates dropping to between 3.2% and 14.7% for some types of attacks. Moving forward, we derive recommendations for further research on machine learning-based approaches to ensure clarity on their ability to detect unknown attacks.

arXiv:2205.09196

Hybrid Machine Learning Modeling of Engineering Systems -- A Probabilistic Perspective Tested on a Multiphase Flow Modeling Case Study

To operate process engineering systems in a safe and reliable manner, predictive models are often used in decision making. In many cases, these are mechanistic first principles models which aim to accurately describe the process. In practice, the parameters of these models need to be tuned to the process conditions at hand. If the conditions change, which is common in practice, the model becomes inaccurate and needs to be re-tuned. In this paper, we propose a hybrid modeling machine learning framework that allows tuning first principles models to process conditions using two different types of Bayesian Neural Networks. Our approach not only estimates the expected values of the first principles model parameters but also quantifies the uncertainty of these estimates. Such an approach of hybrid machine learning modeling is not yet well described in the literature, so we believe this paper will provide an additional angle at which hybrid machine learning modeling of physical systems can be considered. As an example, we choose a multiphase pipe flow process for which we constructed a three-phase steady state model based on the drift-flux approach which can be used for modeling of pipe and well flow behavior in oil and gas production systems with or without the neural network tuning. In the simulation results, we show how uncertainty estimates of the resulting hybrid models can be used to make better operation decisions.

arXiv:2205.09115

AutoQML: Automated Quantum Machine Learning for Wi-Fi Integrated Sensing and Communications

Commercial Wi-Fi devices can be used for integrated sensing and communications (ISAC) to jointly exchange data and monitor indoor environment. In this paper, we investigate a proof-of-concept approach using automated quantum machine learning (AutoQML) framework called AutoAnsatz to recognize human gesture. We address how to efficiently design quantum circuits to configure quantum neural networks (QNN). The effectiveness of AutoQML is validated by an in-house experiment for human pose recognition, achieving state-of-the-art performance greater than 80% accuracy for a limited data size with a significantly small number of trainable parameters.

arXiv:2205.09442공식 코드 · Papers with Code

Oracle-MNIST: a Realistic Image Dataset for Benchmarking Machine Learning Algorithms

We introduce the Oracle-MNIST dataset, comprising of 28$\times $28 grayscale images of 30,222 ancient characters from 10 categories, for benchmarking pattern classification, with particular challenges on image noise and distortion. The training set totally consists of 27,222 images, and the test set contains 300 images per class. Oracle-MNIST shares the same data format with the original MNIST dataset, allowing for direct compatibility with all existing classifiers and systems, but it constitutes a more challenging classification task than MNIST. The images of ancient characters suffer from 1) extremely serious and unique noises caused by three-thousand years of burial and aging and 2) dramatically variant writing styles by ancient Chinese, which all make them realistic for machine learning research. The dataset is freely available at https://github.com/wm-bupt/oracle-mnist.

arXiv:2205.09526

Simple Regularisation for Uncertainty-Aware Knowledge Distillation

Considering uncertainty estimation of modern neural networks (NNs) is one of the most important steps towards deploying machine learning systems to meaningful real-world applications such as in medicine, finance or autonomous systems. At the moment, ensembles of different NNs constitute the state-of-the-art in both accuracy and uncertainty estimation in different tasks. However, ensembles of NNs are unpractical under real-world constraints, since their computation and memory consumption scale linearly with the size of the ensemble, which increase their latency and deployment cost. In this work, we examine a simple regularisation approach for distribution-free knowledge distillation of ensemble of machine learning models into a single NN. The aim of the regularisation is to preserve the diversity, accuracy and uncertainty estimation characteristics of the original ensemble without any intricacies, such as fine-tuning. We demonstrate the generality of the approach on combinations of toy data, SVHN/CIFAR-10, simple to complex NN architectures and different tasks.