Research Connect
Research PapersAboutContact

Find AI Research Papers

To start, enter a paper identifier.....

See all paper suggestions for ``

Top 10+ AI Research Papers

We also introduce the VoiceAssistant-400K dataset to fine-tune models optimized for speech output. Science mapping software tools: Review, analysis, and cooperative study among tools (Cobo, 2011)

Trending Research

TopNewGreatest

Exploiting symmetry in variational quantum machine learning

Johannes Jakob MeyerMarian MularskiElies Gil-FusterA. A. MeleF. ArzaniAlissa WilmsJ. Eisert
Published in PRX Quantum (2022)
118 Citations47 ReferencesPhysics 1+

Variational quantum machine learning is an extensively studied application of near-term quantum computers. The success of variational quantum learning models crucially depends on finding a suitable parametrization of the model that encodes an inductive bias relevant to the learning task. However, precious little is known about guiding principles for the construction of suitable parametrizations. In this work, we holistically explore when and how symmetries of the learning problem can be exploited to construct quantum learning models with outcomes invariant under the symmetry of the learning task. Building on tools from representation theory, we show how a standard gateset can be transformed into an equivariant gateset that respects the symmetries of the problem at hand through a process of gate symmetrization. We benchmark the proposed methods on two toy problems that feature a non-trivial symmetry and observe a substantial increase in generalization performance. As our tools can also be applied in a straightforward way to other variational problems with symmetric structure, we show how equivariant gatesets can be used in variational quantum eigensolvers.

Graph PDF
External Links: 5View full paper

Machine Learning with a Reject Option: A survey

Kilian HendrickxLorenzo PeriniDries Van der PlasWannes MeertJesse Davis
Published in Machine-mediated learning (2021)
102 Citations276 ReferencesComputer Science

Graph PDF
External Links: 5View full paper

Definitions, methods, and applications in interpretable machine learning

W. James MurdochChandan SinghKarl KumbierR. Abbasi-AslBin Yu
Published in Proceedings of the National Academy of Sciences of the United States of America (2019)
1,293 Citations113 ReferencesMedicine 2+

Significance The recent surge in interpretability research has led to confusion on numerous fronts. In particular, it is unclear what it means to be interpretable and how to select, evaluate, or even discuss methods for producing interpretations of machine-learning models. We aim to clarify these concerns by defining interpretable machine learning and constructing a unifying framework for existing methods which highlights the underappreciated role played by human audiences. Within this framework, methods are organized into 2 classes: model based and post hoc. To provide guidance in selecting and evaluating interpretation methods, we introduce 3 desiderata: predictive accuracy, descriptive accuracy, and relevancy. Using our framework, we review existing work, grounded in real-world studies which exemplify our desiderata, and suggest directions for future work. Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the predictive, descriptive, relevant (PDR) framework for discussing interpretations. The PDR framework provides 3 overarching desiderata for evaluation: predictive accuracy, descriptive accuracy, and relevancy, with relevancy judged relative to a human audience. Moreover, to help manage the deluge of interpretation methods, we introduce a categorization of existing techniques into model-based and post hoc categories, with subgroups including sparsity, modularity, and simulatability. To demonstrate how practitioners can use the PDR framework to evaluate and understand interpretations, we provide numerous real-world examples. These examples highlight the often underappreciated role played by human audiences in discussions of interpretability. Finally, based on our framework, we discuss limitations of existing methods and directions for future work. We hope that this work will provide a common vocabulary that will make it easier for both practitioners and researchers to discuss and choose from the full range of interpretation methods.

Graph PDF
External Links: 7View full paper

Deep learning a boon for biophotonics?

Pranita PradhanShuxia GuoOleg RyabchykovJ. PoppT. Bocklitz
Published in Journal of Biophotonics (2020)
66 Citations131 ReferencesMedicine 1+

This review covers original articles using deep learning in the biophotonic field published in the last years. In these years deep learning, which is a subset of machine learning mostly based on artificial neural network geometries, was applied to a number of biophotonic tasks and has achieved state‐of‐the‐art performances. Therefore, deep learning in the biophotonic field is rapidly growing and it will be utilized in the next years to obtain real‐time biophotonic decision‐making systems and to analyze biophotonic data in general. In this contribution, we discuss the possibilities of deep learning in the biophotonic field including image classification, segmentation, registration, pseudostaining and resolution enhancement. Additionally, we discuss the potential use of deep learning for spectroscopic data including spectral data preprocessing and spectral classification. We conclude this review by addressing the potential applications and challenges of using deep learning for biophotonic data.

Graph PDF
External Links: 5View full paper

Explainable and Interpretable Models in Computer Vision and Machine Learning

Hugo Jair EscalanteSergio EscaleraIsabelle M GuyonXavier BaróYağmur GüçlütürkUmut GüçlüM. Gerven
Published in (2017)
103 Citations432 ReferencesComputer Science 1+

Graph PDF
External Links: 5View full paper

Geometric deep learning of RNA structure

Raphael J. L. TownshendStephan EismannA. WatkinsR. RanganMaria KarelinaRhiju DasR. Dror
Published in Science (2021)
234 Citations58 ReferencesMedicine

Machine learning solves RNA puzzles RNA molecules fold into complex three-dimensional shapes that are difficult to determine experimentally or predict computationally. Understanding these structures may aid in the discovery of drugs for currently untreatable diseases. Townshend et al. introduced a machine-learning method that significantly improves prediction of RNA structures (see the Perspective by Weeks). Most other recent advances in deep learning have required a tremendous amount of data for training. The fact that this method succeeds given very little training data suggests that related methods could address unsolved problems in many fields where data are scarce. Science, abe5650, this issue p. 1047; see also abk1971, p. 964 A machine learning method significantly improves scoring of RNA structural models, despite being trained on very few structures. RNA molecules adopt three-dimensional structures that are critical to their function and of interest in drug discovery. Few RNA structures are known, however, and predicting them computationally has proven challenging. We introduce a machine learning approach that enables identification of accurate structural models without assumptions about their defining characteristics, despite being trained with only 18 known RNA structures. The resulting scoring function, the Atomic Rotationally Equivariant Scorer (ARES), substantially outperforms previous methods and consistently produces the best results in community-wide blind RNA structure prediction challenges. By learning effectively even from a small amount of data, our approach overcomes a major limitation of standard deep neural networks. Because it uses only atomic coordinates as inputs and incorporates no RNA-specific information, this approach is applicable to diverse problems in structural biology, chemistry, materials science, and beyond.

Graph PDF
External Links: 4View full paper

Comparison of Deep-Learning and Conventional Machine-Learning Methods for the Automatic Recognition of the Hepatocellular Carcinoma Areas from Ultrasound Images

R. BreharD. MitreaF. VanceaT. MariţaS. NedevschiM. PlatonMagda RotaruR. Badea
Published in Italian National Conference on Sensors (2020)
64 Citations47 ReferencesMedicine 1+

The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.

Graph PDF
External Links: 7View full paper

Deep Learning applications for COVID-19

Connor ShortenT. KhoshgoftaarB. Furht
Published in Journal of Big Data (2021)
243 Citations152 ReferencesDatasets 8Medicine

Graph PDF
External Links: 6View full paper

Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance

M. AhsanM. MahmudP. SahaKishor Datta GuptaZ. Siddique
Published in Technologies (2021)
324 Citations38 ReferencesComputer Science

Heart disease, one of the main reasons behind the high mortality rate around the world, requires a sophisticated and expensive diagnosis process. In the recent past, much literature has demonstrated machine learning approaches as an opportunity to efficiently diagnose heart disease patients. However, challenges associated with datasets such as missing data, inconsistent data, and mixed data (containing inconsistent missing data both as numerical and categorical) are often obstacles in medical diagnosis. This inconsistency led to a higher probability of misprediction and a misled result. Data preprocessing steps like feature reduction, data conversion, and data scaling are employed to form a standard dataset—such measures play a crucial role in reducing inaccuracy in final prediction. This paper aims to evaluate eleven machine learning (ML) algorithms—Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Naive Bayes (NB), Support Vector Machine (SVM), XGBoost (XGB), Random Forest Classifier (RF), Gradient Boost (GB), AdaBoost (AB), Extra Tree Classifier (ET)—and six different data scaling methods—Normalization (NR), Standscale (SS), MinMax (MM), MaxAbs (MA), Robust Scaler (RS), and Quantile Transformer (QT) on a dataset comprising of information of patients with heart disease. The result shows that CART, along with RS or QT, outperforms all other ML algorithms with 100% accuracy, 100% precision, 99% recall, and 100% F1 score. The study outcomes demonstrate that the model’s performance varies depending on the data scaling method.

Graph PDF
External Links: 4View full paper

Interpretable Machine Learning

Bradley C. BoehmkeBrandon M. Greenwell
Published in (2019)
2,391 Citations165 ReferencesComputer Science

Interpretable machine learning has become a popular research direction as deep neural networks (DNNs) have become more powerful and their applications more mainstream, yet DNNs remain difficult to understand. Testing with Concept Activation Vectors, TCAV, (Kim et al. 2017) is an approach to interpreting DNNs in a human-friendly way and has recently received significant attention in the machine learning community. The TCAV algorithm achieves a degree of global interpretability for DNNs through human-defined concepts as explanations. This project introduces Robust TCAV, which builds on TCAV and experimentally determines best practices for this method. The objectives for Robust TCAV are 1) Making TCAV more consistent by reducing variance in the TCAV score distribution and 2) Increasing CAV and TCAV score resistance to perturbations. A difference of means method for CAV generation was determined to be the best practice to achieve both objectives. Many areas of the TCAV process are explored including CAV visualization in low dimensions, negative class selection, and activation perturbation in the direction of a CAV. Finally, a thresholding technique is considered to remove noise in TCAV scores. This project is a step in the direction of making TCAV, an already impactful algorithm in interpretability, more reliable and useful for practitioners.

Graph PDF
External Links: 4View full paper

Network intrusion detection system: A systematic study of machine learning and deep learning approaches

Zeeshan AhmadA. KhanW. CheahJ. AbdullahFarhan Ahmad
Published in Transactions on Emerging Telecommunications Technologies (2020)
620 Citations150 ReferencesComputer Science

The rapid advances in the internet and communication fields have resulted in a huge increase in the network size and the corresponding data. As a result, many novel attacks are being generated and have posed challenges for network security to accurately detect intrusions. Furthermore, the presence of the intruders with the aim to launch various attacks within the network cannot be ignored. An intrusion detection system (IDS) is one such tool that prevents the network from possible intrusions by inspecting the network traffic, to ensure its confidentiality, integrity, and availability. Despite enormous efforts by the researchers, IDS still faces challenges in improving detection accuracy while reducing false alarm rates and in detecting novel intrusions. Recently, machine learning (ML) and deep learning (DL)‐based IDS systems are being deployed as potential solutions to detect intrusions across the network in an efficient manner. This article first clarifies the concept of IDS and then provides the taxonomy based on the notable ML and DL techniques adopted in designing network‐based IDS (NIDS) systems. A comprehensive review of the recent NIDS‐based articles is provided by discussing the strengths and limitations of the proposed solutions. Then, recent trends and advancements of ML and DL‐based NIDS are provided in terms of the proposed methodology, evaluation metrics, and dataset selection. Using the shortcomings of the proposed methods, we highlighted various research challenges and provided the future scope for the research in improving ML and DL‐based NIDS.

Graph PDF
External Links: 5View full paper

Alibi Explain: Algorithms for Explaining Machine Learning Models

Janis KlaiseA. V. LooverenG. VacantiAlexandru Coca
Published in Journal of machine learning research (2021)
96 Citations24 ReferencesComputer Science

We introduce Alibi Explain , an open-source Python library for explaining predictions of machine learning models ( https://github.com/SeldonIO/alibi ). The library features state-of-the-art explainability algorithms for classification and regression models. The algorithms cover both the model-agnostic (black-box) and model-specific (white-box) setting, cater for multiple data types (tabular, text, images) and explanation scope (local and global explanations). The library exposes a unified API enabling users to work with explanations in a consistent way. Alibi adheres to best development practices featuring extensive testing of code correctness and algorithm convergence in a continuous integration environment. The library comes with extensive documentation of both usage and theoretical background of methods, and a suite of worked end-to-end use cases. Alibi aims to be a production-ready toolkit with integrations into machine learning deployment platforms such as Seldon Core and KFServing , and distributed explanation capabilities using Ray .

Graph
External Links: 3View full paper

Machine learning pipeline for battery state-of-health estimation

D. RomanSaurabh SaxenaV. RobuMichael G. PechtD. Flynn
Published in Nature Machine Intelligence (2021)
305 Citations89 ReferencesComputer Science

Graph
External Links: 6View full paper

The Limitations of Deep Learning in Adversarial Settings

Nicolas PapernotP. McdanielS. JhaMatt FredriksonZ. B. CelikA. Swami
Published in European Symposium on Security and Privacy (2015)
3,774 Citations45 ReferencesDatasets 1Computer Science 1+

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs. In an application to computer vision, we show that our algorithms can reliably produce samples correctly classified by human subjects but misclassified in specific targets by a DNN with a 97% adversarial success rate while only modifying on average 4.02% of the input features per sample. We then evaluate the vulnerability of different sample classes to adversarial perturbations by defining a hardness measure. Finally, we describe preliminary work outlining defenses against adversarial samples by defining a predictive measure of distance between a benign input and a target classification.

Graph PDF
External Links: 6View full paper

Obtaining genetics insights from deep learning via explainable artificial intelligence

Gherman NovakovskyN. DexterMaxwell W. LibbrechtW. WassermanS. Mostafavi
Published in Nature reviews genetics (2022)
172 Citations111 ReferencesMedicine

Graph
External Links: 4View full paper