arXiv research

This study shows how social insects and machine learning methods share a common mathematical framework.

Paper proposes a multi-phase pruning pipeline for deep ensemble learning on IIoT devices.

Meta-learning predicts optimal ensemble size and methods for time series forecasting.

Bayesian inference using stochastic neural networks ensembles.

Stochasticity is key for machine learning's robustness and generalizability.

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic r…

Lecture note for data science students on machine learning basics and advanced topics.

Nowadays, mobile telephony interruptions in our daily life activities are common because of the inappropriate ringing notifications of incoming phone calls in different contexts. Such interruptions may impact on the work attention not only for the mobile phone owners but also the surrounding people. Decision tree is th…

The paper solves optimal bounds for separating data points in high dimensions.

In this article, we advocate the ensemble approach for variable selection. We point out that the stochastic mechanism used to generate the variable-selection ensemble (VSE) must be picked with care. We construct a VSE using a stochastic stepwise algorithm, and compare its performance with numerous state-of-the-art algo…

New method reduces ensemble size for linear bandits, achieving near optimal regret.

Ant colonies and boosting algorithms both reduce bias and variance through adaptive mechanisms.

Deep ensembles effectively capture epistemic uncertainty through training stochasticity, providing a frequentist perspective.

A new stochastic method handles ensemble creation with cost constraints.

A new batch ensemble method reduces regret in stochastic bandits.

Cyber threat intelligence is one of the emerging areas of focus in information security. Much of the recent work has focused on rule-based methods and detection of network attacks using Intrusion Detection algorithms. In this paper we propose a framework for inspecting and modelling the behavioural aspect of an attacke…

Proposes a new method to enhance neural learning by maximizing information gain.

The use of autonomous vehicles (AVs) is a promising technology in Intelligent Transportation Systems (ITSs) to improve safety and driving efficiency. Vehicle-to-everything (V2X) technology enables communication among vehicles and other infrastructures. However, AVs and Internet of Vehicles (IoV) are vulnerable to diffe…

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs…

EPINET improves neural networks with less computation.

Paper uses AI methods to forecast Bitcoin prices.

The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to…

ES reduces high-probability regret in stochastic linear bandits.

Proposes SWA for adversarial training to improve model robustness.

Extracting actionable intelligence from distributed, heterogeneous, correlated and high-dimensional data sources requires run-time processing and learning both locally and globally. In the last decade, a large number of meta-learning techniques have been proposed in which local learners make online predictions based on…

Ensembling DNNs improves minority group performance, leading to fairness.

Paper combines multiple ETA models into a stacked ensemble for better ETA predictions.

Computational Intelligence (CI) is a sub-branch of Artificial Intelligence paradigm focusing on the study of adaptive mechanisms to enable or facilitate intelligent behavior in complex and changing environments. There are several paradigms of CI [like artificial neural networks, evolutionary computations, swarm intelli…

Stochastic mirror descent improves performance on ensemble models.

Statistical estimates can often be improved by fusion of data from several different sources. One example is so-called ensemble methods which have been successfully applied in areas such as machine learning for classification and clustering. In this paper, we present an ensemble method to improve community detection by…

Paper introduces XBART for nonlinear regression, outperforming XGBoost.

LLEB uses a learned prior to quantify neural network uncertainty.

Anti-Distillation improves reproducibility of deep networks by making ensemble predictions more diverse.

SETrLUSI combines diverse knowledge from multiple domains for faster convergence.

Meta-ensemble scheme allocates queries to EC nodes for reduced latency.

A new method for time series imputation that estimates uncertainty.

The question why deep learning algorithms generalize so well has attracted increasing research interest. However, most of the well-established approaches, such as hypothesis capacity, stability or sparseness, have not provided complete explanations (Zhang et al., 2016; Kawaguchi et al., 2017). In this work, we focus on…

SPEQ improves quantized neural networks by stochastic precision sharing and cosine similarity loss.

Paper uses ensemble learning for IoT cybersecurity anomaly detection.

Ensemble models provide more accurate feature importance estimates than single models.

DOFEN improves DNN performance on tabular data benchmarks.

Recent advances in machine learning and artificial intelligence are now being considered in safety-critical autonomous systems where software defects may cause severe harm to humans and the environment. Design organizations in these domains are currently unable to provide convincing arguments that their systems are saf…

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In this paper, we consider a setting where we have access to an ensemble of pre-tr…

This paper uses Bayesian optimization to efficiently identify stochastic dynamical systems.

New algorithm reduces overfitting in neural networks.

The superior performance of ensemble methods with infinite models are well known. Most of these methods are based on optimization problems in infinite-dimensional spaces with some regularization, for instance, boosting methods and convex neural networks use $L^1$-regularization with the non-negative constraint. However…

EnsLoss combines multiple loss functions to prevent overfitting in classification.

In this study, an efficient stochastic gradient-free method, the ensemble neural networks (ENN), is developed. In the ENN, the optimization process relies on covariance matrices rather than derivatives. The covariance matrices are calculated by the ensemble randomized maximum likelihood algorithm (EnRML), which is an i…