Search results for "Learning"

Average Performance Analysis of the Stochastic Gradient Method for Online PCA

2019

International audience; This paper studies the complexity of the stochastic gradient algorithm for PCA when the data are observed in a streaming setting. We also propose an online approach for selecting the learning rate. Simulation experiments confirm the practical relevance of the plain stochastic gradient approach and that drastic improvements can be achieved by learning the learning rate.

On the duality between mechanistic learners and what it is they learn

1993

All previous work in inductive inference and theoretical machine learning has taken the perspective of looking for a learning algorithm that successfully learns a collection of functions. In this work, we consider the perspective of starting with a set of functions, and considering the collection of learning algorithms that are successful at learning the given functions. Some strong dualities are revealed.

Calibrating a Motion Model Based on Reinforcement Learning for Pedestrian Simulation

2012

In this paper, the calibration of a framework based in Multi-agent Reinforcement Learning (RL) for generating motion simulations of pedestrian groups is presented. The framework sets a group of autonomous embodied agents that learn to control individually its instant velocity vector in scenarios with collisions and friction forces. The result of the process is a different learned motion controller for each agent. The calibration of both, the physical properties involved in the motion of our embodied agents and the corresponding dynamics, is an important issue for a realistic simulation. The physics engine used has been calibrated with values taken from real pedestrian dynamics. Two experime…

Multilayer perceptron neural networks and radial-basis function networks as tools to forecast accumulation of deoxynivalenol in barley seeds contamin…

2011

The capacity of multi-layer perceptron artificial neural networks (MLP-ANN) and radial-basis function networks (RBFNs) to predict deoxynivalenol (DON) accumulation in barley seeds contaminated with Fusarium culmorum under different conditions has been assessed. Temperature (20-28 °C), water activity (0.94-0.98), inoculum size (7-15 mm diameter), and time were the inputs while DON concentration was the output. The dataset was used to train, validate and test many ANNs. Minimizing the mean-square error (MSE) was used to choose the optimal network. Single-layer perceptrons with low number of hidden nodes proved better than double-layer perceptrons, but the performance depended on the training …

Kernel manifold alignment for domain adaptation

2016

The wealth of sensory data coming from different modalities has opened numerous opportu- nities for data analysis. The data are of increasing volume, complexity and dimensionality, thus calling for new methodological innovations towards multimodal data processing. How- ever, multimodal architectures must rely on models able to adapt to changes in the data dis- tribution. Differences in the density functions can be due to changes in acquisition conditions (pose, illumination), sensors characteristics (number of channels, resolution) or different views (e.g. street level vs. aerial views of a same building). We call these different acquisition modes domains, and refer to the adaptation proble…

Systematic Approach for Calculating the Concentrations of Chemical Species in Multiequilibrium Problems: Inclusion of the Ionic Strength Effects

2012

A general systematic approach including ionic strength effects is proposed for the numerical calculation of concentrations of chemical species in multiequilibrium problems. This approach extends the versatility of the approach presented in a previous article and is applied using the Solver option of the Excel spreadsheet to solve real problems such as the calculation of the pH of buffer solutions at any ionic strength. It is useful for undergraduate programs, in post-graduate programs, and in professional laboratories to predict experimental conditions.

Delaying elaborated feedback within computer‐based learning environments: The role of summative and question‐based feedback

2021

Technological, Organisational and Socio-Interactional Affordances in Simulation-Based Collaborative Learning

2021

Analysis of the applicability of a learning technology requires an evaluation of how the affordances of the learning environment respond to users’ needs. We examine affordances in a simulation-based collaborative learning environment from the learners’ viewpoint. Our analysis focuses on three types of affordances: technological, organisational and socio-interactional. The findings show how teams of learners employ the different types of affordances in their collaborative tasks. In addition, our analysis illustrates the interdependent and interlinked nature of the affordances. We offer an analytical understanding of the dynamics among different kinds of affordances and show how they can be a…

Detection of developmental dyslexia with machine learning using eye movement data

2021

Dyslexia is a common neurocognitive learning disorder that can seriously hinder individuals’ aspirations if not detected and treated early. Instead of costly diagnostic assessment made by experts, in the near future dyslexia might be identified with ease by automated analysis of eye movements during reading provided by embedded eye tracking technology. However, the diagnostic machine learning methods need to be optimized first. Previous studies with machine learning have been quite successful in identifying dyslexic readers, however, using contrasting groups with large performance differences between diagnosed and good readers. A practical challenge is to identify also individuals with bord…

Deep multimodal fusion for semantic image segmentation: A survey

2021

International audience; Recent advances in deep learning have shown excellent performance in various scene understanding tasks. However, in some complex environments or under challenging conditions, it is necessary to employ multiple modalities that provide complementary information on the same scene. A variety of studies have demonstrated that deep multimodal fusion for semantic image segmentation achieves significant performance improvement. These fusion approaches take the benefits of multiple information sources and generate an optimal joint prediction automatically. This paper describes the essential background concepts of deep multimodal fusion and the relevant applications in compute…