Related papers: Sliding-Window Normalization to Improve the Perfor…

We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x. Our goal is to explain a single image x with an interpretable 3D computer graphics model having scene graph…

High-dimensional prediction is a challenging problem setting for traditional statistical models. Although regularization improves model performance in high dimensions, it does not sufficiently leverage knowledge on feature importances held…

In structured prediction, the goal is to jointly predict many output variables that together encode a structured object -- a path in a graph, an entity-relation triple, or an ordering of objects. Such a large output space makes learning…

The paper is devoted to the elastostatic calibration of industrial robots, which is used for precise machining of large-dimensional parts made of composite materials. In this technological process, the interaction between the robot and the…

Force and torque sensing is crucial in robotic manipulation across both collaborative and industrial settings. Traditional methods for dynamics identification enable the detection and control of external forces and torques without the need…

Increasing digitalization enables the use of machine learning methods for analyzing and optimizing manufacturing processes. A main application of machine learning is the construction of quality prediction models, which can be used, among…

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective…

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may…

Multimodal machine learning has achieved remarkable progress in a wide range of scenarios. However, the reliability of multimodal learning remains largely unexplored. In this paper, through extensive empirical studies, we identify current…

Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline…

Vision-based perception systems are typically exposed to large orientation changes in different robot applications. In such conditions, their performance might be compromised due to the inherent complexity of processing data captured under…

Smartwatches are increasingly being used to recognize human daily life activities. These devices may employ different kind of machine learning (ML) solutions. One of such ML models is Gradient Boosting Machine (GBM) which has shown an…

We propose two well-motivated ranking-based methods to enhance the performance of current state-of-the-art human activity recognition systems. First, as an improvement over the classic power normalization method, we propose a parameter-free…

Human activity recognition has grown in popularity with its increase of applications within daily lifestyles and medical environments. The goal of having efficient and reliable human activity recognition brings benefits such as accessible…

Regularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in a system that is…

Applications of machine learning (ML) techniques to operational settings often face two challenges: i) ML methods mostly provide point predictions whereas many operational problems require distributional information; and ii) They typically…

We study the task of gesture recognition from electromyography (EMG), with the goal of enabling expressive human-computer interaction at high accuracy, while minimizing the time required for new subjects to provide calibration data. To…

Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its…

Ensemble learning is characterized by flexibility, high precision, and refined structure. As a critical component within computational finance, option pricing with machine learning requires both high predictive accuracy and reduced…

This paper provides a framework to analyze stochastic gradient algorithms in a mean squared error (MSE) sense using the asymptotic normality result of the stochastic gradient descent (SGD) iterates. We perform this analysis by taking the…