Related papers: Probabilistic Discriminative Models Address the Ta…

A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that…

The missing signal caused by the objects being occluded or an unstable sensor is a common challenge during data collection. Such missing signals will adversely affect the results obtained from the data, and this issue is observed more…

AI and data-driven models have large potential for data assimilation applications by creating fast and accurate forecasts. Their tendency to produce spurious inaccurate, nonphysical results -- hallucination -- however, raises a serious…

We consider the problem of estimating the conditional probability distribution of missing values given the observed ones. We propose an approach, which combines the flexibility of deep neural networks with the simplicity of Gaussian mixture…

Aliasing is a highly important concept in signal processing, as careful consideration of resolution changes is essential in ensuring transmission and processing quality of audio, image, and video. Despite this, up until recently aliasing…

High-resolution tactile sensing can provide accurate information about local contact in contact-rich robotic tasks. However, the deployment of such tasks in unstructured environments remains under-investigated. To improve the robustness of…

Hidden Markov Models with an underlying Mixture of Gaussian structure have proven effective in learning Human-Robot Interactions from demonstrations for various interactive tasks via Gaussian Mixture Regression. However, a mismatch occurs…

Deep learning offers promising new ways to accurately model aleatoric uncertainty in robotic state estimation systems, particularly when the uncertainty distributions do not conform to traditional assumptions of being fixed and Gaussian. In…

In essence, successful grasp boils down to correct responses to multiple contact events between fingertips and objects. In most scenarios, tactile sensing is adequate to distinguish contact events. Due to the nature of high dimensionality…

Undesired bias afflicts both human and algorithmic decision making, and may be especially prevalent when information processing trade-offs incentivize the use of heuristics. One primary example is \textit{statistical discrimination} --…

Tactile predictive models can be useful across several robotic manipulation tasks, e.g. robotic pushing, robotic grasping, slip avoidance, and in-hand manipulation. However, available tactile prediction models are mostly studied for…

Aliasing refers to the phenomenon that high frequency signals degenerate into completely different ones after sampling. It arises as a problem in the context of deep learning as downsampling layers are widely adopted in deep architectures…

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…

From uncertainty quantification to real-world object detection, we recognize the importance of machine learning algorithms, particularly in safety-critical domains such as autonomous driving or medical diagnostics. In machine learning,…

We address the problem of tactile localization, where the goal is to identify image regions that share the same material properties as a tactile input. Existing visuo-tactile methods rely on global alignment and thus fail to capture the…

Humans represent and discriminate the objects in the same category using their properties, and an intelligent robot should be able to do the same. In this paper, we build a robot system that can autonomously perceive the object properties…

Understanding and interpreting how machine learning (ML) models make decisions have been a big challenge. While recent research has proposed various technical approaches to provide some clues as to how an ML model makes individual…

In this work we introduce a mixture of GPs to address the data association problem, i.e. to label a group of observations according to the sources that generated them. Unlike several previously proposed GP mixtures, the novel mixture has…

One major impediment to the wider use of deep learning for clinical decision making is the difficulty of assigning a level of confidence to model predictions. Currently, deep Bayesian neural networks and sparse Gaussian processes are the…

We show that density models describing multiple observables with (i) hard boundaries and (ii) dependence on external parameters may be created using an auto-regressive Gaussian mixture model. The model is designed to capture how observable…