Electrical Impedance Tomography (EIT)-inspired tactile sensors are gaining attention in robotic tactile sensing due to their cost-effectiveness, safety, and scalability with sparse electrode configurations. This paper presents a data augmentation strategy for learning-based tactile reconstruction that amplifies the original single-frame signal measurement into 32 distinct, effective signal data for training. This approach supplements uncollected conditions of position information, resulting in more accurate and high-resolution tactile reconstructions. Data augmentation for EIT significantly reduces the required EIT measurements and achieves promising performance with even limited samples. Simulation results show that the proposed method improves the correlation coefficient by over 12% and reduces the relative error by over 21% under various noise levels. Furthermore, we demonstrate that a standard deep neural network (DNN) utilizing the proposed data augmentation reduces the required data down to 1/31 while achieving a similar tactile reconstruction quality. Real-world tests further validate the approach's effectiveness on a flexible EIT-based tactile sensor. These results could help address the challenge of training tactile sensing networks with limited available measurements, improving the accuracy and applicability of EIT-based tactile sensing systems.

In frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems, downlink channel state information (CSI) needs to be sent back to the base station (BS) by the users, which causes prohibitive feedback overhead. In this paper, we propose a lightweight and flexible deep learning-based CSI feedback approach by capitalizing on deep equilibrium models. Different from existing deep learning-based methods that stack multiple explicit layers, we propose an implicit equilibrium block to mimic the behavior of an infinite-depth neural network. In particular, the implicit equilibrium block is defined by a fixed-point iteration and the trainable parameters in different iterations are shared, which results in a lightweight model. Furthermore, the number of forward iterations can be adjusted according to users' computation capability, enabling a flexible accuracy-efficiency trade-off. Simulation results will show that the proposed design obtains a comparable performance as the benchmarks but with much-reduced complexity and permits an accuracy-efficiency trade-off at runtime.

The Marpa parser was intended to make the best results in the academic literature on Earley's algorithm available as a practical general parser. Earley-based parsers have had issues handling nullable symbols. Initially, we dealt with nullable symbols by following the approach in Aycock and Horspool's 2002 paper. This paper reports our experience with the approach in that paper, and the approach to handling nullables that we settled on in reaction to that experience.

Modelling highly multi-modal data is a challenging problem in machine learning. Most algorithms are based on maximizing the likelihood, which corresponds to the M(oment)-projection of the data distribution to the model distribution. The M-projection forces the model to average over modes it cannot represent. In contrast, the I(information)-projection ignores such modes in the data and concentrates on the modes the model can represent. Such behavior is appealing whenever we deal with highly multi-modal data where modelling single modes correctly is more important than covering all the modes. Despite this advantage, the I-projection is rarely used in practice due to the lack of algorithms that can efficiently optimize it based on data. In this work, we present a new algorithm called Expected Information Maximization (EIM) for computing the I-projection solely based on samples for general latent variable models, where we focus on Gaussian mixtures models and Gaussian mixtures of experts. Our approach applies a variational upper bound to the I-projection objective which decomposes the original objective into single objectives for each mixture component as well as for the coefficients, allowing an efficient optimization. Similar to GANs, our approach employs discriminators but uses a more stable optimization procedure, using a tight upper bound. We show that our algorithm is much more effective in computing the I-projection than recent GAN approaches and we illustrate the effectiveness of our approach for modelling multi-modal behavior on two pedestrian and traffic prediction datasets.

Prediction intervals are a valuable way of quantifying uncertainty in regression problems. Good prediction intervals should be both correct, containing the actual value between the lower and upper bound at least a target percentage of the time; and tight, having a small mean width of the bounds. Many prior techniques for generating prediction intervals make assumptions on the distribution of error, which causes them to work poorly for problems with asymmetric distributions. This paper presents Expanded Interval Minimization (EIM), a novel loss function for generating prediction intervals using neural networks. This loss function uses minibatch statistics to estimate the coverage and optimize the width of the prediction intervals. It does not make the same assumptions on the distributions of data and error as prior work. We compare to three published techniques and show EIM produces on average 1.37x tighter prediction intervals and in the worst case 1.06x tighter intervals across two large real-world datasets and varying coverage levels.