Abstract: Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.

Abstract: Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution maps of spatio-temporal dynamical systems and approximating general black-box relationships between functional data. We propose a novel operator learning method, LOCA (Learning Operators with Coupled Attention), motivated from the attention mechanism. The input functions are mapped to a finite set of features which are then averaged with attention weights that depend on the output query locations. By coupling these attention weights together with an integral transform, LOCA is able to explicitly learn correlations in the target output functions, enabling us to approximate nonlinear operators even when the number of output function measurements is very small.

Abstract: Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.

Abstract: A method for simultaneous location and mapping (SLAM) includes receiving, by at least one processor, a set of sensor measurements from a movement sensor of a mobile robot and a set of images captured by a camera on the mobile robot as the mobile robot traverses an environment. The method includes, for each image of at least a subset of the set of images, extracting, by the at least one processor, a plurality of detected objects from the image. The method includes estimating, by the at least one processor, a trajectory of the mobile robot and a respective semantic label and position of each detected object within the environment using the sensor measurements and an expectation maximization (EM) algorithm.

Abstract: A method for simultaneous location and mapping (SLAM) includes receiving, by at least one processor, a set of sensor measurements from a movement sensor of a mobile robot and a set of images captured by a camera on the mobile robot as the mobile robot traverses an environment. The method includes, for each image of at least a subset of the set of images, extracting, by the at least one processor, a plurality of detected objects from the image. The method includes estimating, by the at least one processor, a trajectory of the mobile robot and a respective semantic label and position of each detected object within the environment using the sensor measurements and an expectation maximization (EM) algorithm.

Abstract: Light is examined utilizing a wide slit and a dispersion means such as a prism to produce two pairs of diverging beams separated by an intermediate converging beam of white light. The light emerging from the dispersion means impinges upon a narrow slit situated between the dispersion means and a point at which the intermediate beam of white light converges. In a monochrometer, the first pair of diverging beams comprise red and yellow rays and emanate from one side of the dispersion means and the second pair of diverging beams comprises blue and violet rays and emanate from the other side of the dispersion means. A narrow slit located between the dispersion means and a point at which the intermediate white beam converges passes rays of a single color, either red, yellow, blue or violet, to a second dispersion means and light emerging from the second dispersion means impinges upon a means for measuring the dispersion of rays passing through the narrow slit with respect to a reference point.