Abstract: Machine learning is used to classify a pleasantness of a sound emitted from a device. A plurality of pleasantness ratings from human jurors are received, each pleasantness rating corresponding to a respective one of a plurality of sounds emitted by one or more devices. Differences between each pleasantness rating and each of the other pleasantness ratings is determined via pairwise comparisons. These differences are converted into binary values based on which pleasantness rating is higher or lower in each comparison. Measurable sound qualities are received associated with the sounds. Second differences between each of the measurable sound qualities and every other of the plurality of measured sound qualities is determined in pairwise fashion. A classification model is trained to classify sound pleasantness by comparing the binary values with the second differences.

Abstract: Machine learning is used to predict a pleasantness of a sound emitted from a device. A plurality of pleasantness ratings from human jurors are received, each pleasantness rating corresponding to a respective one of a plurality of sounds emitted by one or more devices. A microphone system detects a plurality of measurable sound qualities (e.g., loudness, tonality, sharpness, etc.) of these rated sounds. A regression prediction model is trained based on the jury pleasantness ratings and the corresponding measurable sound qualities. Then, the microphone system detects measurable sound qualities of an unrated sound that has not been rated by the jury. The trained regression prediction model is executed on the measurable sound quality of the unrated sound to yield a predicted pleasantness of the unrated sound.

Abstract: Methods and systems of using a trained machine-learning model to perform root cause analysis on a manufacturing process. A pre-trained machine learning model is provided that is trained to predict measurements of non-faulty parts. The pre-trained model is trained on training measurement data regarding physical characteristics of manufactured parts as measured by a plurality of sensors at a plurality of manufacturing stations. With the trained model, then measurement data from the sensors is received regarding the manufactured part and the stations. This new set of measurement data is back propagated through the pre-trained model to determine a magnitude of absolute gradients of the new measurement data. The root cause is then identified based on this magnitude of absolute gradients. In other embodiments the root cause is identified based on losses determined between a set of predicted measurement data of a part using the model, and actual measurement data.

Abstract: A computer-implemented method includes receiving a combination recorded signals indicating current, voltage, vibrational, and sound information associated with a test device, generating a training data set utilizing the signals, wherein the training data set is sent to a machine learning model, and in response to meeting a convergence threshold of the machine learning model, outputting a trained model that outputs a prediction using the recorded signals from the combination. The prediction indicates a predicted signal characteristic. The method also includes comparing the prediction and signal associated with the test device to identify a prediction error associated with the device, and outputting a prediction analysis indicating information associated with at least the prediction error. The prediction analysis includes information indicative of a relationship between the device and its signals.

Abstract: A system includes a processor, wherein the processor is programmed to receive sound information and vibrational information from a device in a first environment, generate a training data set utilizing at least the vibrational information and a sound perception score associated with the corresponding sound of the vibrational information, wherein the training data set is fed into an un-trained machine learning model, in response to meeting a convergence threshold of the un-trained machine learning model, outputting a trained machine learning model, receive real-time vibrational information from the device in a second environment, and based on the real-time vibrational information as an input to the trained machine learning model, output a real-time sound perception score indicating characteristics associated with sound emitted from the device.

Abstract: A system includes a processor in communication with one or more sensors, wherein the processor is programmed to receive data including one or more of real-time current information, real-time voltage information, or real-time vibrational information from a run-time device, wherein the run-time device is an actuator or electric dive, and utilize a trained machine learning model and the data as an input to the trained machine learning model, output a sound prediction associated with estimated sound emitted from the run-time device.

Abstract: A system includes a processor in communication with one or more sensors. The processor is programmed to receiving, from the one or more sensors, vibrational information and sound information associated with the vibrational information from a test device, generating a training data set utilizing at least the vibrational data and the sound information associated with the vibrational data, wherein the training data set is sent to a machine learning model configured to output sound predictions, receiving real-time vibrational data from a run-time device running an actuator or electric dive emitting the real-time vibrational data, and based on the machine learning model and the real-time vibrational data, output a sound prediction indicating a purported sound emitted from the run-time device.

Abstract: A convolutional neural network system includes a sensor and a controller, wherein the controller is configured to receive an image from the sensor, divide the image into patches, each patch of size p, extract, via a first convolutional layer, a feature map having a number of channels based on a feature detector of size p, wherein the feature detector has a stride equal to size p, refine the feature map by alternatingly applying depth-wise convolutional layers and point-wise convolutional layers to obtain a refined feature map, wherein the number of channels in the feature map and the size of the feature map remains constant throughout all operations in the refinement; and output the refined feature map.

Abstract: A method includes, in response to at least one convergence criterion not being met: receiving a labeled dataset that includes a plurality of labeled samples; receiving an unlabeled dataset that includes a plurality of unlabeled samples; identifying a plurality of labeled-unlabeled sample pairs; applying a data augmentation transformation to each labeled sample and each corresponding unlabeled sample; computing, for each least one labeled-unlabeled sample pair, latent representation spaces using the machine learning model; generating, using the machine learning model, a label prediction for each unlabeled sample for each labeled-unlabeled sample pair; computing a loss function for each labeled-unlabeled sample pair of the plurality of labeled-unlabeled sample pairs based on respective latency representation spaces and respective label predictions; applying an optimization function to each respective loss function; and updating a weight value for each labeled-unlabeled sample pair of the plurality of labeled-un

Abstract: A method includes receiving a labeled dataset that includes a plurality of labeled samples and initially training the machine learning model using the labeled dataset. The method also includes receiving an unlabeled dataset that includes a plurality of unlabeled samples. The method also includes computing latent representation spaces for each respective sample of the plurality of labeled samples and each respective sample of the plurality of the unlabeled samples. The method also includes generating a k-nearest neighbor similarity graph based on the latent representation spaces, generating a combined similarity graph by augmenting the k-nearest neighbor similarity graph using an expert-derived similarity graph, and propagating, using the combined similarity graph, labels to each respective sample of the plurality of unlabeled samples.

Abstract: Methods and systems are disclosed for quantizing images using machine-learning. A plurality of input images are received from a sensor (e.g., a camera), wherein each input image includes a plurality of pixels. Utilizing an image-to-image machine-learning model, each pixel is assigned a new pixel color. Utilizing a mixer machine-learning model, each new pixel color is converted to one of a fixed number of colors to produce a plurality of quantized images, with each quantized image corresponding to one of the input images. A loss function is determined based on an alignment of each input image with its corresponding quantized image via a pre-trained reference machine-learning model. One or more parameters of the image-to-image machine-learning model and the mixer model are updated based on the loss function. The process repeats, with each iteration updating the parameters of the image-to-image machine-learning model and the mixer model, until convergence, resulting in trained models.

Abstract: A multimodal perception system for an autonomous vehicle includes a first sensor that is one of a video, RADAR, LIDAR, or ultrasound sensor, and a controller. The controller may be configured to, receive a first signal from a first sensor, a second signal from a second sensor, and a third signal from a third sensor, extract a first feature vector from the first signal, extract a second feature vector from the second signal, extract a third feature vector from the third signal, determine an odd-one-out vector from the first, second, and third feature vectors via an odd-one-out network of a machine learning network, based on inconsistent modality prediction, fuse the first, second, and third feature vectors and odd-one-out vector into a fused feature vector, output the fused feature vector, and control the autonomous vehicle based on the fused feature vector.

Abstract: Methods and systems of estimating an accuracy of a neural network on out-of-distribution data. In-distribution accuracies of a plurality of machine learning models trained with in-distribution data are determined. The plurality of machine learning models includes a first model, and a remainder of models. In-distribution agreement is determined between (i) an output of the first machine learning model executed with an in-distribution dataset and (ii) outputs of a remainder of the plurality of machine learning models executed with the in-distribution dataset. The machine learning models are also executed with an unlabeled out-of-distribution dataset, and an out-of-distribution agreement is determined. The in-distribution agreement is compared with the out-of-distribution agreement.

Abstract: Methods and systems for training a machine learning model with measurement data captured during a manufacturing process. Measurement data regarding a physical characteristic of a plurality of manufactured parts is received as measured by a plurality of sensors at various manufacturing stations. A time-series dynamics machine learning model encodes the measurement data into a latent space having a plurality of nodes. Each node is associated with the measurement data of one of the manufactured parts and at one of the manufacturing stations. A batch of the measurement data can be built, the batch include a first node and a first plurality of nodes immediately connected to the first node via first edges, and measured in time earlier than the first node. A prediction machine learning model can predict measurements of a first of the manufactured parts based on the latent space of the batch of nodes.

Abstract: Methods and systems are disclosed for generating training data for a machine learning model for better performance of the model. A source image is selected from an image database, along with a target image. An image segmenter is utilized with the source image to generate a source image segmentation mask having a foreground region and a background region. The same is performed with the target image to generate a target image segmentation mask having a foreground region and a background region. Foregrounds and backgrounds of the source image and target image are determined based on the masks. The target image foreground is removed from the target image, and the source image foreground is inserted into the target image to create an augmented image having the source image foreground and the target image background. The training data for the machine learning model is updated to include this augmented image.

Abstract: Performing semantic segmentation in an absence of labels for one or more semantic classes is provided. One or more weak predictors are utilized to obtain label proposals of novel classes for an original dataset for which at least a subset of sematic classes are unlabeled classes. The label proposals are merged with ground truth of the original dataset to generate a merged dataset, the ground truth defining labeled classes of portions of the original dataset. A machine learning model is trained using the merged dataset. The machine learning model is utilized for performing semantic segmentation on image data.

Abstract: Methods and systems are disclosed for quantizing images using machine-learning. A plurality of input images are received from a sensor (e.g., a camera), wherein each input image includes a plurality of pixels. Utilizing an image-to-image machine-learning model, each pixel is assigned a new pixel color. Utilizing a mixer machine-learning model, each new pixel color is converted to one of a fixed number of colors to produce a plurality of quantized images, with each quantized image corresponding to one of the input images. A loss function is determined based on an alignment of each input image with its corresponding quantized image via a pre-trained reference machine-learning model. One or more parameters of the image-to-image machine-learning model and the mixer model are updated based on the loss function. The process repeats, with each iteration updating the parameters of the image-to-image machine-learning model and the mixer model, until convergence, resulting in trained models.

Abstract: A computational method for training a classifier. The method includes receiving a training data set comprised of pairs of training input and output signals, the classifier parameterized by parameters, a class-dependent allowed perturbation for each of at least two different classes and including a first class-dependent allowed perturbation for a first class and a second class-dependent allowed perturbation for a second class, and a loss function. The method further includes partitioning the training data set into a first subset labelled with a first label and a second subset labelled with a second label. The method also includes calculating a first loss in response to the first subset and the first class-dependent allowed perturbation and a second loss calculated in response to the second subset and the second class-dependent allowed perturbation. The method also includes updating the parameters in response to the first and second losses to obtain updated parameters.

Abstract: A convolutional neural network system includes a sensor and a controller, wherein the controller is configured to receive an image from the sensor, divide the image into patches, each patch of size p, extract, via a first convolutional layer, a feature map having a number of channels based on a feature detector of size p, wherein the feature detector has a stride equal to size p, refine the feature map by alternatingly applying depth-wise convolutional layers and point-wise convolutional layers to obtain a refined feature map, wherein the number of channels in the feature map and the size of the feature map remains constant throughout all operations in the refinement; and output the refined feature map.

Abstract: A system and method is disclosed for labeling an unlabeled dataset, with a labeling budget constraint and noisy oracles (i.e. noisy labels provided by annotator), using a noisy labeled dataset from another domain or application. The system and method combine active learning with noisy labels and active learning with domain adaptation to enhance classification performance.