A system comprising a plurality of neuromuscular sensors, each of which is configured to record a time-series of neuromuscular signals from a surface of a user's body; and at least one computer hardware processor programmed to perform: applying a source separation technique to the time series of neuromuscular signals recorded by the plurality of neuromuscular sensors to obtain a plurality of neuromuscular source signals and corresponding mixing information; providing features, obtained from the plurality of neuromuscular source signals and/or the corresponding mixing information, as input to a trained statistical classifier and obtaining corresponding output; and identifying, based on the output of the trained statistical classifier, and for each of one or more of the plurality of neuromuscular source signals, an associated set of one or more biological structures.

One embodiment provides a method comprising receiving training data and experts' intuition, training a machine learning model based on the training data, predicting a class label for a new data input based on the machine learning model, estimating a degree of similarity of a target attribute of the new data input relative to the training data, and selectively applying a correction to the class label for the new data input based on the degree of similarity prior to providing the class label as an output. The target attribute is an attribute related to the experts' intuition.

Computer systems and associated methods are disclosed to implement a model development environment (MDE) that allows a team of users to perform iterative model experiments to develop machine learning (ML) media models. In embodiments, the MDE implements a media data management interface that allows users to annotate and manage training data for models. In embodiments, the MDE implements a model experimentation interface that allows users to configure and run model experiments, which include a training run and a test run of a model. In embodiments, the MDE implements a model diagnosis interface that displays the model's performance metrics and allows users to visually inspect media samples that were used during the model experiment to determine corrective actions to improve model performance for later iterations of experiments. In embodiments, the MDE allows different types of users to collaborate on a series of model experiments to build an optimal media model.

A system may be configured to perform a method for generating customized training. The system may receive first user interaction data associated with a user. The system may determine, using a machine learning model (MLM), whether the first user interaction data exceeds a predetermined threshold. Based on such determination, the system may assign a training module to the user. The system may access a user profile associated with the user, the user profile comprising a plurality of training modules. The system may generate a training plan based on the training module and the plurality of training modules. The system may receive second user interaction data associated with the user, and may determine an efficacy level of the training plan based on the second user interaction data. The system may dynamically update the training plan based on the efficacy level, and may dynamically display the training plan in the user profile.

Disclosed herein are techniques and systems for classifying and moderating text using a machine learning approach that is based on a word embedding process. For instance, word embedding vectors may be used to determine clusters of associated text (e.g., similar words) from a corpus of comments maintained by a remote computing system. The remote computing system may then identify, within the corpus of comments, a subset of comments that include text from a given cluster that was determined, from human labeling input, to include a particular type of word or speech. Using this information, the corpus of comments may be labeled with one of multiple class labels. A machine learning model(s) may be trained to classify text as one of the multiple class labels using a sampled set of labeled comments as training data. At runtime, text can be moderated based on its class label.

A segmentation neural network is extended to provide classification at the segment level. An input image of a document is received and processed, utilizing a segmentation neural network, to detect pixels having a signature feature type. A signature heatmap of the input image can be generated based on the pixels in the input image having the signature feature type. The segmentation neural network is extended from here to further process the signature heatmap by morphing it to include noise surrounding an object of interest. This creates a signature region that can have no defined shape or size. The morphed heatmap acts as a mask so that each signature region or object in the input image can be detected as a segment. Based on this segment-level detection, the input image is classified. The classification result can be provided as feedback to a machine learning framework to refine training.

Disclosed are systems, methods, and non-transitory computer-readable media for automatic image selection for online product catalogs. An image selection system gathers feature data for images of an item included in listings posted to an online marketplace. The image selection system uses the feature data as input in a machine learning model to determine probability scores indicating an estimated probability that each image is suitable to represent the item. The machine learning model is trained based on a set of training images of the item that have been labeled to indicate whether they are suitable to represent the image. The image selection system compares the probability scores and selects an image to represent the item as a stock image based on the comparison.

Improved (e.g., high-throughput, low-noise, and/or low-artifact) X-ray Microscopy images are achieved using a deep neural network trained via an accessible workflow. The workflow involves selection of a desired improvement factor (x), which is used to automatically partition supplied data into two or more subsets for neural network training. The neural network is trained by generating reconstructed volumes for each of the subsets. The neural network can be trained to take projection images or reconstructed volumes as input and output improved projection images or improved reconstructed volumes as output, respectively. Once trained, the neural network can be applied to the training data and/or subsequent data—optionally collected at a higher throughput—to ultimately achieve improved de-noising and/or other artifact reduction in the reconstructed volume.

An apparatus includes a processor and a memory that stores a deep Q reinforcement learning (DQN) algorithm configured to generate an action, based on a state. Each action includes a recommendation associated with a computational resource. Each state identifies at least a role within an enterprise. The processor receives information associated with a first user, including an identification of a first role assigned to the user and computational resource information associated with the user. The processor applies the DQN algorithm to a first state, which includes an identification of the first role, to generate a first action, which includes a recommendation associated with a first computational resource. In response to applying the DQN algorithm, the processor generates a reward value based on the alignment between the first recommendation and the computational resource information associated with the first user. The processor uses the reward value to update the DQN algorithm.

Systems and methods for training a machine learning (ML) ranking model to rank genealogy hints are described herein. One method includes retrieving a plurality of genealogy hints for a target person, where each of the plurality of genealogy hints corresponds to a genealogy item and has a hint type of a plurality of hint types. The method includes generating, for each of the plurality of genealogy hints, a feature vector having a plurality of feature values, the feature vector being included in a plurality of feature vectors. The method includes extending each of the plurality of feature vectors by at least one additional feature value based on the number of features of one or more other hint types of the plurality of hint types. The method includes training the ML ranking model using the extended plurality of feature vectors and user-provided labels.