Techniques for using a federated learning framework to update machine learning models for spoken language understanding (SLU) system are described. The system determines which labeled data is needed to update the models based on the models generating an undesired response to an input. The system identifies users to solicit labeled data from, and sends a request to a user device to speak an input. The device generates labeled data using the spoken input, and updates the on-device models using the spoken input and the labeled data. The updated model data is provided to the system to enable the system to update the system-level (global) models.

Provided is a detection and classification system and method for small unmanned aircraft systems (sUAS). The system and method detect and classify multiple simultaneous heterogeneous RC transmitters/sUAS downlinks from the RF signature using Object Detection Deep Convolutional Neural Networks (DCNNs). The method further utilizes not only passive RF, but may also utilize Electro Optic/Infrared (EO/IR), radar and acoustic sensors as well, with a fusion of the individual sensor classifications. Detection and classification with Identification Friend or Foe (IFF) of individual sUAS in a swarm, multi-modal approach for high confidence classification, decision, and implementation on a low C-SWaP (cost, size, weight and power) NVIDIA Jetson TX2 embedded AI platform is achieved.

Aspects of the invention include detecting an error alert from a target computer system. In response to detecting the error alert, performance data is then retrieved from the target computer system. A gated recurrent unit (GRU) neural network is used to generate a prediction of a root cause of the error alert based on the performance data. The weights of a reset gate of the GRU neural network are adjusted based on received feedback of the prediction.

Techniques for speech processing using a deep neural network (DNN) based acoustic model front-end are described. A new modeling approach directly models multi-channel audio data received from a microphone array using a first model (e.g., multi-geometry/multi-channel DNN) that is trained using a plurality of microphone array geometries. Thus, the first model may receive a variable number of microphone channels, generate multiple outputs using multiple microphone array geometries, and select the best output as a first feature vector that may be used similarly to beamformed features generated by an acoustic beamformer. A second model (e.g., feature extraction DNN) processes the first feature vector and transforms it to a second feature vector having a lower dimensional representation. A third model (e.g., classification DNN) processes the second feature vector to perform acoustic unit classification and generate text data. The DNN front-end enables improved performance despite a reduction in microphones.

An example method of document classification comprises: detecting a set of keypoints in an input image; generating a set of keypoint vectors, wherein each keypoint vector of the set of keypoint vectors is associated with a corresponding keypoint of the set of keypoints; extracting a feature map from the input image; producing a combination of the set of keypoint vectors with the feature map; transforming the combination into a set of keypoint mapping vectors according to a predefined mapping scheme; estimating, based on the set of keypoint mapping vectors, a plurality of importance factors associated with the set of keypoints; and classifying the input image based on the set of keypoints and the plurality of importance factors.

A machine learning prediction system can analyze a dataset of users with self-reported symptoms and associated data from a wearable device to impact measure the impact of an acute health condition (such as the flu) at the population level. The machine learning prediction system can train a machine learning model to recognize individual acute health condition patterns based on differences in user activity with respect to the characteristics of determined baseline periods. For example, per-individual normalized change with respect to baseline aggregated at the population level can be used to determine individual acute health condition patterns and predict the onset of certain acute health conditions using a trained machine learning model. In response to predictions, the machine learning prediction system can take interventions to manage the impact of a predicted acute health condition on an individual.

The present invention relates to an artificial intelligence method and system for event predication, comprising: receiving, user messages, user activity data, event data, user identification information and transaction data; scraping webpages for additional event data; applying a natural language processing module to process the event data; constructing a training data set using the processed event data; constructing user preferences from the user messages, the user activity data, the user identification information and the transaction data; training a predictive model using the training data set to determine at least one upcoming event predictions determining to display the at least one event predictions based on the user profile; if it is determined to display one of the at least one event predictions, generating a graphical user interface display with a calendar depicting the at least one event prediction; and presenting the graphical user interface display to the user.

A pedestrian tracking system includes: a buffer or a memory configured to store a trajectory sequence of a pedestrian; a step attention module and a control module. The step attention module iteratively performs a step attention process to predict states of the pedestrian. Each iteration of the step attention process includes the step attention module: learning the stored trajectory sequence to provide time-dependent hidden states, reshaping each of the time-dependent hidden states to provide two-dimensional tensors; condensing the two-dimensional tensors via convolutional networks to provide convolutional sequences; capturing global information of the convolutional sequences to output a set of trajectory patterns represented by a new sequence of tensors; learning time-related patterns in the new sequence and decoding the new sequence to provide one or more of the states of the pedestrian; and modifying the stored trajectory sequence to include the predicted one or more of the states of the pedestrian.

A long short-term memory (LSTM) model-based disease prediction method and apparatus, a computer device, and a storage medium are provided. The method includes: obtaining first medical data of a target object and second medical data of an associated object; inputting the first medical data and the second medical data into a first LSTM network in the LSTM model, to obtain a hidden state vector sequence in the first LSTM network; inputting the hidden state vector sequence into a second LSTM network for operation, to obtain a disease prediction result; selecting a predicted disease with an incidence rate higher than a preset threshold, and recording the predicted disease as a designated disease, and obtaining, based on a preset disease association network, an associated disease directly connected to the designated disease; and outputting the disease prediction result and the associated disease, thereby improving the prediction accuracy.

A long short-term memory (LSTM) model-based disease prediction method and apparatus, a computer device, and a storage medium are provided. The method includes: obtaining first medical data of a target object and second medical data of an associated object; inputting the first medical data and the second medical data into a first LSTM network in the LSTM model, to obtain a hidden state vector sequence in the first LSTM network; inputting the hidden state vector sequence into a second LSTM network for operation, to obtain a disease prediction result; selecting a predicted disease with an incidence rate higher than a preset threshold, and recording the predicted disease as a designated disease, and obtaining, based on a preset disease association network, an associated disease directly connected to the designated disease; and outputting the disease prediction result and the associated disease, thereby improving the prediction accuracy.