A method for training a speech-emotion recognition classifier under a continuous self-updating and re-trainable ASER machine learning model, wherein the training data is generated by: obtaining an utterance of a human speech source; processing the utterance in an emotion evaluation and rating process with normalization; extracting the features of the utterance; quantifying the feature attributes of the extracted features by labelling, tagging, and weighting the feature attributes, with their values assigned under measurable scales; and hashing the quantified feature attributes in a feature attribute hashing process to obtain hash values for creating a feature vector space. The run-time speech-emotion recognition comprising: extracting the features of an utterance; the trained recognition classifier recognizing the emotions and levels of intensity of the utterance units; and computing a quantified emotional state of the utterance by fusing recognized emotions and levels of intensity, and the quantified extracted feature attributes by their respective weightings.

A method for training a speech-emotion recognition classifier under a continuous self-updating and re-trainable ASER machine learning model, wherein the training data is generated by: obtaining an utterance of a human speech source; processing the utterance in an emotion evaluation and rating process with normalization; extracting the features of the utterance; quantifying the feature attributes of the extracted features by labelling, tagging, and weighting the feature attributes, with their values assigned under measurable scales; and hashing the quantified feature attributes in a feature attribute hashing process to obtain hash values for creating a feature vector space. The run-time speech-emotion recognition comprising: extracting the features of an utterance; the trained recognition classifier recognizing the emotions and levels of intensity of the utterance units; and computing a quantified emotional state of the utterance by fusing recognized emotions and levels of intensity, and the quantified extracted feature attributes by their respective weightings.

Systems and methods disclosed herein use a first machine learning architecture and a second machine learning architecture where the first machine learning architecture executes on a first processor and receives a first image representing a mouth of a user, determines user feedback for outputting to the user based on a first machine learning model, and outputs the user feedback for capturing a second image representing the mouth of the user. The second machine learning architecture executes on a second processor and receives the first image and the second image, and generates a 3D model of at least a portion of a dental arch of the user based on the first image and the second image where the 3D model is generated based on a second machine learning model of the second machine learning architecture.

A system and method for promoting, tracking, and assessing mental wellness. The method includes receiving an entry from a subject user, the entry including an input and a mood indicator, storing the entry in within a set of entries, the set including at least two entries received over a period of time, and determining a presence of at least one marker in the input of each entry within the set. The method further includes analyzing the set of entries for occurrences of markers or sequences of markers and alerting a supervisory user if the occurrences of markers or sequences of markers exceed a predetermined threshold. The method further includes associating contextual content from a supervisory user to an entry, the contextual content including a note, an attachment, a form, and/or a flag. The system includes a platform for accessing, managing, and storing data and analytics for implementing the method.

Systems and methods of discovering compounds with biological properties are provided. A first training dataset is obtained, including chemical structures and biological properties. Projections of compounds are obtained by projecting chemical structure information into a latent representation space using encoder weights. Compounds are classified by inputting projections into the classifier using classifier weights. The encoder and classifier are trained by comparing the classification of each compound to actual biological properties and updating the respective weights. A second training dataset is obtained including chemical structures. Projections of compounds are obtained by projecting chemical structure information into a latent representation space using encoder weights. Chemical structures are obtained by inputting projections into a decoder using decoder weights. The decoder is trained by comparing outputted and actual chemical structures and updating the respective weights. Candidate compounds not present in the first and second datasets are identified using the trained encoder, classifier, and decoder.

A method for training a machine learning model using information pertaining to characteristics of upload activity performed at one or more client devices includes generating first training input including (i) information identifying first amounts of data uploaded during a specified time interval for one or more of multiple application categories, and (ii) information identifying first locations external to a client device to which the first amounts of data are uploaded. The method includes generating a first target output that indicates whether the first amounts of data uploaded to the first locations correspond to malicious or non-malicious upload activity. The method includes providing the training data to train the machine learning model on (i) a set of training inputs including the first training input, and (ii) a set of target outputs including the first target output.

Some examples relate to classifying IoT malware at a network device. An example includes receiving, by a network device, network traffic from an Internet of Things (IoT) device. Network device may analyze network parameters from the network traffic with a machine learning model. In response to analyzing, network device may classify the network traffic into a category of malware activity. Network device may determine an effectiveness of network traffic classification by measuring a deviation of the network parameters from previously trained network parameters that were used for training the machine learning model. In response to a determination that the deviation of the network parameters from the trained network parameters is more than a pre-defined threshold, network device may generate an alert highlighting the deviation, which allows a user to perform a remedial action pertaining to the IoT device.

Methods and systems are provided for detecting and responding to dangerous road users. In some aspects, a process can include steps for receiving sensor data of a detected object from an autonomous vehicle, determining whether the detected object is exhibiting a dangerous attribute, generating output data based on the determining of whether the detected object is exhibiting the dangerous attribute, and updating a machine learning model based on the output data relating to the dangerous attribute.

A system includes a processor and a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform operations comprising displaying a prompt to a user of a mobile device on a display of a mobile device to capture an image representing at least a portion of a mouth of the user using a rear-facing camera of the mobile device, where the rear-facing camera is on an opposite side of the mobile device including the display. The operations further comprise controlling the rear-facing camera to enable the rear-facing camera to capture the image, receiving the image, and outputting, user feedback based on the image, where the user feedback is outputted on the display that is on the opposite side of the mobile device than the rear-facing camera.

System and methods enable vehicles to make ethical/empathetic driving decisions by using deep learning aided location intelligence. The systems and methods identify moral islands/complex driving scenarios where a complex ethical decision is required. A Generative Adversarial Network (GAN) is used to generate synthetic training data to capture varied ethically complex driving situations. Embodiments train a deep learning model (ETHNET) that is configured to output one or more driving decisions to be taken when a vehicle comes across an ethically complex driving situations in the real world.