Abstract: Methods, systems, and computer programs are presented for generating multimodal content utilizing multimodal templates. One method includes presenting, in a user interface (UI), a template-selection option with one or more templates. Each template comprises a sequence of operations, where each operation comprises a prompt for creating items using generative artificial intelligence (GAI) tools. Further, each operation in the template is multimodal to be configurable to create text and configurable to create one or more images. The method further includes detecting a selection of a template in the UI. For each operation in the selected template, perform operations comprising: presenting, in the UI, the prompt associated with the operation; in response to receiving an input for the prompt, selecting a GAI tool based on a mode of the operation; providing the input to the selected GAI tool to generate the item; and presenting, in the UI, the generated item.

Abstract: A system, apparatus and method for processing observational data for training a neural network model for use by a neural network. Observational data is parsed into raw data and metadata components and then stored separately on a raw data storage system and a metadata storage system, respectively. A digital fingerprint may be generated and assigned to the raw data and the metadata, used to verify the integrity of the data. When it is desired to train a neural network model, a DETL query is generated and used to identify any raw data that may be relevant to training the neural network model. The DETL query is processed by the metadata storage system to match any metadata to search terms in the DETL which, in turn, identifies raw data stored in the raw data storage system. The identified raw data is used to train the neural network model, and a updated neural network model is produced.

Abstract: A method and a system for maintaining network integrity for incrementally training machine learning (ML) models at edge devices is provided. The method includes registering, by a certifying node, one or more edge devices with a peer to peer network. Upon registration, an incrementally updated ML model is received from a first registered device at the certifying node. The certifying node accepts the incrementally updated ML model if a contribution of the first edge device is within a predetermined threshold, and else rejects the updated ML model if the contribution is beyond the predetermined threshold. Limiting the contribution by each edge device enables prevention of skew by any of the edge devices at the certifying node. Upon accepting the updated ML model, the certifying node certifies the updated ML model and transfers the certified ML model to one or more other edge devices in the peer to peer network.

Abstract: Systems and methods are provided for suggesting actions for selected text based on content displayed on a mobile device. An example method can include converting a selection made via a display device into a query, providing the query to an action suggestion model that is trained to predict an action given a query, each action being associated with a mobile application, receiving one or more predicted actions, and initiating display of the one or more predicted actions on the display device. Another example method can include identifying, from search records, queries where a website is highly ranked, the website being one of a plurality of websites in a mapping of websites to mobile applications. The method can also include generating positive training examples for an action suggestion model from the identified queries, and training the action suggestion model using the positive training examples.

Abstract: Embodiments are directed to a machine learning engine that determines training documents and validation documents from a plurality of documents. The machine learning engine may determine attributes associated with the documents. In response to receiving a request to predict attribute values of a selected document the machine learning engine may train a plurality of ML models to predict the attribute values based on the training documents and the attributes and associate the trained ML models with an accuracy score. The machine learning engine may determine candidate ML models from the trained ML models based on the training accuracy scores. The machine learning engine may evaluate and rank the candidate ML models based on the request and the validation documents. The machine learning engine may generate confirmed ML models based on the ranked candidate ML models such that the confirmed ML models may answer the request.

Abstract: A perception model is trained to classify inputs in relation to a discrete set of leaf node classes. A hierarchical classification tree encodes hierarchical relationships between the leaf node classes. A training loss function is dependent on a classification score for a given training input a its ground truth leaf node class of the training input, but also classification scores for at least some others of the leaf node classes, with the classification scores of the other leaf node classes weighted in dependence on their hierarchical relationship to the ground truth leaf node class within the hierarchical classification tree.

Abstract: A system and method for iteratively updating a parameter according to a gradient descent algorithm. In a given nth iteration of the method, one or more processors may determine a gradient value of a gradient vector of the parameter in a first dimension, determine a product value based at least in part on a sum of (i) the product value determined in an n?1th iteration and (ii) a product of the determined gradient value and a learning rate of the gradient descent algorithm, determine an updated parameter value according to a function including the product value, and update the parameter to equal the updated parameter value.

Abstract: A method for determining machine learning training parameters is disclosed. The method can include a processor receiving a first input. The processor may receive a first response to the first input, determine a first intent, and identify a first action. The processor can then determine first trainable parameter(s) and determine whether the first trainable parameter(s) is negative or positive. Further, the processor can update a training algorithm based on the first trainable parameter(s). The processor can then receive a second input and determine a second intent for the second input. The processor can also determine a second action for the second intent and transmit the second action to a user. The processor can then determine second trainable parameter(s) and determine whether the second trainable parameter(s) is positive or negative. Finally, the processor can further update the training algorithm based on the second trainable parameter(s).

Abstract: Systems and methods for selecting a neural network for a machine learning problem are disclosed. A method includes accessing an input matrix. The method includes accessing a machine learning problem space associated with a machine learning problem and multiple untrained candidate neural networks for solving the machine learning problem. The method includes computing, for each untrained candidate neural network, at least one expressivity measure capturing an expressivity of the candidate neural network with respect to the machine learning problem. The method includes computing, for each untrained candidate neural network, at least one trainability measure capturing a trainability of the candidate neural network with respect to the machine learning problem. The method includes selecting, based on the at least one expressivity measure and the at least one trainability measure, at least one candidate neural network for solving the machine learning problem.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating sequences of predicted observations, for example images. In one aspect, a system comprises a controller recurrent neural network, and a decoder neural network to process a set of latent variables to generate an observation. An external memory and a memory interface subsystem is configured to, for each of a plurality of time steps, receive an updated hidden state from the controller, generate a memory context vector by reading data from the external memory using the updated hidden state, determine a set of latent variables from the memory context vector, generate a predicted observation by providing the set of latent variables to the decoder neural network, write data to the external memory using the latent variables, the updated hidden state, or both, and generate a controller input for a subsequent time step from the latent variables.

Abstract: Disclosed herein are system, method, and computer program product embodiments for detecting erroneous data. In an embodiment, a data monitoring system may store an initial dataset. The data monitoring system may analyze the initial dataset to generate rules associated with the initial dataset. The data monitoring system may receive a new data entry from a client device intended to be associated with the initial dataset. The data monitoring system may compare the new data entry to the previously determined rules to determine if the new data entry complies. If so, the data monitoring system may store the new data entry. If not, the data monitoring system may generate an alert, requesting a confirmation that the noncompliant data entry is correct. If the noncompliant data is confirmed as correct, the data monitoring system may store the new data entry and update the rules associated with the updated dataset.

Abstract: In one embodiment, a first deep fusion reasoning engine (DFRE) agent in a network receives first sensor data from a first set of one or more sensors in the network. The first DFRE agent translates the first sensor data into symbolic data. The first DFRE agent applies, using a symbolic knowledge base maintained by the first DFRE agent, symbolic reasoning to the symbolic data to make an inference regarding the first sensor data. The first DFRE agent updates, based on the inference regarding the first sensor data, the knowledge base. The first DFRE agent propagates the inference to one or more other DFRE agents in the network.

Abstract: By formulizing a specific company's internal knowledge and terminology, the ontology programming accounts for linguistic meaning to surface relevant and important content for analysis. The ontology is built on the premise that meaningful terms are detected in the corpus and then classified according to specific semantic concepts, or entities. Once the main terms are defined, direct relations or linkages can be formed between these terms and their associated entities. Then, the relations are grouped into themes, which are groups or abstracts that contain synonymous relations. The disclosed ontology programming adapts to the language used in a specific domain, including linguistic patterns and properties, such as word order, relationships between terms, and syntactical variations. The ontology programming automatically trains itself to understand the domain or environment of the communication data by processing and analyzing a defined corpus of communication data.

Abstract: A technology is described for automating deployment of a machine learning model. An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.

Abstract: A method for assessing movement of a body portion includes, via one or more machine learning models, analyzing a sensor signal indicative of movement of the body portion to determine a movement of the body portion; determining a sensor confidence level based, at least in part, on a characteristic of the sensor signal; receiving a series of images indicative of movement of the body portion; measuring an angle of movement of the body portion; determining a vision confidence level based, at least in part, on a quality of an identification the body portion; selecting the sensor signal, the measured angle of movement, or a combination thereof as an input into a machine learning model based on the sensor confidence level and the vision confidence level, respectively; analyzing the input to determine a movement pattern of the body portion; and outputting the movement pattern to a user.

Abstract: A method optimizes a training of a machine learning system. A conflict detection system discovers a conflict between a first training data and a second training data for a machine learning system, where the first training data and the second training data are ground truths that describe a same type of entity, and where the first training data and the second training data have different labels. In response to discovering the conflict between the first training data and the second training data for the machine learning system, an oracle adjusts the different labels of the first training data and the second training data. The machine learning system is then trained using the first training data and the second training data with the adjusted labels.

Abstract: Systems, methods, and articles of manufacture for learning design policies based on user interactions. One example includes determining a first task for an environment, receiving data from a plurality of data sources, determining a first time step associated with the received data, determining a plurality of candidate actions for the determined first time step, computing a respective probability value of each candidate action achieving the first task at the first time step based on a first machine learning (ML) model, determining that a first candidate action has a greater probability value for achieving the first task at the first time step relative to the remaining plurality of candidate actions, determining that the first candidate action has not been implemented in the environment at the first time step, and generating an indication specifying to implement the first candidate action as part of a policy to achieve the first task.

Abstract: Aspects described herein may provide an interface and/or search functionality for a dealership to determine vehicles a customer is most likely to purchase. A recommender system may generate vehicle recommendations for a dealership to sell to a customer based on customer information, vehicle information, and dealership information. Machine learning may be used to generate the recommendations. The recommendations may be based on the vehicle preferences of a customer.

Abstract: An abduction apparatus 1 includes: a probability calculation unit 2 configured to, with respect to each of candidate hypotheses generated using observation information and knowledge information, calculate a probability that the candidate hypothesis holds true as an explanation of the observation information; and a reward selection unit 3 configured to, when the candidate hypothesis holds true, select a reward value regarding the candidate hypothesis that has held true by referring to reward definition information in which a condition that the candidate hypothesis holds true is associated with the reward value.

Abstract: A system and method include input of data records to a first trained predictive model to obtain a predicted value associated with each input data record. A model region is then associated with each of the input data records based on the first trained predictive model, the input data records and the predicted values. Enhanced input data records are generated by, for each model region, adding derived values of engineered features associated with the model region to input data records associated with the model region and default values of the engineered features associated with the model region to input training records not associated with the model region. The enhanced input data records are input to a second trained predictive model to obtain an enhanced predicted value associated with each input data record.