Abstract: Systems and methods that use geospatial data to train machine learning models to make predictions based on the geospatial data, for example for use in precision agriculture. A database is created that includes agricultural geospatial data acquired from two or more data sources. Using the spatial and temporal extent of response data, a training vector and a training feature matrix are then generated using a data systematic approach to engineer a virtually infinite number of training features derived from the database. A plurality of machine learning models are then trained using the training vector and the training feature matrix, with each one of the trained machine learning models generating a test result. At least one of the trained machine learning models is chosen to create predictions using new data at the spatial and temporal extent of interest. An output is created using the prediction(s) on the new data.

Abstract: The systems and methods disclosed herein receive alphanumeric characters defining operative boundaries for expected model use cases, along with operational data. The expected model use cases share common attributes, which are used by a first AI model to construct observed model use cases from the operational data. Each observed model use case includes features such as a text-based description, expected input and output, AI model(s) generating the expected output from the input, and/or data supporting the AI models. For each observed model use case, a second AI model maps the alphanumeric characters and features to a risk category, selecting from multiple risk categories based on the level of risk associated with the features. The system identifies criteria for the observed model use case within the alphanumeric characters and generates gaps by comparing the criteria with the features of the observed model use case.

Abstract: Various embodiments of the present disclosure describe data evaluation techniques that leverage a graph-based machine learning model to evaluate a knowledge graph. The techniques include using a target graph model to generate a predictive representation for a graph node of a graph training dataset. The techniques include using a feature prediction model to generate predicted feature values for the graph node based on the predictive representation. The techniques include generating a data evaluation score for the graph training dataset based on the predicted feature values. The techniques include using the target graph model to generate a predictive output for the graph node based on the predictive representation and then generating an evaluation output for the target graph model based on the evaluation score and the predictive output.

Abstract: In an embodiment a method for classification of a decision tree ensemble include saving of threshold values representative of decision trees in the decision tree ensemble into one group per feature to be classified, sorting of the threshold values of a group according to a threshold index, conducting a node comparison of the threshold values of a corresponding group of threshold values, outputting a rank as a result of the node comparison, wherein the rank represents a encoded address to representative of the threshold value and determining a class of the features to be classified as a function of ranks.

Abstract: The systems and methods disclosed herein receives, from a computing device, operational data indicating software or hardware assets used on informational assets, and obtains set of alphanumeric characters defining operative boundaries for expected system assets, which include a set of common attributes. Using the set of attributes, a first set of AI models determines observed system assets from the operational data, each with specific features. A second set of AI models associates each information asset with the corresponding observed system assets. For each observed system asset, a third set of AI models identifies criteria within the alphanumeric characters, compares the criteria with the asset's features to identify gaps, and generates actions to ensure the observed system asset meets the identified criteria.

Abstract: In some examples, special-purpose machines are provided that facilitate smart copy optimization in a network service or publication system, including software-configured computerized variants of such special-purpose machines and improvements to such variants, and to the technologies by which such special-purpose machines become improved compared to other special-purpose machines that facilitate adding the new features. Such technologies can include special artificial-intelligence (AI), machine-learning (ML), and natural-language-processing (NLP) techniques.

Abstract: Methods and systems are described herein for facilitating segmentation of training data using measures of statistical dispersion (e.g., Gini impurities) of dataset features. The system determines, from a training dataset, a target feature and candidate features. The system determines, for the target feature in relation to each candidate feature, first Gini impurities. The system selects a first and second feature having the lowest first Gini impurities. The system determines, for the target feature in relation to a first combination of the first and second features, a second Gini impurity. If the second Gini impurity does not satisfy a threshold, the system selects a third feature having the next lowest first Gini impurity and determines a third Gini impurity for a second combination of the first, second, and third features. If the third Gini impurity satisfies the threshold, the system trains a model using the target, first, second, and third features.

Abstract: The systems and methods disclosed herein generate responses using data retrieved in accordance with chunk-level access controls. An output generation request is received via a computing device and includes (1) an input with instructions to generate an output and (2) an access control metadata set indicating the degree of access to a content set within a vector database for the user associated with the request. A vector representation set of data chunks that are associated with generating the output is selected by comparing the vector representation of the input with corresponding vector representations of data chunks in the content set. Using a first artificial intelligence (AI) model set, the data chunk set is filtered to generate a subset in accordance with the access control metadata set. A second AI model set (same or different) is used to generate a response to the input based on the data chunk subset.

Abstract: Methods, systems, and apparatus for gradient-based quantum assisted Hamiltonian learning. In one aspect, a method includes obtaining, by a classical processor, multiple experimental data points, wherein each experimental data point is generated according to a Hamiltonian comprising parameters with unknown values; learning, by the classical processor, values of the parameters, comprising iteratively adjusting, by the classical processor and until predetermined completion criteria are met, estimated values of the parameters to minimize a cost function, wherein the cost function is dependent on the multiple experimental data points and at each iteration derivatives of the cost function with respect to respective estimated values of the parameters for the previous iteration are computed using a quantum computer.

Abstract: Aspects of the present disclosure relate to optimized generative machine learning systems. Embodiments include a generative machine learning model that comprises multiple sets of hidden decoder layers. In certain embodiments, a first set of decoder layers having a relatively small number of synaptic weights is used to generate reasoning steps for the model. The second set of decoder layers may have a larger number of synaptic weights than the first set, and the second set may be used to generate tokens of the response based on the reasoning steps. In some embodiments, each set of decoder layers comprise a plurality of neurons organized in an array, wherein each neuron comprises a register, a microprocessor, and at least one input. The neurons may be connected using synaptic circuitry.

Abstract: Systems and methods for monitoring and assessing crop health and performance can provide rapid screening of individual plants. The systems and methods have an automated component, and rely primarily on the detection and interpretation of plant-based signals to provide information about crop health. In some cases knowledge from human experts is captured and integrated into the automated crop monitoring systems and methods. Predictive models can also be developed and used to predict future health of plants in a crop.

Abstract: An interactive multimedia with multiple levels and a method for designing the interactive multimedia are provided. The interactive multimedia includes: a first level program, providing at least one first level interactive activity to determine one of multiple lines for the user to proceed from a first level to a next level; and a second level program, providing at least one second level interactive activity to determine one of multiple lines for the user to proceed from the second level to a next level. The levels and the lines of the interactive multimedia are designed at least partially based on a decision tree generated by a machine learning technique with a source data including predictor variables indicating attributes of respondents and a target variable indicating related outcomes of the respondents.

Abstract: A method and a system for improving classification of data samples, which may be considered as class outliers, are claimed. The method includes inferring a pretrained classifying ML-based model on the incoming data sample, to assign a particular class of a plurality of classes thereto; calculating a similarity metric value representing a degree of similarity between the incoming data sample and one or more previously classified data samples of the particular class; and validating assignment of the particular class to the incoming data sample, based on the calculated similarity metric value.

Abstract: Disclosed herein is a computing platform configured to (i) for a deep-learning AI model, determine a respective fairness-importance score of a respective parameter for at least a subset of the deep-learning AI model's parameters that quantifies how much the respective parameter influences generating fair predictions across a plurality of demographic groups, (ii) carry out an optimization process that produces and evaluates different quantized versions of the deep-learning AI model, (iii) based on the optimization process, select a given quantized version of the deep-learning AI model for deployment, (iv) fine-tune the given quantized version of the deep-learning AI model, and after fine-tuning the given quantized version of the deep-learning AI model, deploying the given quantized version of the deep-learning AI model.

Abstract: A method of forming an anomaly detection monitor includes obtaining data samples of operations performed on an application by a plurality of users and detecting, by a processor, anomalous behavior associated with a target user of the plurality of users with respect to the application based on a portion of the data samples associated with the target user and a portion of the data samples associated with a second user of the plurality of users, different from the target user.

Abstract: A student model may be trained in two stages by using two teacher models, respectively. The first teacher model has been trained with a pretraining dataset. The second teacher model has been trained with a training dataset that is specific to a task to be performed by the student model. In the first stage, the student model may be generated based on a structure of the first teacher model. Internal parameters of the student model are adjusted through a pretraining process based on the first teacher model and the pretraining dataset. Weights of the student model may be pruned during the pretraining process. In the second stage, a sparsity mask is generated for the student model to lock the sparsity pattern generated from the first stage. Further, some of the internal parameters of the student model are modified based on the second teacher model and the training dataset.

Abstract: An apparatus and method for efficiently creating less computationally intensive nodes for a neural network. In various implementations, a computing system includes a memory that stores multiple input data values for training a neural network, and a processor. Rather than determine a bit width P of an integer accumulator of a node of the neural network based on bit widths of the input data values and corresponding weight values, the processor selects the bit width P during training. The processor adjusts the magnitudes of the weight values during iterative stages of training the node such that an L1 norm value of the weight values of the node does not exceed a corresponding weight magnitude limit.

Abstract: Generally discussed herein are devices, systems, and methods for machine learning (ML) modeling of a system that operates on a multivector object. A method includes receiving, by an ML model, the multivector object as an input that represents a state of the multivector system. The method includes operating, by the ML model and using a Clifford layer that includes neurons that implement a multivector kernel, on the multivector input to generate a multivector output that represents the state of the multivector system responsive to the multivector input.

Abstract: A neural network system and an operation method for a neural network system are provided. The neural network system includes at least one edge device and a server. Each edge device stores a neural network architecture. The neural network architecture includes at least one operator and a model identifier, and the at least one operator of the neural network architecture stored in the each edge device includes an operator identifier. The server is connected to the each edge device. The each edge device is configured to, upon being powered on, transmit the operator identifier of each operator to the server to request the server to return parameters for the each operator; receive the parameters of the each operator and combine the parameters of the each operator with the neural network architecture to obtain a neural network model; and execute a predetermined task based on the neural network model.

Abstract: A method for automated therapy discovery includes: accessing a corpus of scientific publications; compiling a population of semantic concepts from the corpus of scientific publications into a vector space model; deriving domains of concepts in the vector space model based on proximity to domain descriptors in the vector space model; deriving association scores and action characteristics between connected concepts, based on proximity and action descriptors in the vector space model; generating a semantic network; receiving a query for a target concept and a target domain at a research portal; isolating a set of edges between a target node and a subset of nodes; identifying subsets of concepts along the set of edges; generating hypotheses for directions and magnitudes of effects of subsets of concepts on the target concept based on association scores and action characteristics stored in connections along the set of edges; and returning hypotheses to the research portal.