Abstract: A system and method is disclosed for automated cross-node communication in a distributed directed acyclic graph. The method can include identifying a directed acyclic graph (“DAG”) overlaying a plurality of nodes and identifying the nodes underlying the DAG. A subordinate DAG can be generated in an entry vertex of the DAG. The subordinate DAG can include a vertex for each of the nodes underlying the DAG. Data and metadata can be received at the entry vertex. The data can be delivered to a next vertex in the DAG, and the metadata can be communicated to nodes underlying the DAG via the subordinate DAG.

Abstract: Embodiments of the present disclosure relate to methods, systems and computer program products for causal analysis. In some embodiments, there is provided a computer-implemented method. The method comprises determining, from observation samples of a plurality of factors, a first causal structure indicating a first causal relationship among the plurality of factors, each observation sample including a set of observation values of the plurality of factors; presenting the first causal structure to a user; in response to receiving at least one user input about the first causal structure from the user, executing actions associated with the at least one user input based on the first causal structure; and presenting a result of the execution of the actions to the user. In other embodiments, another method, systems and computer program products are provided.

Abstract: A system and method are disclosed for providing a private multi-modal artificial intelligence platform. The method includes splitting a neural network into a first client-side network, a second client-side network and a server-side network and sending the first client-side network to a first client. The first client-side network processes first data from the first client, the first data having a first type. The method includes sending the second client-side network to a second client. The second client-side network processes second data from the second client, the second data having a second type. The first type and the second type have a common association. Forward and back propagation occurs between the client side networks and disparate data types on the different client side networks and the server-side network to train the neural network.

Abstract: A neural network is augmented to enhance robustness against adversarial attack. In this approach, a fully-connected additional layer is associated with a last layer of the neural network. The additional layer has a lower dimensionality than at least one or more intermediate layers. After sizing the additional layer appropriately, a vector bit encoding is applied. The encoding comprises an encoding vector for each output class. Preferably, the encoding is an n-hot encoding, wherein n represents a hyperparameter. The resulting neural network is then trained to encourage the network to associated features with each of the hot positions. In this manner, the network learns a reduced feature set representing those features that contain a high amount of information with respect to each output class, and/or to learn constraints between those features and the output classes. The trained neural network is used to perform a classification that is robust against adversarial examples.

Abstract: Embodiments for ensemble training in a distributed marketplace in a computing environment. One or more ensemble machine learning models may be provided from a plurality of machine learning models competing within the distributed marketplace that achieve a performance on ensemble training data equal to or greater than a selected performance threshold, wherein the distributed marketplace is a blockchain.

Abstract: Techniques are described herein for selecting, curating, normalizing, enriching, and synthesizing the results of user experience tests. In some embodiments, a system identifies a qualitative element within a result set for a user experience test. The system then selects a machine learning model to apply based on one or more attributes associated with the user experience test and generates a predicted visibility, quality, and/or relevance for the qualitative element. Based on the prediction, the system generates a user interface that curates a set of results of the user experience test.

Abstract: A computation unit comprises first, second, and third circuits. The first circuit traverses gradient loss elements gpn and normalized output elements pn and produces an accumulation C. The accumulation C is produced by element-wise multiplying the gradient loss elements gpn with the corresponding normalized output elements pn and summing the results of the element-wise multiplication. The second circuit, operatively coupled to the first circuit, element-wise subtracts the accumulation C from each of the gradient loss elements gpn and produces modulated gradient loss elements gpn?. The third circuit, operatively coupled to the second circuit, traverses the modulated gradient loss elements gpn? and produces gradient loss elements gxn for a function preceding the softmax function. The gradient loss elements gxn are produced by element-wise multiplying the modulated gradient loss elements gpn? with the corresponding normalized output elements pn.

Abstract: A method for programming an activation function is provided. The method includes generating segment data for segmenting the activation function; segmenting the activation function into a plurality of segments using the segment data; and approximating at least one segment of the plurality of segments as a programmable segment. An apparatus for performing the method may include a programmable activation function generator configured to generate segment data for segmenting an activation function; segment the activation function into a plurality of segments using the generated segment data; and approximate at least one segment of the plurality of segments as a programmable segment. By using segment data, various non-linear activation functions, particularly newly proposed or known activation functions with some modifications, can be programmed to be processable in hardware.

Abstract: A method includes obtaining training data for a classifier, the training data comprises one or more target classes, obtaining candidate background classes, selecting negative classes from the candidate background classes, wherein the negative classes exclude candidate background classes that are close to the target classes, wherein the negative classes exclude candidate background classes that are very different from the target classes, and wherein the negative classes include candidate background classes that are similar to the target classes, and training the classifier on a combined set of the selected negative classes and target classes.

Abstract: Provided is an optimal solution determination method for determining optimality of a solution in a combinatorial optimization problem using a computer, including uniformly extracting a plurality of solutions in a solution space of the combinatorial optimization problem as a plurality of first solutions, and estimating a maximum evaluation value in a case where solutions of a number that exceeds the number of the plurality of first solutions are assumed, on the basis of a plurality of first evaluation values respectively corresponding to the plurality of first solutions that are uniformly extracted, as a first maximum evaluation value Z.

Abstract: Systems and methods of the present disclosure use one or more processor(s) to receive a consumable preference and a daily score intake value associated with a user and to obtain a content data regarding consumable item including an amount of a first nutrient found in the consumable item. The processor(s) utilizes, in real-time, a nutrient prediction machine learning model to ingest the content data regarding the consumable item and predict an amount of a second nutrient in the consumable item based on the content data and a decision tree library of thousand nutrient decision trees. The processor(s) determines zero-scored consumable item based on the daily score intake value, the amount of the first nutrient, the amount of the second nutrient, and the consumable preference. The processor(s) instructs a computing device to utilize a graphical user interface element to identify the zero-scored consumable item on a screen of the computing device.

Abstract: In an approach for constructing an ensemble model from a set of base learners, a processor performs a plurality of boosting iterations, where: at each boosting iteration of the plurality of boosting iterations, a base learner is selected at random from a set of base learners, according to a sampling probability distribution of the set of base learners, and trained according to a training dataset; and the sampling probability distribution is altered: (i) after selecting a first base learner at a first boosting iteration of the plurality of boosting iterations and (ii) prior to selecting a second base learner at a final boosting iteration of the plurality of boosting iterations. A processor constructs an ensemble model based on base learners selected and trained during the plurality of boosting iterations.

Abstract: A method for training a generator. The generator is supplied with at least one actual signal that includes real or simulated physical measured data from at least one observation of the first area. The actual signal is translated by the generator into a transformed signal that represents the associated synthetic measured data in a second area. Using a cost function, an assessment is made concerning to what extent the transformed signal is consistent with one or multiple setpoint signals, at least one setpoint signal being formed from real or simulated measured data of the second physical observation modality for the situation represented by the actual signal. Trainable parameters that characterize the behavior of the generator are optimized with the objective of obtaining transformed signals that are better assessed by the cost function. A method for operating the generator, and that encompasses the complete process chain are also provided.

Abstract: A set of classifiable data containing a plurality of classes is ingested. A target class within the plurality of classes is determined. Using the set of classifiable data, an interactive recall rate chart is generated, and the interactive recall rate chart shows a set of target class recall rates against a set of class recall rates for the remainder of the plurality of classes. The interactive recall rate chart is presented to a user. A target class recall rate selection from the set of target class recall rates is received from the user. The set of classifiable data is reclassified, based on the target class recall rate selection.

Abstract: Mechanisms are provided to implement a hardened ensemble artificial intelligence (AI) model generator. The hardened ensemble AI model generator co-trains at least two AI models. The hardened ensemble AI model generator modifies, based on a comparison of the at least two AI models, a loss surface of one or more of the at least two AI models to prevent an adversarial attack on one AI model, in the at least two AI models, transferring to another AI model in the at least two AI models, to thereby generate one or more modified AI models. At least one of the one or more modified AI models then processes an input to generate an output result.

Abstract: An electronic device including a deep memory model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive input data to the deep memory model. The at least one processor is also configured to extract a history state of an external memory coupled to the deep memory model based on the input data. The at least one processor is further configured to update the history state of the external memory based on the input data. In addition, the at least one processor is configured to output a prediction based on the extracted history state of the external memory.

Abstract: Described herein are systems and methods for applying machine learning to telematics data to generate a unique driver fingerprint for an individual by periodically receiving telematics data generated at a plurality of sensors of a vehicle; standardizing the telematics data; aggregating the standardized telematics data; applying a trained machine learning model to embed the aggregated telematics data into a low-dimensional state; and generating a unique driver fingerprint for the individual, the driver fingerprint comprising a static component, a dynamic component, or both a static component and a dynamic component; including iterative repetition to update the dynamic component of the driver fingerprint.

Abstract: This disclosure relates generally to artificial intelligence system, and more particularly to method and system for tracing a learning source of an explainable artificial intelligence (AI) model. In one example, the method may include receiving a desired behavior of the explainable AI model with respect to input data, generating a learning graph based on similarities among a plurality of learning sources with respect to the input data for the desired behavior and for a current behavior, retracing a learning of the explainable AI model by iteratively comparing the learning graph for the desired behavior and for the current behavior at each of a plurality of layers of the explainable AI model starting from an outer layer, and detecting the learning source responsible for the current behavior based on the retracing.

Abstract: A method including monitoring, using a machine learning model, network events of a network. The machine learning model generates fraud scores representing a corresponding probability that a corresponding network event is fraudulent. The method also includes detecting a failure of the machine learning model to generate, within a threshold time, a given fraud score for a given network event. The method also includes determining, by the machine learning model and after the threshold time, the given fraud score. The method also includes logging, responsive to detecting the failure, the given network event in a first table, including logging the given fraud score. The method also includes determining a metric based on comparing the first table to a second table which logs at least the given fraud score and the fraud scores. The method also includes generating an adjusted machine learning model based on the metric.

Abstract: A system for training a neural-network-based floating-point-to-binary feature vector encoder preserves the locality relationships between samples in an input space over to an output space. The system includes a neural network under training and a probability distribution loss function generator. The neural network has floating-point inputs and floating-point pseudo-bipolar outputs. The generator compares an input probability distribution constructed from floating-point cosine similarities of an input space and an output probability distribution constructed from floating-point pseudo-bipolar pseudo-Hamming similarities of an output space. The system includes a proxy vector set generator to take a random sampling of vectors from training data for a proxy set, a sample vector selector to select sample vectors from the training data and a KNN vector set generator to find a set of k nearest neighbors closest to each sample vector from said proxy set for a reference set.