Abstract: A method for active learning includes obtaining a set of unlabeled training samples and for each unlabeled training sample, perturbing the unlabeled training sample to generate an augmented training sample. The method includes generating, using a machine learning model, a predicted label for both samples and determining an inconsistency value for the unlabeled training sample that represents variance between the predicted labels for the unlabeled and augmented training samples. The method includes sorting the unlabeled training samples based on the inconsistency values and obtaining, for a threshold number of samples selected from the sorted unlabeled training samples, a ground truth label. The method includes selecting a current set of labeled training samples including each selected unlabeled training samples paired with the corresponding ground truth label. The method includes training, using the current set and a proper subset of unlabeled training samples, the machine learning model.

Abstract: A system and a method of generating and using a multimodal knowledge representation within an artificial intelligence computing system may include prompting a selection of nodes in a graphical visualization; defining an adaptation strategy based; integrating an adaptation strategy representation with the selection of nodes to generate a multimodal knowledge representation; traversing the selection of nodes in response to a user query; performing an adaptation on the selection of nodes; and updating the knowledge representation based on user feedback to a result generated in response to the user query.

Abstract: A facility providing systems and methods for discovering novel features to use in machine learning techniques. The facility receives, for a number of subjects, one or more sets of data representative of some output or condition of the subject over a period of time or capturing some physical aspect of the subject. The facility then extracts or computes values from the data and applies one or more feature generators to the extracted values. Based on the outputs of the feature generators, the facility identifies novel feature generators for use in at least one machine learning process and further mutates the novel feature generators, which can then be applied to the received data to identify additional novel feature generators.

Abstract: A processor may receive user information for a request payload from an external device and data describing a plurality of user interface (UI) elements configured to be presented in a UI of the external device. The processor may select a machine learning (ML) model from a plurality of ML models using a contextual bandit ML model that is trained based on the user information. The processor determines at least one recommended user interface (UI) element with a selected ML model, based on the user information and the data describing the plurality of UI elements. The at least one recommended UI element may be presented in the UI of the external device. The processor may receive event data indicating a user interaction with the at least one recommended UI element in the UI of the external device. The contextual bandit ML model may be re-trained based on the event data.

Abstract: A foldable display apparatus, a method of manufacturing the same, and a controlling method of the same are disclosed. The foldable display apparatus includes a substrate including a metal thin film and an insulating layer provided on the metal thin film, an organic light-emitting unit formed on the substrate and emitting light in an direction away from the substrate, and a thin film encapsulating layer for encapsulating the organic light-emitting unit. The foldable display apparatus may be folded in a direction such that the metal thin film is exposed.

Abstract: A method comprises receiving an input signal for processing in one or more neurons of a neural network, wherein the neural network has zero bias neurons and includes a plurality of resistive processing unit (RPU) weights and each neuron has an activation function. The method also includes applying an arbitrary amplification factor to activation function outputs of the one or more neurons in the neural network, wherein the arbitrary amplification factor is based on a dynamic range of components in the neural network and compensates for conductance drift in values of the RPU weights. The method also includes performing a calculation with the neural network using the amplified activation function outputs of the one or more neurons.

Abstract: The present disclosure relates to electronic circuit design, and more specifically, to training a neural network to serve as the reward function for optimization-based approaches to PCB design automation. Embodiments may include generating, using a processor, one or more placed designs using a genetic optimization methodology including a reward function and adjusting the one or more placed designs and the reward function during the generating. Embodiments may further include routing the one or more placed designs using an auto-router to assign a routability score label and training a neural network, using the one or more placed designs and the routability score label, to extract one or more intermediate features from the one or more placed designs. Embodiments may also include predicting a routability of the PCB design based upon, at least in part, the one or more intermediate features.

Abstract: Techniques for providing actionable recommendations for configuring system parameters are disclosed. A set of environmental constraints and a set of values for a set of parameters for a target device is applied to a machine learning model to predict a first performance value of the target device. Candidate values for the set of parameters are identified that are within a threshold range from the first set of values in a multi-dimensional space. For each particular candidate set of values of the candidate sets of values the machine learning model to predicts a performance value of the target device and identifies a subset of the candidate sets of values with corresponding performance values that meet a performance criteria. A subset of candidate sets of values that meets performance criteria is provided as a recommendation.

Abstract: A computer-implemented method for training a machine-learning network includes receiving an input data from a sensor, wherein the input data includes a perturbation, wherein the input data is indicative of image, radar, sonar, or sound information, obtain a worst-case bound on a classification error and loss for perturbed versions of the input data, utilizing at least bounding of one or more hidden layer values, in response to the input data, train a classifier, wherein the classifier includes a plurality of classes, including an additional abstain class, wherein the abstain class is determined in response to at least bounding the input data, outputting a classification in response to the input data, and output a trained classifier configured to detect the additional abstain class in response to the input data classifier with a plurality of classes, including an additional abstain class.

Abstract: A nervous system emulator engine includes working computational models of the vertebrate nervous system to generate lifelike animal behavior in a robot. These models include functions representing several anatomical features of the vertebrate nervous system, such as spinal cord, brainstem, basal ganglia, thalamus, and cortex. The emulator engine includes a hierarchy of controllers in which controllers at higher levels accomplish goals by continuously specifying desired goals for lower-level controllers. The lowest levels of the hierarchy reflect spinal cord circuits that control muscle tension and length. Moving up the hierarchy into the brainstem and midbrain/cortex, progressively more abstract perceptual variables are controlled. The nervous system emulator engine may be used to build a robot that generates the majority of animal behavior, including human behavior. The nervous system emulator engine may also be used to build working models of nervous system functions for clinical experimentation.

Abstract: In a process of inferential analysis and reporting of contextual complaints data, a social media message is processed to formulate an input data for a neural network, The input data is processed to chunk and identify one or more entities of interest to an enterprise, wherein the enterprise includes one or more line of business (LOB). The identified entities of interest are processed by a plurality of neural nodes in the neural network to identify a specific set of LOB(s) that are impacted by the social media message. With the entities of interest as input to the neural network, corresponding to a plurality of parameters associated with an enterprise, output from the individual neural nodes is dynamically determined. The output from the plurality of neural nodes is collated to generate a report with action items specific to the set of LOB(s) to take pre-emptive actions in the enterprise.

Abstract: A system for assessing a data model includes a data receiver, a model receiver, and a model assessment device. The data receiver receives training data, historical data, and production data. The model receiver receives the data model associated with the historical data and trained using the training data. The historical data includes a first outcome of the data model provided based on an input feature in the production data. The model assessment device identifies a key feature in the production data relative to the input feature based on a target category in the historical data and a statistical distribution of the input feature in the production data. The model assessment device determines a second outcome of the data model based on the key feature. In response to the second outcome being different from the first outcome, the model assessment device determines a veracity score for assessing the data model.

Abstract: A system and method include receiving a first set of variables associated with a real-time request, extracting a predetermined subset of the first set of variables for generating a second set of variables, identifying historical request data, computing a set of parameters based on the first set of variables and the historical request data, generating a plurality of numeric sequences and a plurality of string sequences for the real-time request, converting each of the plurality of string sequences into an encoded string sequence to obtain a plurality of encoded string sequences, inputting the plurality of numeric sequences and the plurality of encoded string sequences into a trained deep machine learning model, and computing a score from the trained deep machine learning model, the score indicative of a likelihood that the real-time request belongs to an unauthorized classification.

Abstract: A semiconductor device that is less influenced by variations in characteristics between transistors or variations in a load, and is efficient even for normally-on transistors is provided. The semiconductor device includes at least a transistor, two wirings, three switches, and two capacitors. A first switch controls conduction between a first wiring and each of a first electrode of a first capacitor and a first electrode of a second capacitor. A second electrode of the first capacitor is connected to a gate of the transistor. A second switch controls conduction between the gate and a second wiring. A second electrode of the second capacitor is connected to one of a source and a drain of the transistor. A third switch controls conduction between the one of the source and the drain and each of the first electrode of the first capacitor and the first electrode of the second capacitor.

Abstract: An apparatus for training a tunable data structure to predict internal ribosome entry site (IRES) activity includes at least a processor and a memory containing instructions configuring the at least a processor to assemble a training set including a plurality of nucleotide sequence data examples IRES sequences and a plurality of correlated observed IRES activity, partition the training set into at least a first section and a second section, train, using the first section at least an activity data structure to generate probable IRES activity using nucleotide sequence data, and iteratively retrain the at least an activity data structure using the second section, wherein each iteration of the iterative retraining includes generating a predicted IRES activity value using the at least an activity neural network and a nucleotide sequence data example, evaluating an error function, and tuning the activity data structure.

Abstract: Systems, apparatuses, and methods related to a neuron using posits are described. An example apparatus may include a memory array including a plurality of memory cells configured to store data. The data can include a plurality of bit strings. The example apparatus may include a neuron component coupled to the memory array. The neuron component can include neuron circuitry configured to perform neuromorphic operations on at least one of the plurality of bit strings.

Abstract: Technologies are provided for identifying individuals having a risk of non-adherence to or from a prescribed treatment program; for predicting and the risk, which may be determined as a forecast over a future time span; and evaluating it to further determine or invoke specific actions to mitigate the risk or otherwise improve likelihood of compliance. A singular spectrum analysis (SSA) is utilized to analyze temporal properties of a time series determined from measured or observational data to determine an emergent pattern. Based on this pattern, a risk of non-adherence, including relapse or absconding, over a future time interval by the individual may be determined and utilized to implement an intervening action.

Abstract: Embodiments described herein relate to an adaptable photonic apparatus including an optical neural network. The photonic apparatus includes an optical input that provides an optical signal. The photonic apparatus also includes a chassis component and an optical neural network (ONN). The chassis component includes at least one modular mounting location for receiving a modular network component. The ONN is operably connected with the optical input and is configured to perform optical processing on the optical signal according to a deep learning algorithm. The ONN includes optical components arranged into layers to form the ONN. The modular network component is an additional optical processing component that is configured to function in cooperation with the ONN to adapt the deep learning algorithm.

Abstract: A neural processing unit may comprise a first circuit configured to perform operations for an artificial neural network (ANN) model, and arranged for a plurality of groups of processing elements (PEs) including a plurality of PEs; a second circuit arranged to output a plurality of clock signals to the first circuit; a third circuit configured to measure a ratio of peak power and average power of at least the first circuit; and a fourth circuit, arranged to dynamically calibrate a phase of at least one of the plurality of clock signals of the second circuit based on the ratio of peak power and average power measured in the third circuit.

Abstract: A system for generating a supplement instruction set using artificial intelligence. The system includes at least a server wherein the at least a server is designed and configured to receive training data. The system includes a diagnostic engine operating on the at least a server designed and configured to record at least a biological extraction from a user and generate a diagnostic output based on the at least a biological extraction and training data. The system includes a plan generator module operating on the at least a server designed and configured to generate a comprehensive instruction set associated with the user as a function of the diagnostic output. The system includes a supplement plan generator module operating on the at least a server designed and configured to generate a supplement instruction set as a function of the comprehensive instruction set.