Abstract: A method for data processing by a data clean room orchestration system is described. The method includes receiving an indication of mutually attested code for a data clean room between two or more partners. The method further includes configuring a trusted execution environment (TEE), including one or more virtual machines (VMs) that are individually or collectively operable to execute the mutually attested code. The method further includes transmitting, to endpoints associated with the partners, an attestation report including at least an encrypted token and a host public key of a host machine associated with the one or more VMs. The method further includes receiving respective partner secret keys wrapped with the host public key. The method further includes executing the mutually attested code on respective partner datasets in the TEE based on using a host private key of the host machine to unwrap the respective partner secret keys.

Abstract: A system and method for securing an application through an application-aware runtime agent can include: acquiring a code profile, instrumenting the application with a runtime agent according to the code profile, enforcing the runtime agent on the execution of the application, and responding to the runtime agent. Enforcing the runtime agent on the execution of the application can include monitoring the execution flow, which comprises of monitoring the utilization of the controls through the execution of the application; detecting a threat, which comprises identifying a section of the execution flow as a potential security threat; and regulating the execution flow to prevent or ameliorate the security threat. Responding to the runtime agent can include responding to the security threat and providing a user interface that may output runtime agent diagnostics and trigger alerts.

Abstract: Systems and methods described herein can involve training a first generative artificial intelligence (AI) model for a general domain, the first generative AI model trained using standard information components of the general domain; training a second AI model for a specific domain from the first generative AI model, the training of the second AI model being based on the use of the standard information components, non-standard information components of the specific domain and available label data of the specific domain; and fine-tuning the second AI model to align with preferences of the specific domain to maximize reward and minimize error.

Abstract: Various embodiments of the present disclosure are directed to automatic improved network architecture generation. In this regard, embodiments may process data representing a network architecture to generate an improved network architecture that resolves one or more vulnerabilities associated with the network architecture.

Abstract: Systems and methods described herein which can involve for a first input of a plurality of labeled images of a new domain task, processing the first plurality of labeled images through a plurality of backbone snapshots, each of the backbone snapshots representative of a model trained across a plurality of other domain tasks, each of the plurality of backbone snapshots configured to output a first plurality of features responsive to the input; processing a second input of second plurality of unlabeled images through the plurality of backbone snapshots to output a second plurality of features responsive to the second input; and generating a representative model for the new domain task from the clustering and transformation of the first plurality of features and as associated from the clustered and transformed second plurality of features.

Abstract: Systems and methods described herein can involve obtaining Pareto optimal solutions through making sequential decisions in a system that has multi-dimensional rewards and a continuous state space, and is controllable through a finite discrete set of actions, involving learning a value function through reinforcement learning (RL), wherein the value function is configured to take in an input of a state and an action pair, and provides a set of vectors as output, each of the set of vectors representing an expected total sum of rewards corresponding to a sequence of future control decisions; receiving, at an initial stage of a control sequence, a request about a total sum of rewards to be achieved; and determining a sequence of actions iteratively based on the output of the value function, an observation of the current state, and the request.

Abstract: Systems and methods described herein can involve learning a functional neural network (FNN) for a source domain associated with source time series data, the learning involving learning functional parameters of the FNN, the FNN comprising a plurality of layers of continuous neurons; transferring the functional parameters of the FNN to a target domain that is separate from the source domain; and tuning the functional parameters of the FNN with target time series data from the target domain, the target time series data having fewer samples than the source time series data.

Abstract: Example implementations described herein involve systems and methods for bound enhanced reinforcement learning systems for distribution supply chain management which can include initializing a replay buffer, a first state-action value function network having first random weights, and a second state-action value function network having second random weights; determining an action corresponding to an inventory ordering quantity at one or more facility in a multi-echelon supply chain network based on an (epsilon) ?-greedy exploration policy; executing the action in a simulated environment, and storing transition results in the replay buffer; calculating an upper bound and a lower bound of the optimal inventory costs; incorporating the upper bound and the lower bound with at least hyper-parameters T1, ?2 in updating at least one of the first or the second state-action value function networks; and performing a gradient descent on the first state-action value function network based on the upper or the lower bound.

Abstract: A method for predictive maintenance of equipment. The method may include receiving expected future return value as input to a decision maker model, wherein the decision maker model is a machine learning model that predicts maintenance action associated with the equipment; feeding recent observations and recent actions from environment as inputs to the decision maker model; generating a next action as model outputs of the decision maker model, wherein the next action is the predicted maintenance action; and executing the next action in the environment.

Abstract: Conventional simulation-based optimization, even when automated, requires substantial user-involved development time. Accordingly, embodiments are disclosed to automate various aspects of simulation-based optimization. In particular, an optimization configurator and associated data structures are disclosed for generating and running optimization templates that can be easily constructed (e.g., via lists of available components), revised, evaluated, and re-run as needed. The optimization templates may comprise a plurality of optimization configurations that each define and pair an optimization algorithm with a simulator of a real-world system. Embodiments can reduce development time, are applicable to various domains, can be used by novice users without specialized knowledge, and can improve the overall quality of optimization for the operations of real-world systems, such as supply chains.

Abstract: Example implementations described herein are directed to systems and methods for generating a model ensemble to reduce bias, the method involving training a plurality of machine learning models from data, each of the plurality of machine learning models trained from a first subset of the data and validated from a second subset of the data, each of the first subset and the second subset being different for each of the plurality of machine learning models; determining accuracy of each of the plurality of machine learning models based on validation against the second subset of the data; pruning the plurality of machine learning models based on the accuracy to generate a subset of the plurality of machine learning models; and forming the model ensemble from the subset of the plurality of machine learning models.

Abstract: Example implementations described herein involve systems and methods that can include, for receipt of time-series data indicative of energy consumption associated with a type of building of a plurality of different types of buildings and a climatic zone from a plurality of climatic zones, executing random convolutional kernel (RCK) on the time-series data to generate a classification group of the time-series data according to type of building and the climatic zone; and executing a trained functional neural network (FNN) on the time-series data of the classification group to provide a short-term energy consumption forecast.

Abstract: Systems and methods described herein can involve training a functional encoder involving a plurality of layers of continuous neurons from input time series data to learn a dimension reduced form of the input time series data, the dimension reduced form of the input time series data being at least one of a feature reduced or time point reduced form of the input time series data; and training a functional decoder comprising another plurality of layers of continuous neurons to learn the input time series data from the dimension reduced form of the input time series data.

Abstract: Example implementations described herein involve systems and methods for efficient learning for mixture of domains which can include applying a clustering technique to a set of data comprised of multiple domains to obtain an initial domain separation of the set of data into one or more clusters; training one or more experts associated with each of the one or more clusters based on the initial domain separation where each expert corresponds with one domain of the multiple domains; inputting all data points to the one or more experts for refining each of the one or more clusters using expert output probabilities; retraining the one or more experts based on the refined one or more clusters; and training a gating mechanism to route an input to an appropriate expert of the one or more experts based on the refined one or more clusters.

Abstract: In some examples, a computer system may receive sensor data and failure data for equipment. The system may determine, for the equipment, a plurality of time between failure (TBF) durations that are longer than other TBF durations for the equipment. The system may determine, from the sensor data corresponding to operation of the equipment during the plurality of TBF durations, a plurality of measured sensor values for the equipment. Additionally, the system may determine a subset of the measured sensor values corresponding to a largest number of the TBF durations of the plurality of TBF durations. The system may further determine at least one operating parameter value for the equipment based on the subset of the measured sensor values. The system may send a control signal for operating the equipment based on the operating parameter value and/or a communication based on the operating parameter value.

Abstract: Techniques for determining range of electric vehicles are described. A sensor provides a signal indicative of the current being supplied by a battery of an electric vehicle to a motor of the electric vehicle. A controller receives the signal and determines the current supplied by the battery. The controller also receives a voltage supplied by the battery and determines a notional distance travelled by the electric vehicle. Based on the voltage, the current, and the notional distance, the controller determines the range of the electric vehicle.

Abstract: A method for reinforcement learning (RL) of continuous actions. The method may include receiving a state as input to at least one actor network to predict candidate actions based on the state, wherein the state is a current observation; outputting the candidate actions from the at least one actor network; receiving the state and the candidate actions as inputs to a plurality of distributional critic networks, wherein the plurality of distributional critic networks calculates quantiles of a return distribution associated with the candidate actions in relation to the state; outputting the quantiles from the plurality of distributional critic networks; and selecting an output action based on the candidate actions and the quantiles.

Abstract: A method for detecting an anomaly in time series sensor data. The method may include identifying a noisiest cycle from the time series sensor data; for an evaluation of the noisiest cycle indicative of the anomaly being detected at a confidence level above a threshold, providing an output associated with the noisiest cycle as being the anomaly; and for the evaluation of the noisiest cycle indicative of the anomaly being detected at the confidence level not above the threshold: identifying a cycle from the time series sensor data having a most differing shape; and providing the output associated with the cycle having the most differing shape as being the anomaly.

Abstract: K-nearest multi-agent reinforcement learning for collaborative tasks with variable numbers of agents. Centralized reinforcement learning is challenged by variable numbers of agents, whereas decentralized reinforcement learning is challenged by dependencies among agents' actions. An algorithm is disclosed that can address both of these challenges, among others, by grouping agents with their k-nearest agents during training and operation of a policy network. The observations of all k+1 agents in each group are used as the input to the policy network to determine the next action tor each of the k+1 agents in the group. When an agent belongs to more than one group, such that multiple actions are determined for the agent, an aggregation strategy can be used to determine the final action for that agent.

Abstract: An apparatus for predicting a characteristic of a system is provided. The apparatus may include a memory and at least one processor coupled to the memory. The at least one processor may be configured to perform a method including measuring, at a high sample rate, data relating to an operation of the system over a first time period. The method may further include producing a two-dimensional (2D) time-and-frequency input data set by applying a wavelet transform to the measured data. The method may additionally include generating a set of one or more values associated with one or more system characteristics by processing the 2D time-and-frequency input data set using a functional neural network (FNN).