Abstract: Systems and methods for determining treatment effects of a randomized control trial (RCT) in accordance with embodiments of the invention are illustrated. One embodiment includes a method for determining treatment effects. The method includes steps for receiving data from a RCT, generating result data using a set of one or more generative models, and determining treatment effects for the RCT using the generated result data.

Abstract: One embodiment includes a method for predicting the progression of a current state. The method obtains input information concerning time-series forecasts of a state of an entity. The input information includes baseline information known about the state of the entity at a start time; and context information that includes a vector of time-independent background variables related to the entity. The method determines a first forecast for the entity at a first timestep that is separated from the start time by a time gap. The first forecast is determined, by a point prediction model, based on the baseline information and the context information. The method derives, from an autoregressive function, a mean parameter for a probabilistic function. The mean parameter is derived based on: the first forecast; and a learnable function trained based on the time gap and context information. The method parameterizes the probabilistic function based on the mean parameter.

Abstract: Systems and methods for determining treatment effects of a randomized control trial (RCT) in accordance with embodiments of the invention are illustrated. One embodiment includes a method for determining treatment effects. The method includes steps for receiving data from a RCT, generating result data using a set of one or more generative models, and determining treatment effects for the RCT using the generated result data.

Abstract: Systems and techniques for adjusting experiment parameters are illustrated. One embodiment includes a method that defines a joint distribution, wherein the joint distribution corresponds to a combination of a probabilistic model and a point prediction model, and wherein the point prediction model is configured to obtain a measurement of regression accuracy. The method derives an energy function for the joint distribution. The method obtains, from the energy function for the joint distribution, an approximation for a conditional distribution, wherein an output of the point prediction model is a parameter of the approximation. The method determines, from a loss function, at least one training parameter. The method trains the probabilistic based on the at least one parameter to operate as a conditional generative model, wherein the trained probabilistic model follows the conditional distribution. The method applies the trained probabilistic model to a dataset corresponding to a randomized trial.

Abstract: Systems and techniques for adjusting experiment parameters are illustrated. One embodiment includes a method that defines a joint distribution, wherein the joint distribution corresponds to a combination of a probabilistic model and a point prediction model, and wherein the point prediction model is configured to obtain a measurement of regression accuracy. The method derives an energy function for the joint distribution. The method obtains, from the energy function for the joint distribution, an approximation for a conditional distribution, wherein an output of the point prediction model is a parameter of the approximation. The method determines, from a loss function, at least one training parameter. The method trains the probabilistic based on the at least one parameter to operate as a conditional generative model, wherein the trained probabilistic model follows the conditional distribution. The method applies the trained probabilistic model to a dataset corresponding to a randomized trial.

Abstract: Systems and methods for training and utilizing predictive models that ignore missing features in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating representations of inputs with missing values. The method includes steps for, at a single layer in a multi-layer model, receiving an input includes a set of one or more values for several features and identifying a missingness pattern of the input, wherein the missingness pattern indicates whether the set of values is missing a value for each of the several features. The method further includes determining a set of one or more transformation weights based on the missingness pattern and transforming the input based on the determined transformation weights.

Abstract: One embodiment includes a method for generating representations of inputs with missing values. The method includes steps for receiving an input includes a set of one or more values for several features, wherein the set of values for at least one of the several features includes values for each of several points in time, and for identifying a missingness pattern of the input, wherein the missingness pattern for the at least one feature indicates whether the set of values is missing a value for each of the several points in time. The method further includes steps for determining a set of one or more transformation weights based on the missingness pattern, and transforming the input based on the determined transformation weights.

Abstract: This disclosure provides connectors for smart windows and doors. A smart window or door may incorporate an optically switchable pane. In one aspect, a smart window or door includes an insulated glass unit including an optically switchable pane. One aspect pertains to connectors such as, e.g., detachable power transfer connectors for movable doors or windows.

Abstract: Disclosed herein as methods, apparatuses, non-transitory computer readable media, and systems relating to reduction and/or identification of one or more health risks in a facility. For example, by sensing a bodily characteristic of an individual in a facility, e.g., by sensing at least one environmental characteristic. For example, by sensing surface cleanliness. For example, by tracking personnel in the facility. For example, by suggesting routes in an enclosure based at least in part in personnel concentration in the facility. Disclosed herein as methods, apparatuses, non-transitory computer readable media, and systems relating to monitoring occupancy of a facility.

Abstract: Systems and methods are provided for restraining cargo in a cargo compartment. In one embodiment, the system comprises a bracket having a main plate segment. At least one adapter is coupled to the bracket and dimensioned to be releasably secured to a location within the cargo compartment. A hook is disposed along a portion of the bracket, the hook comprising a receiving space formed between a rear segment, an end segment and a front segment. A portion of cargo is dimensioned to be placed within a portion of the receiving space. The system may include a locking member, wherein the portion of cargo is capable of being inserted into the receiving space when the locking member is in an open state, and wherein the portion of cargo is restrained from forward, rearward and lateral movement in the cargo compartment when the locking member is in a closed state.

Abstract: Systems and methods for modeling complex probability distributions are described. One embodiment includes a method for training a restricted Boltzmann machine (RBM), wherein the method includes generating, from a first set of visible values, a set of hidden values in a hidden layer of a RBM and generating a second set of visible values in a visible layer of the RBM based on the generated set of hidden values. The method includes computing a set of likelihood gradients based on the first set of visible values and the generated set of visible values, computing a set of adversarial gradients using an adversarial model based on at least one of the set of hidden values and the set of visible values, computing a set of compound gradients based on the set of likelihood gradients and the set of adversarial gradients, and updating the RBM based on the set of compound gradients.

Abstract: Systems and methods for model selection in accordance with embodiments of the invention are illustrated. One embodiment includes a method for ranking candidate models. The method includes steps for identifying several candidate models and a set of one or more scoring models for each of the several candidate models and determining a rank distribution for each of several model pairs, where each model pair of the several model pairs includes a candidate model of the several candidate models and a scoring model of the set of scoring models. The rank distribution for each model pair can be determined based on scores for the candidate model generated by the scoring model and scores generated by the scoring model for other candidate models of the several candidate models. The method further includes ranking the several models based on the determined rank distributions.

Abstract: Systems and methods for designing random control trials in accordance with embodiments of the invention are illustrated. One embodiment includes a method for designing a target random control trial. The method includes steps for generating a set of prognostic scores for a set of samples, computing a first correlation between the set of prognostic scores and a set of outcomes for the set of samples, computing a first variance for the set of outcomes for the set of samples, estimating a second correlation and a second variance for a target random control trial, and determining a set of target trial parameters based on the first and second correlations and the first and second variances.

Abstract: Systems and methods for determining treatment effects of a randomized control trial (RCT) in accordance with embodiments of the invention are illustrated. One embodiment includes a method for determining treatment effects. The method includes steps for receiving data from a RCT, generating result data using a set of one or more generative models, and determining treatment effects for the RCT using the generated result data.

Abstract: Systems and methods for modeling complex probability distributions are described. One embodiment includes a method for training a restricted Boltzmann machine (RBM), wherein the method includes generating, from a first set of visible values, a set of hidden values in a hidden layer of a RBM and generating a second set of visible values in a visible layer of the RBM based on the generated set of hidden values. The method includes computing a set of likelihood gradients based on the first set of visible values and the generated set of visible values, computing a set of adversarial gradients using an adversarial model based on at least one of the set of hidden values and the set of visible values, computing a set of compound gradients based on the set of likelihood gradients and the set of adversarial gradients, and updating the RBM based on the set of compound gradients.

Abstract: A mobile content distribution system in an airplane, a train, or a bus is capable of receiving wireless broadcast channels from a wireless service provider. The system offers a user purchase of wireless services including one or more broadcast channels provided by the wireless service provider, receives information indicative of a route from an originating location to a destination location, and determines if the content distribution system is authorized to receive services from the wireless service provider according to the information; and if the content distribution system is not authorized to receive services from the wireless service provider according to the information, the system provide a refund to the user. If the system is within an authorized area, the system determines if the system is authorized to provide full service from the wireless service provider according to the information and if the system is not authorized to provide full service, the system provides a partial refund to the user.

Abstract: A mobile content distribution system in an airplane, a train, or a bus is capable of receiving wireless broadcast channels from a wireless service provider. The system offers a user purchase of wireless services including one or more broadcast channels provided by the wireless service provider, receives information indicative of a route from an originating location to a destination location, and determines if the content distribution system is authorized to receive services from the wireless service provider according to the information; and if the content distribution system is not authorized to receive services from the wireless service provider according to the information, the system provide a refund to the user. If the system is within an authorized area, the system determines if the system is authorized to provide full service from the wireless service provider according to the information and if the system is not authorized to provide full service, the system provides a partial refund to the user.

Abstract: A mobile content distribution system in an airplane, a train, or a bus is capable of determining if a mobile content distribution system is within an area authorized for the mobile content distribution system to receive content from a wireless service provider and displaying channels from the wireless service provider accordingly. If the system is not within the authorized area, the system displays a program guide including channels from locally stored content but no channel from the wireless service provider. If the system is within the authorized area and a user indicates live wireless program guide information is needed, the system acquires the live wireless program guide information and displays the program guide includes channels from the locally stored content and channels from the wireless service provider.

Abstract: A method, device and computer readable medium that measures the error rate in a network data stream to a device, for example a Set Top Box. The method including joining one or more multicast groups representing audio and or video data for a requested channel; discarding a predetermined number of received packets for each of the joined multicast groups; and comparing a sequence number of a first packet received subsequent to the predetermined number of discarded packets to a sequence number of a next subsequent received packet in order to determine a sequence error. The method may further include tracking sequence numbers of received packets for one or more of the joined multicast groups; incrementing a packets received counter for each received packet for one or more of the joined multicast groups; and comparing each received sequence number with the next received sequence number in order to determine sequence errors.

Abstract: A method, system and computer readable medium box is disclosed for determining a networked device connection status of an IP set top. A signal strength parameter request is generated associated with the networked device's operation. This request is transmitted to a specific point in a network system where it is received at specific hardware and/or software point. Then a reply or signal strength parameter is generated in response to the signal strength parameter request. This reply or signal strength parameter is transmitted across the network system from the specific hardware and/or software point back to the networked device. There it is loaded into a signal strength parameter variable and displayed to the user.