Abstract: A method for verifying and/or validating whether a technical system fulfills a desired criterion. The technical system emits output signals based on input signals supplied to the technical system. The method includes: obtaining models for a plurality of components comprised by the technical system; obtaining a plurality of validation measurements; for each component, training a machine learning model to predict measurement outputs of the respective component based on inputs of the respective component; obtaining first test outputs from a last model based on test inputs; determining second test outputs from the machine learning model corresponding to the last model and based on the test inputs of the models; determining a discrepancy; verifying and/or validating whether the technical system fulfills the criterion.

Abstract: A method for verifying and/or validating whether a technical system fulfills a desired criterion. The technical system emits output signals based on input signals supplied to the technical system. The method includes: obtaining models for a plurality of components of the technical system; obtaining a plurality of validation measurements; for each component, training a machine learning model to predict outputs of the respective component; obtaining first test outputs from a last model based on test input; determining, second test outputs from the machine learning model corresponding to the last model and based on the test inputs of the models; determine a deviation which characterizes a difference between first test outputs determined from the last model and second test outputs determined by the machine learning model corresponding to the last model; verifying and/or validating whether the technical system fulfills the criterion.

Abstract: A computer-implemented method for verifying and/or validating whether a technical system fulfills a desired criterion with a predefined probability. The technical system emits output signals based on input signals supplied to the technical system. The method includes: obtaining models for components of the technical system and connections between the models; obtaining test outputs for the models based on test inputs of the models and the connections between the models; determining an upper or lower bound of an output of the technical system; verifying and/or validating whether the technical system fulfills the criterion with the predefined probability based on the determined upper or lower bound of the output.

Abstract: A device, computer program and computer-implemented method for machine learning. The method comprises providing a task comprising an action space of a multi-armed bandit problem or a contextual bandit problem and a distribution over rewards that is conditioned on actions, providing a hyperprior, wherein the hyperprior is a distribution over the action space, determining, depending on the hyperprior, a hyperposterior for that a lower bound for an expected reward on future bandit tasks has as large a value as possible, when using priors sampled from the hyperposterior, and wherein the hyperposterior is a distribution over the action space.

Abstract: A method for generating a simplified computer-implemented neural network. The method includes: receiving a predefined neural network, which includes a plurality of neural network structures and is described by weights, each neural network structure being assigned a pruning vector which describes a change in weights as a result of the pruning of the respective neural network; calculating a product of a matrix including a structure vector, the matrix including partial second order derivations of a loss function with respect to the plurality of weights; determining changes in the loss function with respect to the predefined neural network, each change occurring as a result of a pruning of a corresponding neural network structure of the two or more neural network structures to be pruned; and pruning at least one neural network structure based on the determined two or more changes in the loss function to generate the simplified neural network.

Abstract: A collapsible flotation device is provided and includes an inflatable member forming a closed loop and defining at least in part a first opening within the closed loop. The inflatable member has a first portion positioned to be a back support and a second portion configured to be disposed beneath a leg of the user, a floor of the first opening being disposed between the first and second portions. The inflatable member defines a second opening providing access of a foot of the user to water. The second opening has a smaller axial length than the first opening such that a third, forwardmost portion of the closed loop is positioned to be a foot support member.

Abstract: A cigar ventilating implement includes both a cylindrical punch and a piercing member such as a needle or spike. The punch and piercing member are sequentially extendable in response to a continuous twisting motion of a knob, with the sequencing being controlled by multiple slotted guide cylinders, a pair of actuator/driving cylinders, and a detent mechanism that initially prevents and subsequently enables relative rotation of the actuator and guide cylinders. Retraction of the punch and piercing members is carried out upon reverse rotation of the knob.

Abstract: Methods for generating a simplified computer-implemented neural network for a device. The method includes receiving a predefined neural network, which includes a plurality of neural network substructures in two or more layers; computing an approximative neural network for the predefined neural network, and computing a matrix with respect to the approximative neural network, which describes changes in the loss function due to simultaneous pruning of at least two network substructures from the plurality of neural network substructures which are situated within different layers of the two or more layers of the predefined neural network. The method finally includes pruning, based on the changes in the loss function described in the matrix, at least one neural network substructure from the plurality of neural network substructures to generate the simplified neural network.

Abstract: A cigar ventilating implement includes both a cylindrical punch and a piercing member such as a needle or spike. The cylindrical punch and piercing member are extendable from a housing of the implement by gripping laterally extending flanges or pins and pressing on an actuator. One or two coil springs may be provided to bias the punch and/or piercing member to a retracted position, and a retaining member may be provided to latch the punch in the extended position.

Abstract: A drinking vessel includes one or more self-retaining indicator sleeves, each including a detenting mechanism for positioning a window in the sleeve relative to a number, symbol, or picture to be viewed through the window, the detenting mechanism also serving to retain the sleeve on the drinking vessel.

Abstract: A shot glass or pipe includes a counter in the form of a sleeve rotatably coupled to a main body or stem of the shot glass or marijuana pipe, the sleeve including a window through which a number indicative of the number of units of alcohol or marijuana consumed is visible. A ratcheting mechanism prevents reverse rotation of the sleeve, and ensures that the window stays in place in front of a particular number until the user intentionally applies force to rotate the sleeve to a next number.

Abstract: Fastening devices and systems and methods thereof. Fastening devices and systems and methods thereof can include a unitary or one-piece body having first and second ends configured and operative to be coupled together or to be coupled to their respective complement in another of said fastening devices. The first end can include a ring or annular portion and a projection that are sized and shaped to fit around an anchor and in an orifice, respectively, of the second end. Fastening devices and systems and methods thereof according to embodiments may be used with items, including footwear, apparel, luggage, a backpack, a bag, a purse, a boxing glove, a punching bag, football or lacrosse shoulder pads, or the like.

Abstract: A fastening device for connecting identified openings, including: an elongated main body member defining a longitudinal axis, the main body member having a first end portion and a second end portion at opposite ends of the longitudinal axis; first and second tip end members located at the first end portion and second end portion of the body, respectively, the first and second tip end members each adapted to fit through one of the identified openings; and a first deformable interference portion located between the main body member and the first tip end member, and a second deformable interference portion located between the main body and the second tip end member; where the first and second deformable interference portions are each normally located in a rest state where they define an outer dimension that prevents their passage through one of the identified openings. Other embodiments, features and methods are also described.

Abstract: A computer-implemented method of configuring a system which interacts with a physical environment. An action of the system in a state of the physical environment results in an updated state of the physical environment according to a transition probability. A safe set of state-action pairs known to be safely performable and an unsafe set of state-action pairs to be avoided are indicated. During an environment interaction, a safe set of state-action pairs is updated by estimating a transition probability for a state-action pair based on an empirical transition probability of a similar other state-action pair, and including the state-action pair in the safe set of state-action pairs only if the state-action pair is not labelled as unsafe and the safe set of state-action pairs can be reached with sufficient probability from the state-action pair based on the estimated transition probability.

Abstract: A fastening device for connecting identified openings, including: an elongated main body member defining a longitudinal axis, the main body member having a first end portion and a second end portion at opposite ends of the longitudinal axis; first and second tip end members located at the first end portion and second end portion of the body, respectively, the first and second tip end members each adapted to fit through one of the identified openings; and a first deformable interference portion located between the main body member and the first tip end member, and a second deformable interference portion located between the main body and the second tip end member; where the first and second deformable interference portions are each normally located in a rest state where they define an outer dimension that prevents their passage through one of the identified openings. Other embodiments, features and methods are also described.

Abstract: Fastening devices and systems and methods thereof. Fastening devices and systems and methods thereof can include a unitary or one-piece body having first and second ends configured and operative to be coupled together or to be coupled to their respective complement in another of said fastening devices. The first end can include a ring or annular portion and a projection that are sized and shaped to fit around an anchor and in an orifice, respectively, of the second end. Fastening devices and systems and methods thereof according to embodiments may be used with items, including footwear, apparel, luggage, a backpack, a bag, a purse, a boxing glove, a punching bag, football or lacrosse shoulder pads, or the like.

Abstract: A collapsible flotation device is provided and includes an inflatable member forming a closed loop and defining at least in part a first opening within the closed loop. The inflatable member has a first portion positioned to be a back support and a second portion configured to be disposed beneath a leg of the user, a floor of the first opening being disposed between the first and second portions. The inflatable member defines a second opening providing access of a foot of the user to water. The second opening has a smaller axial length than the first opening such that a third, forwardmost portion of the closed loop is positioned to be a foot support member.

Abstract: A cigar ventilating implement includes both a cylindrical punch and a piercing member such as a needle or spike. The cylindrical punch and piercing member are sequentially extendable and retractable by rotating a knob.

Abstract: A cigar ventilating implement includes both a cylindrical punch and a piercing member such as a needle or spike. The cylindrical punch and piercing member are extendable from a housing of the implement by gripping laterally extending flanges or pins and pressing on an actuator. One or two coil springs may be provided to bias the punch and/or piercing member to a retracted position, and a retaining member may be provided to latch the punch in the extended position.

Abstract: A collapsible flotation device is provided that uses a coilable spring coupled to a panel to collapse the device when the spring is coiled, and to expand the device when the spring is uncoiled configuration. The spring can be contained within a sleeve along the outer portion of the panel. A support member that traverses the panel is provided. An inflatable bladder disposed about a part of the outer portion of the panel and coupled to the support member buoyantly supports a body weight of a user. The combination of the inflatable bladder and the support member provide support for a user in a seated position on the panel. Many configurations are disclosed, including a multi-user collapsible flotation device, multiple connected single-user flotation devices, and so forth. A back support member and a headrest, both of which can be inflatable, provide additional support for a user to maintain a seated position on the panel. A foot support member is provided for the comfort of the user.