Abstract: There are provided a method, system and computer program product for preventing unauthorized use of a deep reinforcement learning agent. The DRL agents are trained to behave as expected only when they observe the one or more required secret operational keys. In some embodiments, the DRL agents are further trained to operate at a diminished capacity when the one or more required secret operational keys are unused.

Abstract: Methods and systems that enable communication network traffic engineering functions or application functions using combinations of neural network (NN) encoders and NN decoders are provided. A first network element has a NN encoder deployed thereat and receives input data based on which the NN encoder generates a latent representation. The latent representation is provided to a second network element that has a NN decoder deployed thereat and is configured to process the latent representation in accordance with a traffic engineering function to produce a traffic engineering output, which may be used to modify an operational state variable of the communication network. The input data are values of operational state variables of the communication network obtained at the first network element.

Abstract: The present invention relates to imidazo-pyridinyl compounds, or a pharmaceutically acceptable salt thereof, to pharmaceutical compositions comprising such compounds and salts, and to methods of using such compounds, salts and compositions for the treatment of abnormal cell growth, including cancer, in a subject.

Abstract: There is provided a method and system for communication network management. There is provided an active TE architecture and procedure that rely on the epistemic uncertainty obtained from traffic forecasting models. According to embodiments, the traffic forecasting models can predict the mean of the network traffic demand and can extract one or more of the features relating epistemic uncertainty and the aleatoric uncertainty. According to embodiments, the epistemic uncertainty is used to vary the sampling frequency of network statistics in TE applications, for specific times or specific flows. A time-window can be used to predict network traffic can be varied (e.g. increased or decreased) to adjust the epistemic uncertainty.

Abstract: There are provided a method, system and computer program product for preventing unauthorized use of a deep reinforcement learning agent. The DRL agents are trained to behave as expected only when they observe the one or more required secret operational keys. In some embodiments, the DRL agents are further trained to operate at a diminished capacity when the one or more required secret operational keys are unused.

Abstract: This disclosure relates to devices and kits for delivery of a fluid. In some embodiments, the fluid is useful in facilitating and maintaining hemostasis.

Abstract: The present disclosure provides a compound represented by structural formula (I-0): or a pharmaceutically acceptable salt thereof useful for treating a cancer.

Abstract: The present invention relates to imidazo-pyridinyl compounds, or a pharmaceutically acceptable salt thereof, to pharmaceutical compositions comprising such compounds and salts, and to methods of using such compounds, salts and compositions for the treatment of abnormal cell growth, including cancer, in a subject.

Abstract: A system and method for compressing and decompressing image data, which provides better compression and minimal representation of the input image with minimal loss compared to previous Deep Learning codecs. The system can provide for quantization during training, flexible addition of filters, and conditional complexity of image compression. The Deep Learning codec generates codes that are directly usable with Machine Learning algorithms, thus boosting the performance of Machine Learning algorithms.

Abstract: The present invention relates to imidazo-pyridinyl compounds, or a pharmaceutically acceptable salt thereof, to pharmaceutical compositions comprising such compounds and salts, and to methods of using such compounds, salts and compositions for the treatment of abnormal cell growth, including cancer, in a subject.

Abstract: Provided is a rehabilitation and training gaming system that can comprise a mechanism of detecting user inputs, such as a camera, joystick, force sensor, position sensor, inertial sensor, robotic interface, bioelectrical signal sensor, etc., computing unit(s) for processing inputs and generating outputs, and a computer-rendered object that is at least partially controlled by the user's inputs in a physics-driven manner. The physics-driven manner involves the computer-rendered object responding to user inputs in a manner which is both continuous and time-dependent, including but not limited to: a viscosity relationship, where the velocity, or rate of change, of a property of the computer-rendered object is proportional to the user's input, or an inertial relationship, where the acceleration, or second time derivative, of a property of the computer-rendered object is proportional to the user's input.

Abstract: The present invention relates to imidazo-pyridinyl compounds, or a pharmaceutically acceptable salt thereof, to pharmaceutical compositions comprising such compounds and salts, and to methods of using such compounds, salts and compositions for the treatment of abnormal cell growth, including cancer, in a subject.

Abstract: This disclosure relates to devices and kits for delivery of a fluid. In some embodiments, the fluid is useful in facilitating and maintaining hemostasis.

Abstract: Provided is a system for hand rehabilitation comprising an enclosure comprising a top surface and a bottom surface opposite the top surface; a wrist support attached to the top surface and configured to support and rigidly hold a wrist in position with respect to the top surface; a finger retention support arranged on the top surface, sized to accommodate at least a fingertip, and arranged to allow the finger to exert forces on the finger retention support in any direction; a sensor housed within the enclosure and in communication with the finger retention support, the sensor configured to detect and convert forces exerted by the finger on the finger retention support in multiple degrees of freedom into an electrical signal; and a processor in electrical communication with the sensor and configured to receive the electrical signal and provide feedback to a user.

Abstract: Provided is a rehabilitation and training gaming system that can comprise a mechanism of detecting user inputs, such as a camera, joystick, force sensor, position sensor, inertial sensor, robotic interface, bioelectrical signal sensor, etc., computing unit(s) for processing inputs and generating outputs, and a computer-rendered object that is at least partially controlled by the user's inputs in a physics-driven manner. The physics-driven manner involves the computer-rendered object responding to user inputs in a manner which is both continuous and time-dependent, including but not limited to: a viscosity relationship, where the velocity, or rate of change, of a property of the computer-rendered object is proportional to the user's input, or an inertial relationship, where the acceleration, or second time derivative, of a property of the computer-rendered object is proportional to the user's input.

Abstract: A software keyboard is provided with a dedicated key (dynamic character key) for inputting a character, where the character associated with the key is determined based upon a context and may dynamically change according to the context. For example, a first character may be dynamically determined and associated with the dedicated key for a first context and a second character, possibly different from the first character, may be selected and associated with the dedicated key for a different context. The character that is associated with the dynamic character key may also be displayed on the dynamic character key. In some embodiments, the character associated with the dynamic character key may be a non-alphanumeric character such as a diacritical mark, a punctuation mark, and the like.

Abstract: A computer implemented method describes managing privacy information. Initially, a request is received from a requester for the privacy information of an entity. The request is often the result of an applicant submitting a form or application to the requester. Next, implementations of the present invention create a privacy transaction in a database for the privacy information including one or more identity qualities from the applicant and one or more characteristics for the submission. These identity qualities, characteristics for the submission and other pieces of information are used to score the privacy transaction according to the one or more identity qualities from the applicant and the one or more characteristics for the submission. The score provides a confidence level indicative of the authenticity and authorization associated with the submission.