Abstract: The disclosure describes integrated circuits and training apparatuses for efficiently training learnable logic networks. One or more hardware-implemented learnable logic engines execute forward and backward propagation through differentiable relaxations of Boolean logic gates arranged in configurable clusters. Each engine processes multiple inputs and outputs with shared parameter sets, supports variable numbers of gate inputs, and may reuse locally stored parameters across batched samples to reduce memory bandwidth. Engines and associated cores employ mixed-precision arithmetic, including low-precision activations and higher-precision gradients with on-chip gradient accumulation. Configurable interconnects route activations between engines, and topology bits select among logic operations and wiring options. Systems including a host processor orchestrate the use of the learnable logic engines to design fixed logic gate networks for efficient inference.

Abstract: Systems and methods are described for training and deploying a logic gate neural network. In various examples, a computing system receives a training data set of input vectors with target outputs and instantiates an untrained network whose nodes are parameterized over a predefined set of potential logic operators. Training may include forward propagating a batch of input vectors, computing node outputs as differentiable functions of the potential operators, aggregating outputs by summation to form scores, evaluating a loss, and updating the differentiable parameters. A fixed network is defined after multiple iterations by selecting a single logic operator for each respective node. Examples of suitable logic operators include AND, OR, NAND, NOR, XOR, constants, inverters, direct connections, and the like.

Abstract: A method, program and system for training a neural network to perform a machine learning task is provided. The method comprises receiving input data for the neural network. The method further comprises determining values for a plurality of hyperparameters of the neural network. The method further comprises building the neural network according to the hyper parameter values, wherein the neural network comprises a plurality of neurons. Each neuron includes a probability distribution for a plurality of logic operators, such that the neuron includes a corresponding probability for each of the logic operators. The method further comprises training the neural network according to the hyper parameter values and the input data by learning the probability distribution of each neuron. The method further comprises determining a logic operator of the plurality of logic operators for each neuron by selecting a value in the probability distribution.

Abstract: A method, apparatus, and computer program product are provided, which may provide activity coordination services. An apparatus may include a processor configured to receive a request for a context-sensitive calendar. The request may comprise an indication of an associated context. The processor may also be configured to determine the context associated with the received request. The processor may further be configured to aggregate one or more information atoms based at least in part upon the determined context. The processor may additionally be configured to generate a context-sensitive calendar comprising the aggregated information atoms. The processor may also be configured to provide the generated context-sensitive calendar to a user. Corresponding methods and computer program products are also provided.

Abstract: An approach is provided for rendering categorized location-based results. The approach involves determining a distribution of one or more entities over a geographical area. The approach further involves receiving an input for specifying one or more categories of the one or more entities. The approach also involves processing and/or facilitating a processing of the distribution to generate one or more clusters of the one or more entities with respect to the one or more categories. The approach further involves determining one or more geographical locations associated with the one or more clusters, the one or more entities, or a combination thereof. The approach also involves causing, at least in part, rendering or one or more graphical presentations of the one or more geographical locations, the one or more entities, or a combination thereof based, at least in part, on the one or more clusters.

Abstract: A method, apparatus, and computer program product are provided, which may provide activity coordination information. An apparatus may include a processor configured to cause a map to be displayed in a viewing agent. The processor may be further configured to receive an indication of a selection of a location on the map. The processor may also be configured to determine one or more information atoms having associated location information defining a location within a predefined distance of the selected location. The processor may additionally be configured to cause the one or more determined information atoms to be displayed in the viewing agent. Corresponding methods and computer program products are also provided.

Abstract: A method, apparatus, and computer program product are provided, which may provide activity coordination information. An apparatus may include a processor configured to cause a map to be displayed in a viewing agent. The processor may be further configured to receive an indication of a selection of a location on the map. The processor may also be configured to determine one or more information atoms having associated location information defining a location within a predefined distance of the selected location. The processor may additionally be configured to cause the one or more determined information atoms to be displayed in the viewing agent. Corresponding methods and computer program products are also provided.

Abstract: A method, apparatus, and computer program product are provided, which may provide activity coordination service. An apparatus may include a processor configured to maintain data regarding a user's previous activities and contacts invited to those previous activities. The processor may be further configured to retrieve the maintained data in response to creation of a new activity by the user. The processor may also be configured to determine one or more suggested contacts to invite to the new activity based at least in part upon the maintained data. The processor may additionally be configured to provide the one or more suggested contacts to the user. Corresponding methods and computer program products are also provided.

Abstract: A method, apparatus, and computer program product are provided, which may provide activity coordination services. An apparatus may include a processor configured to receive a request for a context-sensitive calendar. The request may comprise an indication of an associated context. The processor may also be configured to determine the context associated with the received request. The processor may further be configured to aggregate one or more information atoms based at least in part upon the determined context. The processor may additionally be configured to generate a context-sensitive calendar comprising the aggregated information atoms. The processor may also be configured to provide the generated context-sensitive calendar to a user. Corresponding methods and computer program products are also provided.