Abstract: Systems, methods, and non-transitory computer-readable media can determine a respective embedding for each entity in a set of entities that are accessible through the social networking system, wherein each embedding is learned based at least in part on one or more sessions of connections formed between users and entities of the social networking system. One or more candidate entities that are related to a first entity can be determined based at least in part on the respective embeddings for the candidate entities and the first entity. At least a first candidate entity from the one or more candidate entities can be provided as a recommendation to a user that formed a connection with the first entity.

Abstract: A system for firmware protection and validation includes: a memory device, including firmware; a chipset, a microprocessor; a secure logic device in electrical communication with the chipset and the memory device; and a power on reset circuit in communication with the secure logic device, wherein, when the secure logic device receives a reset signal from the power on reset circuit, the secure logic device applies a hold signal to the chipset, when the hold signal is applied to the chipset, the power on reset circuit de-asserts the reset signal, when the reset signal is de-asserted, the secure logic device validates the content of the firmware in the memory device, and further wherein, when the content of the firmware is validated by the secure logic device, the secure logic device de-asserts the hold signal applied to the chipset.

Abstract: This invention relates to an apparatus, system, and method for computing with neuromorphic circuit architectures that have neurons with interconnected internal state information. The interconnected internal state information allows the neurons to enable or strengthen the input to other neurons. Furthermore, neuron internal state information provides insights on the characteristics of the input data that can be used to enhance the performance of the neuromorphic system. The neuromorphic system can be implemented with an artificial phase-change-based neurons.

Abstract: A voice user interface (VUI) system use collaborative filtering to expand its own knowledge base. The system is designed to improve the accuracy and performance of the Natural Language Understanding (NLU) processing that underlies VUIs. The system leverages the knowledge of system users to crowdsource new information.

Abstract: An online system generates one or more models that determine a likelihood of a user interacting with an application over a particular time interval after installing the application. To generate the one or more models, the online system obtains information describing a user's interaction with the application that occurred greater than a threshold time period prior to a time for which user interaction with the application is to be determined. Example user interactions with the application include: usage of the application, numbers of particular interactions with the application, an amount of compensation the application receives from the user, interactions with other users of the application via the application, and any other suitable interactions. Various engagement metrics may be predicted by the one or more models such as an amount of time spent using the application, particular actions taken in the application, and revenue generated by the user in the application.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and applying a machine learning model. One of the methods includes the actions of obtaining a collection of training data, the training data comprising collection of data points associated with a labeled set of real property parcels; training a machine learning model using the training data, the machine learning model being trained to generate a likelihood with respect to a parameter from input data associated with a specific parcel of real property, wherein training includes optimizing the model using a Markov chain optimization that seeks to minimize error in the model where the model is underpinned by one or more non-differentiable functions; receiving a plurality of data points associated with an input parcel of real property; and using the optimized model to generate a likelihood for the parameter for the input parcel of real property.

Abstract: An image processing apparatus capable of shifting to a power saving mode. The image processing apparatus includes a storing unit configured to store a document in a storage device, a notification unit configured to periodically notify an apparatus of a predetermined destination of information about a document that has been newly stored by the storing unit into the storage device, and a control unit configured to restrict shifting to a power saving mode in which the notification unit cannot make the notification after storage of a document by the storing unit has been completed and until the notification unit notifies at least information about the document.

Abstract: A method and system are provided for updating a neuron membrane potential in a spike time dependent plasticity model in a Neuromorphic system. The method includes approximating a shape of an analog spike signal from an axon input using a hardware-based digital axon timer. The method further includes generating a first intermediately updated neuron membrane potential value from a current axon timer value, a current synapse weight value and a current neuron membrane potential value using a first look-up table and an accumulator. The method also includes generating a second intermediately updated neuron membrane potential value with a leak decay effect using a second look-up table and the first intermediately updated neuron membrane potential value. The method additionally includes generating a final updated neuron membrane potential value based on a comparison of the second intermediately updated neuron membrane potential value with a neuron fire threshold level using a comparator.

Abstract: A processor or integrated circuit includes a memory to store weight values for a plurality neuromorphic states and a circuitry coupled to the memory. The circuitry is to detect an incoming data signal for a pre-synaptic neuromorphic state and initiate a time window for the pre-synaptic neuromorphic state in response to detecting the incoming data signal. The circuitry is further to, responsive to detecting an end of the time window: retrieve, from the memory, a weight value for a post-synaptic neuromorphic state for which an outgoing data signal is generated during the time window, the post-synaptic neuromorphic state being a fan-out connection of the pre-synaptic neuromorphic state; perform a causal update to the weight value, according to a learning function, to generate an updated weight value; and store the updated weight value back to the memory.

Abstract: A cognitive method, system and computer readable medium comprising: monitoring a user interaction of a user; generating user interaction data based upon the user interaction; receiving data from a plurality of data sources; processing the user interaction data and the data from the plurality of data sources to perform a cognitive learning operation, the processing being performed via a cognitive inference and learning system, the cognitive learning operation comprising analyzing the user interaction data, the cognitive learning operation generating a cognitive learning result based upon the user interaction data; associating a cognitive profile with the user based on the cognitive learning result; and, performing a cognitive procurement assistant operation based upon the cognitive profile, the cognitive procurement assistant operation assisting the user in performance of a procurement task.

Abstract: Embodiments provide a method and an apparatus for wake-up control of an intelligent terminal. At least two alarm set indications are sent by one or more applications of the intelligent terminal. The alarm set indication is used to indicate a first alarm wake-up time determined by the application for waking up the intelligent terminal. At least two of the at least two first alarm wake-up times corresponding to the at least two alarm set indications are delayed until a second alarm wake-up time. The second alarm wake-up time is determined according to preset adjustment control information. The intelligent terminal is woken at the second alarm wake-up time.

Abstract: In one embodiment, a system includes one or more electronic neurons and one or more electronic axons. Each neuron is connected to at least one electronic axon via an electronic synapse, and at least one of the one or more electronic neurons is configured to store information in a membrane potential thereof and/or at least one of the one or more electronic axons is configured to store information in an axon delay buffer thereof to act as a memory. In another embodiment, a computer-implemented method includes storing information to a memory comprising electronic neurons and electronic axons. Information is stored in either a membrane potential of at least one of the electronic neurons or in an axon delay buffer of at least one of the electronic axons. Also, each neuron is connected to at least one electronic axon via an electronic synapse.

Abstract: Systems, methods, and non-transitory computer readable media are configured to determine a feature set for a model to be trained by machine learning. A subset of features from the feature set can be associated with entities having relationship types and corresponding to pages on a social networking system. The feature set can be reduced based on at least one rule applied to the relationship types.

Abstract: An automated method of making a prediction regarding development of a software product includes receiving code changes information, build information, and failure information related to the software product. Entries are stored in a database, wherein each entry links a subset of the code changes information with a subset of the build information and with a subset of the failure information. A first matrix and a second matrix are generated using the entries in the database. Multi-target entropy calculations are performed based on the first matrix and the second matrix. The prediction regarding the development of the software product is performed based on the multi-target entropy calculations.

Abstract: A cognitive information processing system environment which includes a plurality of data sources, at least one of the plurality of data sources comprising a blockchain data source having associated blockchain data; a cognitive inference and learning system coupled to receive the data from the plurality of data sources to provide cognitively processed data, the cognitive inference and learning system performing a learning operation to improve the cognitively processed data over time, the learning operation being based at least in part on the blockchain data from the blockchain data source; and, a destination, the destination receiving the cognitively processed data.

Abstract: Systems and methods for recognizing an analogous case from a knowledge base including a plurality of candidate cases are disclosed. The system may include a data receiver to receive a representation of a target case, and a microprocessor coupled to the data receiver to generate a plurality of target attributes from the representation of the target case. The microprocessor may query the knowledge base to recognize the analogous case similar to the target case in information content using the target attributes and a plurality of attribute memories each including first and second attributes and an inter-attribute contextual representation of interactions between the first and second attributes in a context of the plurality of candidate cases. The system may include an output circuit to output the recognized analogous case to a user or a process.

Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes identifying characteristics and parameters for the CNN accelerator. Resources on the target are identified. A design for the CNN accelerator is generated in response to the characteristics and parameters of the CNN accelerator and the resources on the target.

Abstract: The present disclosure is directed to generating and using a machine learning model, such as a neural network, by augmenting another machine learning model with an additional parameter. The additional parameter may be connected to some or all nodes of an internal layer of the neural network. A machine learning model can determine a value associated with the additional parameter using non-behavior or non-event-based information. The machine learning model can be trained using non-behavior or non-event-based information and parameter values of the other machine learning model.

Abstract: Respective statistical distributions of a target variable within a proposed training data set and a proposed test data set for a machine learning model are obtained. A metric indicative of the difference between the two statistical distributions is computed. The difference metric is used to determine whether the proposed test data set is acceptable to evaluate the machine learning model.

Abstract: A computer-implementable method for cognitive information processing comprising: receiving data from a plurality of data sources, at least one of the plurality of data sources comprising a blockchain data source having associated blockchain data; processing the data from the plurality of data sources to provide cognitively processed data; performing a learning operation to improve the cognitively processed data over time, the learning operation being based at least in part on the blockchain data from the blockchain data source; and, providing the cognitively processed data to a destination.