Abstract: A noise reduction and smart ticketing application for social media-based communication systems may identify social media-based communications from users who are attempting to engage with a brand or entity on a social media platform as actionable, and distinguish other communications as noise. The noise reduction and smart ticketing system may use machine learning to determine which social media communications are actionable for a given company or other organization, and generates tickets for actionable communications. Actionable communications may include, but are not limited to, technical support issues, inquiries about a product release date, grievances, incidents, suggestions to improve service, critiques of company policies, etc. Non-actionable communications (i.e., “noise”) may include, but are not limited to, suggestions to other users, promotions, coupons, offers, marketing campaigns, affiliate marketing, statements that a user is attending an event, etc.

Abstract: A circuit comprises a series of calculating blocks that can each implement a group of neurons; a transformation block that is linked to the calculating blocks by a communication means and that can be linked at the input of the circuit to an external data bus, the transformation block transforming the format of the input data and transmitting the data to said calculating blocks by means of K independent communication channels, an input data word being cut up into sub-words such that the sub-words are transmitted over multiple successive communication cycles, one sub-word being transmitted per communication cycle over a communication channel dedicated to the word such that the N channels can transmit K words in parallel.

Abstract: Neuromorphic synapse apparatus is provided comprising a synaptic device and a control signal generator. The synaptic device comprises a memory element, disposed between first and second terminals, for conducting a signal between those terminals with an efficacy which corresponds to a synaptic weight in a read mode of operation, and a third terminal operatively coupled to the memory element. The memory element has a non-volatile characteristic, which is programmable to vary the efficacy in response to programming signals applied via the first and second terminals in a write mode of operation, and a volatile characteristic which is controllable to vary the efficacy in response to control signals applied to the third terminal. The control signal generator is responsive to input signals and is adapted to apply control signals to the third terminal in the read and write modes, in dependence on the input signals, to implement predetermined synaptic dynamics.

Abstract: Methods and computer systems improve a trained base deep neural network by structurally changing the base deep neural network to create an updated deep neural network, such that the updated deep neural network has no degradation in performance relative to the base deep neural network on the training data. The updated deep neural network is subsequently training. Also, an asynchronous agent for use in a machine learning system comprises a second machine learning system ML2 that is to be trained to perform some machine learning task. The asynchronous agent further comprises a learning coach LC and an optional data selector machine learning system DS. The purpose of the data selection machine learning system DS is to make the second stage machine learning system ML2 more efficient in its learning (by selecting a set of training data that is smaller but sufficient) and/or more effective (by selecting a set of training data that is focused on an important task).

Abstract: An integrated circuit is configurable to generate a notification message when an indicator of an event used to synchronize the execution of different functional blocks of the integrated circuit changes status. The indicator of the event is cleared when an operation is triggered and is set when the operation completes. The notification message includes a timestamp indicating the time when the indicator of the event changes status. The notification message is used to determine the execution timeline of a set of instructions executed by integrated circuit and to identify bottlenecks in the set of instructions or the integrated circuit.

Abstract: The present invention concerns a method of programming an analogue electronic neural network comprising a plurality of layers of somas. Any two consecutive layers of somas are connected by a matrix of synapses. The method comprises: applying test signals to inputs of the neural network; measuring at a plurality of measurement locations in the neural network responses of at least some somas and synapses to the test signals; extracting from the neural network, based on the responses, a first parameter set characterising the behaviour of the at least some somas; carrying out a training of the neural network by applying to a training algorithm the first parameter set and training data for obtaining a second parameter set; and programming the neural network by using the second parameter set. The invention also relates to the neural network and to a method of operating it.

Abstract: Systems and methods are provided for reducing power in in-memory computing, matrix-vector computations, and neural networks. An apparatus for in-memory computing using charge-domain circuit operation includes transistors configured as memory bit cells, transistors configured to perform in-memory computing using the memory bit cells, capacitors configured to store a result of in-memory computing from the memory bit cells, and switches, wherein, based on a setting of each of the switches, the charges on at least a portion of the plurality of capacitors are shorted together. Shorting together the plurality of capacitors yields a computation result.

Abstract: Methods, systems, and apparatus for updating machine learning models to improve locality are described. In one aspect, a method includes receiving data of a machine learning model. The data represents operations of the machine learning model and data dependencies between the operations. Data specifying characteristics of a memory hierarchy for a machine learning processor on which the machine learning model is going to be deployed is received. The memory hierarchy includes multiple memories at multiple memory levels for storing machine learning data used by the machine learning processor when performing machine learning computations using the machine learning model. An updated machine learning model is generated by modifying the operations and control dependencies of the machine learning model to account for the characteristics of the memory hierarchy. Machine learning computations are performed using the updated machine learning model.

Abstract: A method, computer program product, and system includes a processor(s) obtaining real time data related to an agricultural site by continuously monitoring remote data collection entities at the agricultural site, which include satellites, ground monitoring stations, and sensors. The processor(s) determine which data of the real time data can be utilized in subsequent decisions and accumulate a portion of the real time data in a data store, based on a timestamp of the portion indicating that the portion of the real time data is no longer current and is historical data. Based on obtaining a request for a recommendation, the processor(s) generate based on a cognitive analysis of the historical data, the real time data that can be utilized, and the agricultural data from the controlled environment, at least one agricultural model. The processor(s) determine the recommendation from the model and transmit the recommendation to the client.

Abstract: An integrated artificial neuron device includes an input signal node, an output signal node and a reference supply node. An integrator circuit receives and integrates an input signal to produce an integrated signal. A generator circuit receives the integrated signal and, when the integrated signal exceeds a threshold, delivers the output signal. The integrator circuit includes a main capacitor coupled between the input signal node and the reference supply node. The generator circuit includes a main MOS transistor coupled between the input signal node and the output signal node. The main MOS transistor has a gate that is coupled to the output signal node, and a substrate that is mutually coupled to the gate.

Abstract: Disclosed herein are techniques for classifying data with a data processing circuit. In one embodiment, the data processing circuit includes a probabilistic circuit configurable to generate a decision at a pre-determined probability, and an output generation circuit including an output node and configured to receive input data and a weight, and generate output data at the output node for approximating a product of the input data and the weight. The generation of the output data includes propagating the weight to the output node according a first decision of the probabilistic circuit. The probabilistic circuit is configured to generate the first decision at a probability determined based on the input data.

Abstract: A neuromorphic device is provided. The neuromorphic device may include a plurality of pre-synaptic neuron circuits, a plurality of post-synaptic neuron circuits, and a plurality of synapses. Each of the synapses may be electrically connected to the plurality of pre-synaptic neuron circuits and a corresponding one of the plurality of post-synaptic neuron circuits. Each of the plurality of synapses may include a plurality of synapse cells. Each of the synapse cells may be electrically connected to a corresponding one of the plurality of pre-synaptic neuron circuits through a corresponding one of a plurality of row lines, respectively. Each of the synapse cells may be electrically connected to the corresponding one of the plurality of post-synaptic neuron circuits through one common column line.

Abstract: Disclosed herein is a neuromorphic integrated circuit, including in many embodiments, a neural network disposed in a multiplier array in a memory sector of the integrated circuit, and a plurality of multipliers of the multiplier array, a multiplier thereof including at least one transistor-based cell configured to store a synaptic weight of the neural network, an input configured to accept digital input pulses for the multiplier, an output configured to provide digital output pulses of the multiplier, and a charge integrator, where the charge integrator is configured to integrate a current associated with an input pulse of the input pulses over an input pulse width thereof, and where the multiplier is configured to provide an output pulse of the output pulses with an output pulse width proportional to the input pulse width.

Abstract: Embodiments of the present invention are directed to a computer-implemented machine-learning method and system for automatically creating and updating tasks by reading signals from external data sources and understanding what users are doing. Embodiments of the present invention are directed to a computer-implemented machine-learning method and system for automatically completing tasks by reading signals from external sources and understanding when an existing task has been executed. Tasks created are representable and explainable in a human readable format that can be shown to users and used to automatically fill productivity applications including but not limited to task managers, to-do lists, project management, time trackers, and daily planners. Tasks created are representable in a way that can be interpreted by a machine such as a computer system or an artificial intelligence so that external systems can be delegated or connected to the system.

Abstract: Mapping of logical neural cores to physical neural cores is provided. In various embodiments, a neural network description describing a plurality of logical cores is read. A plurality of precedence relationships is determined among the plurality of logical cores. Based on the plurality of precedence relationships, a directed acyclic graph among the plurality of logical cores is generated. By breadth first search of the directed acyclic graph, a schedule is generated. The schedule maps each of the plurality of logical cores to one of a plurality of physical cores at one of a plurality of time slices. Execution of the schedule is simulated.

Abstract: Deep reinforcement learning of cooperative neural networks can be performed by obtaining an action and observation sequence including a plurality of time frames, each time frame including action values and observation values. At least some of the observation values of each time frame of the action and observation sequence can be input sequentially into a first neural network including a plurality of first parameters. The action values of each time frame of the action and observation sequence and output values from the first neural network corresponding to the at least some of the observation values of each time frame of the action and observation sequence can be input sequentially into a second neural network including a plurality of second parameters. An action-value function can be approximated using the second neural network, and the plurality of first parameters of the first neural network can be updated using backpropagation.

Abstract: A deep neural network models semiconductor devices. Measurements of test transistors are gathered into training data including gate and drain voltages and transistor width and length, and target data such as the drain current measured under the input conditions. The training data is converted by an input pre-processor that can apply logarithms of the inputs or perform a Principal Component Analysis (PCA). Rather than use measured drain current as the target when training the deep neural network, a target transformer transforms the drain current into a transformed drain current, such as a derivative of the drain current with respect to gate or drain voltages, or a logarithm of the derivative. Weights in the deep neural network are adjusted during training by comparing the deep neural network's output to the transformed drain current and generating a loss function that is minimized over the training data.

Abstract: Systems and methods for training a personalized Machine Learning (ML) model used to detect fall events are described herein. The methods may be implemented by one or more computing devices and may include obtaining sensor data associated with one or more activities of a user. A processed or unprocessed version of at least a copy of the sensor data having been fed to a personalized ML model associated with the user and that has been determined not to be associated with a fall event; and using the obtained sensor data training the personalized ML model.

Abstract: One embodiment provides for a graphics processing unit to accelerate machine-learning operations, the graphics processing unit comprising a multiprocessor having a single instruction, multiple thread (SIMT) architecture, the multiprocessor to execute at least one single instruction; and a first compute unit included within the multiprocessor, the at least one single instruction to cause the first compute unit to perform a two-dimensional matrix multiply and accumulate operation, wherein to perform the two-dimensional matrix multiply and accumulate operation includes to compute a 32-bit intermediate product of 16-bit operands and to compute a 32-bit sum based on the 32-bit intermediate product.

Abstract: A system is described that determines, based on information associated with a user of a computing device, an event for initiating an interaction between the user and an assistant executing at the computing device. The system selects, based on the event and from a plurality of actions performed by the assistant, at least one action associated with the event. The system determines, based on the at least one action, whether to output a notification of the event which includes an indication of the event and a request to perform the at least one action associated with the event. Responsive to determining to output the notification of the event, the system sends, to the assistant, the notification of the event for output during the interaction between the user and the assistant.