Abstract: A neuromorphic chip includes synaptic cells including respective resistive devices, axon lines, dendrite lines and switches. The synaptic cells are connected to the axon lines and dendrite lines to form a crossbar array. The axon lines are configured to receive input data and to supply the input data to the synaptic cells. The dendrite lines are configured to receive output data and to supply the output data via one or more respective output lines. A given one of the switches is configured to connect an input terminal to one or more input lines and to changeably connect its one or more output terminals to a given one or more axon lines.

Abstract: In some aspects, the disclosure is directed to methods and systems for a dynamic, reconfigurable virtual reality environment with in-environment access to external data and resources. Implementations of these systems also provide an external mechanism for modifying other aspects of the virtual reality experience with no need to recode or compile the experience. This can alter the primary flow of the experience, change its behavior based on the specific user accessing it and add branded or customer-specific aspects to the application. The same level or environment can provide drastically different experiences for various users from beginners through experts, even allowing the option of random or ordered events, controllable by an instructor or administrator, through simple configuration.

Abstract: Disclosed herein is a system and method for Natural Language Processing (NLP) of real world documents. The system and method combine various models not previously combined and overcome the challenges of this combination. Models include an encoder-decoder model, a spatial model, and a multi-modal model.

Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix.

Abstract: An improved computer implemented method and corresponding systems and computer readable media for improving performance of a deep neural network are provided to mitigate effects related to catastrophic forgetting in neural network learning. In an embodiment, the method includes storing, in memory, logits of a set of samples from a previous set of tasks (D1); and maintaining classification information from the previous set of tasks by utilizing the logits for matching during training on a new set of tasks (D2).

Abstract: A method, system, and computer program product for augmented reality-based environmental parameter filtering are provided. The method determines an environmental parameter by a wearable augmented reality (AR) device. A visualization of the environmental parameter is generated on a display of the wearable AR device. The method generates a set of control options on the display of the wearable AR device. The set of control options are configured to modify the environmental parameter. A user interaction with the wearable AR device is detected. The user interaction selects a control option of the set of control options. The method interacts with an external device to modify the environmental parameter based on the selected control option.

Abstract: A Magnetic Tunnel Junction (MTJ) device can include a reference magnetic layer having one or more trenches disposed therein. One or more sections of a tunnel barrier layer can be disposed on the walls of the one or more trenches. One or more sections of a free magnetic layer can be disposed on the one or more sections of the tunnel barrier layer in the one or more trenches. One or more sections of a conductive layer can be disposed on the one or more sections of the free magnetic layer in the one or more trenches. One or more insulator blocks can be disposed between corresponding sections of the tunnel barrier layer, corresponding sections of the free magnetic layer and corresponding sections of the conductive layer in the one or more trenches.

Abstract: A Magnetic Tunnel Junction (MTJ) device can include a reference magnetic layer having one or more trenches disposed therein. One or more sections of a tunnel barrier layer can be disposed on the walls of the one or more trenches. One or more sections of a free magnetic layer can be disposed on the one or more sections of the tunnel barrier layer in the one or more trenches. One or more sections of a conductive layer can be disposed on the one or more sections of the free magnetic layer in the one or more trenches. One or more insulator blocks can be disposed between corresponding sections of the tunnel barrier layer, corresponding sections of the free magnetic layer and corresponding sections of the conductive layer in the one or more trenches.

Abstract: Integrated capacitor including a first electrode structure, a second electrode structure, and an interposed dielectric layer structure. The dielectric layer structure includes a layer combination having an SiO2 layer, an Si3N4 layer, and an SixNy layer. The SixNy layer includes a non-stoichiometric silicon nitride material with an increased proportion of silicon.

Abstract: A system for generating an augmented reality image using an initial image comprising a reference element, the system comprising: an image analyzer for identifying the reference element within the initial image; an image generating unit for: generating a simulation image of a scene of a virtual environment based on the identified reference element, an outline of the simulation image corresponding to the reference outline; overlaying the initial image with the simulation image to obtain the augmented reality image; and providing the augmented reality image for display.

Abstract: In some embodiments, a computer system receives data representing a pose of at least a first portion of a user and causes presentation of an avatar that includes a respective avatar feature corresponding to the first portion of the user and presented having a variable display characteristic that is indicative of a certainty of the pose of the first portion of the user. In some embodiments, a computer system receives data indicating current activity of one or more users is activity of a first type and, in response, updates a representation of a user having a first appearance based on a first appearance template. The system receives second data indicating current activity of the one or more users and, in response, updates the appearance of the representation of the first user based on the current activity of the one or more users using the first or a second appearance template.

Abstract: The present disclosure provides directed to new, more efficient neural network architectures. As one example, in some implementations, the neural network architectures of the present disclosure can include a linear bottleneck layer positioned structurally prior to and/or after one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. As another example, in some implementations, the neural network architectures of the present disclosure can include one or more inverted residual blocks where the input and output of the inverted residual block are thin bottleneck layers, while an intermediate layer is an expanded representation. For example, the expanded representation can include one or more convolutional layers, such as, for example, one or more depthwise separable convolutional layers. A residual shortcut connection can exist between the thin bottleneck layers that play a role of an input and output of the inverted residual block.

Abstract: An artificial intelligence system includes a neural network layer including an arithmetic operation circuit that performs an arithmetic operation of a sigmoid function. The arithmetic operation circuit includes a first circuit configured to perform an exponent arithmetic operation using a Napier's constant e as a base and output a first calculation result when an exponent in the exponent arithmetic operation is a negative number, wherein an absolute value of the exponent is used in the exponent arithmetic operation, and a second circuit configured to subtract the first calculation result obtained by the first circuit from 1 and output the subtracted value.

Abstract: The present disclosure provides an integrated circuit chip device and a related product. The integrated circuit chip device includes: a primary processing circuit and a plurality of basic processing circuits. The primary processing circuit or at least one of the plurality of basic processing circuits includes the compression mapping circuits configured to perform compression on each data of a neural network operation. The technical solution provided by the present disclosure has the advantages of a small amount of computations and low power consumption.

Abstract: A processor implemented method to update a sentence generation model includes: generating a target sentence corresponding to a source sentence using a first decoding model; calculating reward information associated with the target sentence using a second decoding model configured to generate a sentence in an order different from an order of the sentence generated by the first decoding model; and generating an updated sentence generation model by resetting a weight of respective nodes in the first decoding model based on the calculated reward information.

Abstract: A method and system for managing a dataset. An artificial intelligence (AI) model is to be used on the dataset. A data mask describes a labeling status of the data items. A loop is repeated until patience parameters are satisfied. The loop comprises receiving trusted labels provided by trusted labelers; updating the data mask; from a labelled data items subset, training the AI model; cloning the trained AI model into a local AI model on processing nodes; creating and chunking a randomized unlabeled subset into data subsets for dispatching to the processing nodes; receiving an indication that predicted label answers have been inferred by the processing nodes using the local AI model; computing a model uncertainty measurement from statistical analysis of the predicted label answers. The patience parameters include one or more of a threshold value on the model uncertainty measurement and information gain between different training cycles.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining data identifying (i) a first observation characterizing a first state of the environment, (ii) an action performed by the agent in response to the first observation, and (iii) an actual reward received resulting from the agent performing the action in response to the first observation; determining a pseudo-count for the first observation; determining an exploration reward bonus that incentivizes the agent to explore the environment from the pseudo-count for the first observation; generating a combined reward from the actual reward and the exploration reward bonus; and adjusting current values of the parameters of the neural network using the combined reward.

Abstract: A method includes maintaining respective episodic memory data for each of multiple actions; receiving a current observation characterizing a current state of an environment being interacted with by an agent; processing the current observation using an embedding neural network in accordance with current values of parameters of the embedding neural network to generate a current key embedding for the current observation; for each action of the plurality of actions: determining the p nearest key embeddings in the episodic memory data for the action to the current key embedding according to a distance measure, and determining a Q value for the action from the return estimates mapped to by the p nearest key embeddings in the episodic memory data for the action; and selecting, using the Q values for the actions, an action from the multiple actions as the action to be performed by the agent.

Abstract: A method for time series analysis of time-oriented usage data pertaining to computing resources of a computing system. A method embodiment commences upon collecting time series datasets, individual ones of the time series datasets comprising time-oriented usage data of a respective individual computing resource. A plurality of prediction models are trained using portions of time-oriented data. The trained models are evaluated to determine quantitative measures pertaining to predictive accuracy. One of the trained models is selected and then applied over another time series dataset of the individual resource to generate a plurality of individual resource usage predictions. The individual resource usage predictions are used to calculate seasonally-adjusted resource usage demand amounts over a future time period. The resource usage demand amounts are compared to availability of the resource to form a runway that refers to a future time period when the resource is predicted to be demanded to its capacity.

Abstract: A video and audio presentation device configured to present video and audio for sports training with less delay in physical reaction is provided.