Abstract: An AI database hosted on cloud platform is configured to cooperate with a search engine and an AI engine. The AI database stores and indexes trained AI objects and its class of AI objects have searchable criteria. The AI database cooperates with the search engine to utilize search criteria supplied from a user, from either or both 1) via scripted software code and 2) via data put into defined fields of a user interface. The search engine utilizes the search criteria in order for the search engine to retrieve one or more AI data objects that have already been trained as query results. The AI database is coupled to an AI engine to allow any of reuse, reconfigure ability, and recomposition of the one or more trained AI data objects from the AI database into a new trained AI model.

Abstract: A method and associated imaging system for classifying at least one concept type in a video segment is disclosed. The method associates an object concept type in the video segment with a spatio-temporal segment of the video segment. The method then associates a plurality of action concept types with the spatio-temporal segment, where each action concept type of the plurality of action concept types is associated with a subset of the spatio-temporal segment associated with the object concept type. The method then classifies the action concept types and the object concept types associated with the video segment using a conditional Markov random field (CRF) model where the CRF model is structured with the plurality of action concept types being independent and indirectly linked via a global concept type assigned to the video segment, and the object concept type is linked to the global concept type.

Abstract: A method includes receiving N pairs of training examples and class labels therefor. Each pair includes a respective anchor example, and a respective non-anchor example capable of being a positive or a negative training example. The method further includes extracting features of the pairs by applying a DHCNN, and calculating, for each pair based on the features, a respective similarly measure between the respective anchor and no example. The method additionally includes calculating a similarity score based on the respective similarity measure for each pair. The score represents similarities between all anchor points and positive training examples in the pairs relative to similarities between all anchor points and negative training examples in the pairs. The method further includes maximizing the similarity score for the anchor example for each pair to pull together the training examples from a same class while pushing apart the training examples from different classes.

Abstract: A spiking neural network (SNN) is implemented on a neuromorphic computers and includes a plurality of neurons, a first set of the plurality of synapses defining feed-forward connections from a first subset of the neurons to a second subset of the neurons, a second subset of the plurality of synapses to define recurrent connections between the second subset of neurons, and a third subset of the plurality of synapses to define feedback connections from the second subset of neurons to the first subset of neurons. A set of input vectors are provided to iteratively modify weight values of the plurality of synapses. Each iteration involves selectively enabling and disabling the third subset of synapses with a different one of the input vectors applied to the SNN. The weight values are iteratively adjusted to derive a solution to an equation comprising an unknown matrix variable and an unknown vector variable.

Abstract: A neuromorphic device may include: a plurality of pre-synaptic neurons; row lines extending in a row direction from the plurality of pre-synaptic neurons; a plurality of post-synaptic neurons; column lines extended in a column direction from the plurality of post-synaptic neurons; a plurality of synapses arranged at intersections between the row lines and the column lines; a plurality of first control blocks; and first control lines extending from the control blocks. The first control lines may be electrically connected to the plurality of synapses.

Abstract: A multi-layer artificial neural network having at least one high-speed communication interface and N computational layers is provided. N is an integer larger than 1. The N computational layers are serially connected via the at least one high-speed communication interface. Each of the N computational layers respectively includes a computation circuit and a local memory. The local memory is configured to store input data and learnable parameters for the computation circuit. The computation circuit in the ith computational layer provides its computation results, via the at least one high-speed communication interface, to the local memory in the (i+1)th computational layer as the input data for the computation circuit in the (i+1)th computational layer, wherein i is an integer index ranging from 1 to (N?1).

Abstract: The present disclosure provides systems and methods that enable adaptive training of a channel coding model including an encoder model, a channel model positioned structurally after the encoder model, and a decoder model positioned structurally after the channel model. The channel model can have been trained to emulate a communication channel, for example, by training the channel model on example data that has been transmitted via the communication channel. The channel coding model can be trained on a loss function that describes a difference between input data input into the encoder model and output data received from the decoder model. In particular, such a loss function can be backpropagated through the decoder model while modifying the decoder model, backpropagated through the channel model while the channel model is held constant, and then backpropagated through the encoder model while modifying the encoder model.

Abstract: A method for generating a dual-class dataset is disclosed. A single-class dataset and a context dataset are obtained. The context dataset can be labeled. A model can be trained using the combination of the single-class dataset and the labeled context dataset. The model can be run on the context dataset. The data points that are classified the same as the data points included in the single-class dataset, can be removed from the labeled context dataset and added to the single-class dataset. These steps can be repeated until no data points are classified by the model.

Abstract: Methods, apparatus, systems, and articles of manufacture to enable status change detection in a low power mode of a microcontroller unit are disclosed herein. An example integrated circuit (IC) includes a controller to determine that the IC is to enter a low power mode. The example IC includes a universal serial bus (USB) physical layer integrated circuit including a transceiver and a detector circuit. The transceiver is disabled while in the low power mode. The detector circuit is enabled while in the low power mode. The detector circuit is to determine whether a pinout of a USB receptacle is shorted to ground. The example IC includes a power control module (PCM) to disable the controller when entering the low power mode. Upon receipt of an indication that the ID pinout of the USB receptacle is shorted to the ground, the PCM initiates a boot sequence.

Abstract: A memory device can include: a non-volatile storage register configured to store an active reset polling enable bit that corresponds to a reset operation; a controller configured to control execution of the reset operation on the memory device; an operation completion indicator configured to provide a reset recovery indication external to the memory device when the reset operation has completed and the active reset polling enable bit is set; and a command decoder configured to receive a command to be executed on the memory device in response to the reset recovery indication.

Abstract: A method and an apparatus for detecting changed data are provided. The method includes: recording change status information of each data field in a data table during a version change; obtaining a probability of a second data field being changed simultaneously when a first data field is changed, the probability being a confidence probability of the second data field being changed in the first data field being changed; determining, when confidence probabilities of at least two second data fields being changed in the same first data field being changed are greater than a confidence probability threshold of the data table, that the second data fields corresponding to the confidence probabilities greater than the confidence probability threshold are a combined field; determining whether a combination of the changed data fields matches a combined field template during the current version change, and prompting a location of the unmatched changed data field.

Abstract: An AI database hosted on cloud platform is configured to cooperate with a search engine and an AI engine. The AI database stores and indexes trained AI objects and its class of AI objects have searchable criteria. The AI database cooperates with the search engine to utilize search criteria supplied from a user, from either or both 1) via scripted software code and 2) via data put into defined fields of a user interface. The search engine utilizes the search criteria in order for the search engine to retrieve one or more AI data objects that have already been trained as query results. The AI database is coupled to an AI engine to allow any of reuse, reconfigure ability, and recomposition of the one or more trained AI data objects from the AI database into a new trained AI model.

Abstract: A memory management system, and method of operation thereof, includes: a primary device of a resilient storage module configured as a boot device for booting a computer system; an operational status received from the computer system; a secondary device of the resilient storage module configured as the boot device based on the operational status indicating a non-operational state; and a memory module controller of the resilient storage module for initiating a reboot operation using the secondary device as the boot device.

Abstract: Systems and methods for determining neural network brittleness are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a modeling request comprising a preliminary model and a dataset. The operations may include determining a preliminary brittleness score of the preliminary model. The operations may include identifying a reference model and determining a reference brittleness score of the reference model. The operations may include comparing the preliminary brittleness score to the reference brittleness score and generating a preferred model based on the comparison. The operations may include providing the preferred model.

Abstract: A system and method for optimizing customer magnetic resonance systems is provided. An automation system gathers data from a geographically dispersed network of installed magnetic resonance systems, which data is mined and analyzed in order to recognize patterns about the best practices of the installed base. Customer-specific variables for customer magnetic resonance systems are then optimized, based on the recognized patterns. More particularly, customer specific protocols and hardware/software configurations can be calculated and optimized, by making use of data mined from best-in-class customers having similar profiles.

Abstract: The present disclosure provides systems and methods that leverage machine learning to perform user input motion prediction. In particular, the systems and methods of the present disclosure can include and use a machine-learned motion prediction model that is trained to receive motion data indicative of motion of a user input object and, in response to receipt of the motion data, output predicted future locations of the user input object. The user input object can be a finger of a user or a stylus operated by the user. The motion prediction model can include a deep recurrent neural network.

Abstract: A recognition apparatus and a training method are provided. The recognition apparatus includes a memory configured to store a neural network including a previous layer of neurons, and a current layer of neurons that are activated based on first synaptic signals and second synaptic signals, the first synaptic signals being input from the previous layer, and the second synaptic signals being input from the current layer. The recognition apparatus further includes a processor configured to generate a recognition result based on the neural network. An activation neuron among the neurons of the current layer generates a first synaptic signal to excite or inhibit neurons of a next layer, and generates a second synaptic signal to inhibit neurons other than the activation neuron in the current layer.

Abstract: A neuromorphic device may include: a pre-synaptic neuron; a plurality of post-synaptic neurons; and a plurality of synapses electrically connected to the pre-synaptic neuron and electrically connected to the plurality of post-synaptic neurons. Each of the post-synaptic neurons may include: an integrator; a main comparator having a first input port connected to an output port of the integrator; and a first sub comparator having a first input port connected to the output port of the integrator.

Abstract: Described herein are systems and methods that address the task of learning novel visual concepts, and their interactions with other concepts, from a few images with sentence descriptions. Using linguistic context and visual features, embodiments are able to efficiently hypothesize the semantic meaning of new words and add them to model word dictionaries so that they can be used to describe images which contain these novel concepts. In the experiments, it was shown that the tested embodiments effectively learned novel visual concepts from a few examples without disturbing the previously learned concepts.

Abstract: Systems, methods and computer program products for processing natural language input are provided. Natural language input is processed by one or more processing rules. The processing rules may specify one or more actions to be performed. The processing rules may alternatively or additionally split up the natural language input into a plurality of simpler sub-inputs, each of which may then be processed by one or more processing rules. The processing rules themselves may be generalized, which generalization may be based on user input. In the event that a suitable processing rule cannot be found, a request may be made to a user to provide instructions for processing the natural language input.