Abstract: A computing unit for accelerating a neural network is disclosed. The computing unit may include an input unit that includes a digital-to-analog conversion unit and an analog-to-digital conversion unit that is configured to receive an analog signal from the output of a last interconnected analog crossbar circuit of a plurality of analog crossbar circuits and convert the second analog signal into a digital output vector, and a plurality of interconnected analog crossbar circuits that include the first interconnected analog crossbar circuit and the last interconnected crossbar circuits, wherein a second interconnected analog crossbar circuit of the plurality of interconnected analog crossbar circuits is configured to receive a third analog signal from another interconnected analog crossbar circuit of the plurality of interconnected crossbar circuits and perform one or more operations on the third analog signal based on the matrix weights stored by the crosspoints of the second interconnected analog crossbar.

Abstract: Computer systems and computer-implemented methods improve a base neural network. In an initial training, preliminary activations values computed for base network nodes for data in the training data set are stored in memory. After the initial training, a new node set is merged into the base neural network to form an expanded neural network, including directly connecting each of the nodes of the new node set to one or more base network nodes. Then the expanded neural network is trained on the training data set using a network error loss function for the expanded neural network.

Abstract: A method of compressing kernels comprising detecting a plurality of replicated kernels. The plurality of replicated kernels comprise kernels. The method also comprises generating a composite kernel from the replicated kernels. The composite kernel comprises kernel data and meta data indicative of the rotations applied to the composite kernel data. The method also comprises storing a composite kernel.

Abstract: Disclosed are a system and method for training and managing a prediction model, and a master apparatus and a slave apparatus for the same. there is provided a system for training and managing a prediction model, the system including a master apparatus configured to generate a prediction model, train the prediction model, and obtain the trained prediction model; and a slave apparatus configured to collect data, transmit the data to the master apparatus, receive the prediction model or the trained prediction model from the master apparatus, and operate based on the prediction model or the trained prediction model. The master apparatus is further configured to generate the prediction model or train the prediction model based on the data transmitted from the slave apparatus.

Abstract: A method includes: receiving data identifying, for each of one or more objects, a respective target location to which a robotic agent interacting with a real-world environment should move the object; causing the robotic agent to move the one or more objects to the one or more target locations by repeatedly performing the following: receiving a current image of a current state of the real-world environment; determining, from the current image, a next sequence of actions to be performed by the robotic agent using a next image prediction neural network that predicts future images based on a current action and an action to be performed by the robotic agent; and directing the robotic agent to perform the next sequence of actions.

Abstract: The present disclosure provides computing systems and methods directed to algorithms and the underlying machine learning (ML) models for evaluating similarity between graphs using graph structures and/or attributes. The systems and methods disclosed may provide advantages or improvements for comparing graphs without additional context or input from a person (e.g., the methods are unsupervised). In particular, the systems and methods of the present disclosure can operate to generate respective embeddings for one or more target graphs, where the embedding for each target graph is indicative of a respective similarity of such target graph to each of a set of source graphs, and where a pair of embeddings for a pair of target graphs can be used to assess a similarity between the pair of target graphs.

Abstract: Methods and systems for horizontal federated learning are described. A plurality of sets of local model parameters is obtained. Each set of local model parameters was learned at a respective client. For each given set of local model parameters, collaboration coefficients are computed, representing a similarity between the given set of local model parameters and each other set of local model parameters. Updating of the sets of local model parameters is performed, to obtain sets of updated local model parameters. Each given set of local model parameters is updated using a weighted aggregation of the other sets of local model parameters, where the weighted aggregation is computed using the collaboration coefficients. The sets of updated local model parameters are provided to each respective client.

Abstract: An artificial intelligence system and a method for searching for an optimal model are provided. A method for searching for a learning mode of an artificial intelligence system includes receiving, by an operator included in a first node, first channels, deriving, by the operator included in the first node, first parameter weight indexes corresponding to weights of first parameters by calculating the first parameters corresponding to each of the received first channels with the received first channels, generating and outputting a second channel group by combining the first channel with the other channel, receiving, by an operator included in a second node, second channels included in the second channel group, and deriving, by the operator included in the second node, second parameter weight indexes corresponding to weights of second parameters by calculating the second parameters corresponding to the received second channels with the received second channels.

Abstract: Computer-implemented methods using machine learning are provided for generating an estimated cache performance of a cache configuration. A neural network is trained using, as inputs, a set of memory access parameters generated from a non-cycle-accurate simulation of a data processing system comprising the cache configuration and a cache configuration value, and using, as outputs, cache performance values generated by a cycle-accurate simulation of the data processing system comprising the cache configuration. The trained neural network is then provided with sets of memory access parameters generated from a non-cycle-accurate simulation of a proposed data processing system and a selected cache configuration and generates estimated cache performance values for that selected cache configuration.

Abstract: Media content is received for streaming to a user device. A neural network is trained based on a first portion of the media content. Weights of the neural network are updated to overfit the first portion of the media content to provide a first overfitted neural network. The neural network or the first overfitted neural network is trained based on a second portion of the media content. Weights of the neural network or the first overfitted neural network are updated to overfit the second portion of the media content to provide a second overfitted neural network. The first portion and the second portion of the media content are sent with associations to the first overfitted neural network and the second overfitted to the user equipment.

Abstract: Methods and systems are described for populating knowledge graphs. A processor can identify a set of data in a knowledge graph. The processor can identify a plurality of portions of an unannotated corpus, where a portion includes at least one entity. The processor can cluster the plurality of portions into at least one data set based on the at least one entity of the plurality of portions. The processor can train a model using the at least one data set and the set of data identified from the knowledge graph. The processor can apply the model to a set of entities in the unannotated corpus to predict unary relations associated with the set of entities. The processor can convert the predicted unary relations into a set of binary relations associated with the set of entities. The processor can add the set of binary relations to the knowledge graph.

Abstract: A method for generating a trained model is provided. The method for generating a trained model includes: receiving a learning data; generating an asymmetric multi-task feature network including a parameter matrix of the trained model which permits an asymmetric knowledge transfer between tasks and a feedback matrix for a feedback connection from the tasks to features; computing a parameter matrix of the asymmetric multi-task feature network using the input learning data to minimize a predetermined objective function; and generating an asymmetric multi-task feature trained model using the computed parameter matrix as the parameter of the generated asymmetric multi-task feature network.

Abstract: A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.

Abstract: A method includes defining a first virtual being (e.g., including sensory locations for sensors, sense locations for sense properties, artificial neural networks connecting sensors to sense properties) in a virtual environment. The method also includes defining an object (e.g., including sense locations) in the virtual environment. The method also includes, in accordance with an interaction between the virtual being and the object, receiving sensory input at a first sensor at a first sensory location using a first virtual medium according to a first sense property of the object at a first sense location. The first sensor, the first virtual medium, and the first sense property have a same sensory type. According to the received sensory input, a first artificial neural network translates the received sensory input into updates to one or more configuration parameters of sensors of the first virtual being or movement of the virtual being.

Abstract: A plant control supporting apparatus includes a segment selector configured to select, from among a plurality of segments defined in a plant, a segment for which learning for acquiring an optimal value of at least one parameter representing an operation state is executed, a reward function definer configured to define a reward function used for the learning, a parameter extractor configured to extract at least one parameter that is a target for the learning in the selected segment on the basis of input and output information of a device used in the plant and segment information representing a configuration of a device included in the selected segment, and a learner configured to perform the learning for acquiring the optimal value for each segment on the basis of the reward function and the at least one parameter.

Abstract: A computer-implemented method is provided for modified Lexicographic Reinforcement Learning. The computer implemented method includes obtaining, by a hardware processor, a sequence of tasks. Each of the tasks corresponds to, and has a one-to-one correspondence with, a respective award from among set of rewards. The method further includes performing, by the hardware processor for each of the tasks, reinforcement learning and deep learning for both of (i) one or more policies and (ii) one or more value functions, with a plurality of sets of samples. A plurality of solutions in a form of the one or more policies and the one or more value functions are parametrized by a single neural network with a selector which selects an input of the single neural network from among the plurality of sets of samples.

Abstract: A location history manager may be configured to determine a location history associated with a user, and a resource usage manager may be configured to determine a computing resource usage history associated with the user. A location monitor may be configured to determine a location of the user. A resource predictor may be configured to generate a prediction of a computing resource, based on the location history, the computing resource usage history, and the location. A resource provider may be configured to provide the computing resource, based on the prediction.