Abstract: A computer implemented method includes identifying, by one or more processors, a decision tree corresponding to an artificial intelligence model, detecting, by one or more processors, new data associated with an update to the identified decision tree, identifying, by one or more processors, counterfactual data corresponding to the new data, identifying, by one or more processors, one or more expected outcomes corresponding to the counterfactual data and the new data, and generating, by one or more processors, an updated decision tree based on the identified new data and the identified counterfactual data. A computer program product and computer system corresponding to the method are also disclosed.

Abstract: One example method includes deploying, in a production environment, a machine learning model that was trained using metadata created by an intermediate classical computing layer, and the metadata comprises information about one or more aspects of a quantum circuit, generating, with the machine learning model, a prediction as to how one or more computing infrastructures may be expected to perform when executing the quantum circuit, based on the prediction, making an orchestration decision concerning the quantum circuit, and orchestrating the quantum circuit to one of the computing infrastructures.

Abstract: This disclosure provides an accurate and personalized recommendation method based on a knowledge graph, which includes following steps: acquiring relevant knowledge of objects from a knowledge base according to historical behaviors of a user, and constructing a knowledge graph; initializing a vector representation of each node and its connection, and determining a receptive field of the node; generating training samples according to the historical behaviors of the user, and initializing a vector representation of all users and objects; acquiring a receptive field of an entity in the knowledge graph corresponding to the object in the training sample, then inputting the receptive field and the training sample to a graph neural network model to obtain predicted values of a possibility of an interaction between the user and the object.

Abstract: Systems and techniques that facilitate quantum-enhanced features for classical machine learning are provided. In various embodiments, a system can comprise a receiver component that can access a classical dataset. In various aspects, the system can further comprise a feature component that can generate one or more machine learning input features based on a quantum transformation of the classical data set. In various instances, the system can further comprise an execution component that can execute a classical machine learning model on the one or more machine learning input features.

Abstract: A computer implemented method obtains neural network-based model base model weight matrices for each of multiple neural network layers. First low-rank factorization matrices are added to corresponding base model weight matrices to form a first domain model. The low-rank factorization matrices are treated as trainable parameters. The first domain model is trained with first domain specific training data without modifying base model weight matrices.

Abstract: Methods, systems and media for computer vision using 2D convolution of 4D video data tensors are described. 3D convolution operations performed on 5D input tensors are simulated by performing 2D convolution of 4D tensors instead. A convolution block of a CNN performs two parallel operations: a spatial processing branch performs spatial feature extraction on a 4D tensor using 2D convolution, whereas a temporal processing branch performs temporal feature extraction on a different 4D tensor using 2D convolution. The output tensors of the spatial processing branch and the temporal processing branch are combined to generate an output tensor of the convolution block. The convolution block may include additional operations such as reshaping and/or further convolution operations to generate identically-sized output tensors for each branch, thereby eliminating the need for post-processing of the branches' output tensors prior to combining them.

Abstract: A computer-implemented method, a computer program product, and a computer system for recommending model contributions based on federated learning lineage. The computer system retrieves information of model checkpoints. The computer system trains data analytic models for monitoring activities of training rounds in a federated learning system, based on the information of the model checkpoints. The computer system sends to a user summary statistics of the model checkpoints. The computer system receives from the user natural language instructions of modifying a federated learning plan for future training rounds in the federated learning system. The computer system translates the natural language instructions into updates for the federated learning system. The computer system forwards the updates to the federated learning system.

Abstract: An apparatus includes a global memory and a systolic array. The global memory is configured to store and provide an input feature map (IFM) vector stream from an IFM tensor and a kernel vector stream from a kernel tensor. The systolic array is configured to receive the IFM vector stream and the kernel vector stream from the global memory. The systolic array is on-chip together with the global memory. The systolic array includes a plurality of processing elements (PEs) each having a plurality of vector units, each of the plurality of vector units being configured to perform a dot-product operation on at least one IFM vector of the IFM vector stream and at least one kernel vector of the kernel vector stream per unit clock cycle to generate a plurality of output feature maps (OFMs).

Abstract: An apparatus, method and computer program is described comprising: determining an initial performance of a first model, wherein determining the initial performance comprises deploying the first model at a first device; determining one or more operations for modifying the first model based on at least the initial performance of the first model and one or more user requirements; modifying the first model by performing the one or more operations; determining whether a performance of the modified first model satisfies the one or more user requirements, wherein the determining comprises deploying the modified first model at the first device; and in the event that the modified first model does not satisfy the one or more user requirements, further modifying the first model by performing one or more further operations until the performance of the modified first model satisfies the one or more user requirements, wherein the determining further one or more operations based on at least the performance of the modified f

Abstract: In one aspect, a computerized method of an artificial neural network model for implementing a distribution of automated interactions with network effects and n-tiered incentives via an interactive network comprising: training one or more artificial neural network models to automatically: establish a set of specified system-wide data center parameters, wherein the artificial neural network model is trained on a set of existing data sets and is used to automatically determine the specified system-wide data center parameters, receive an item added by a user added to the interactive network, wherein for each item added by the user adds to the system, the user assigns a specific goal, provide a set of data for each specific goals, generate a specified goal algorithm for each goal described by the user, automatically establish a distribution with a plurality of network effects and n-tiered incentives for each item the user adds, and for each transaction related to the item that occurs in the interactive network, ap

Abstract: The present disclosure relates to an apparatus and a method for computing a neural network, a board card, and a readable storage medium. The computing apparatus of the present disclosure is included in an integrated circuit apparatus. The integrated circuit apparatus includes a general interconnection interface and other processing apparatus. The computing apparatus interacts with other processing apparatus to jointly complete a computing operation specified by a user. The integrated circuit apparatus further includes a storage apparatus. The storage apparatus is connected to the computing apparatus and other processing apparatus, respectively. The storage apparatus is used for data storage of the computing apparatus and other processing apparatus.

Abstract: A method and apparatus for training an online prediction model are provided. The method may include: acquiring an offline sample feature and an online sample feature of a user, the offline sample feature including a user portrait feature; offline training to obtain an offline recommendation model, based on the offline sample feature and the online sample feature of the user; acquiring a latest online feature of the user, and online training to obtain an online learning model based on the latest online feature of the user, the online learning model being used to adapt the latest online feature for use as an online sample feature to be input into the trained offline recommendation model; and synchronizing the offline recommendation model to online, and inputting the latest online feature output by the online learning model into the offline recommendation model to generate an online prediction model.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for determining a value corresponding to a composite object. Paths are determined based on initial values of underlying items of the composite object and random numbers. A DNN is trained by determining a final value for each path based on a final set of items corresponding to the path at the final time, iterating the value backward in time using a non-linear generator function from the final value to an initial value, defining a set of initial values comprising the initial value determined for each path and determining a statistical measure based on the set of initial values, and modifying parameters of the DNN based on the statistical measure. Value information comprising the value for the composite object at one or more times is determined based on output of the DNN. The value information is provided such that a user computing device receives it.

Abstract: Systems and methods of optimizing runtime of a neural network (NN) by at least one processor may include: receiving a space of untrained NN architectures, capable of performing a predefined NN function on a given computing device, after being trained; receiving a reference accuracy metric value; evaluating a latency value for each NN architecture of the architecture space; dividing the architecture space to a plurality of groups based on said evaluated latency; performing a search among the plurality of groups, to determine a group G* that corresponds to a minimal evaluated latency, and yet comprises at least one NN architecture that maintains an accuracy metric value that is at least equal to the reference accuracy metric value; and training at least one NN architecture of the determined group G* to perform the NN function.

Abstract: A semiconductor process prediction method and a semiconductor process prediction apparatus considering overall features and local features are provided. The semiconductor manufacturing process prediction method includes the following steps. Several equipment sensing curves are obtained. The equipment sensing curves are filtered to reduce the co-linearity of the equipment sensing curves. A Dynamic Time Warping (DTW) procedure is performed to align the equipment sensing curves. The equipment sensing curves which are aligned are inputted into a Convolutional Neural Network (CNN) model to obtain a first prediction result considering the local features. A statistical analysis procedure is performed on the equipment sensing curves to obtain several statistical data. The statistical data are inputted into an Artificial Neural Network (ANN) model to obtain a second prediction result considering the overall features.

Abstract: A method, computer system, and a computer program product for published content protection is provided. The present invention may include receiving a content file from a content management system (CMS). The present invention may include extracting a feature from the received content file. The present invention may include transforming, using an adversarial generation algorithm, the received content file into an adversarial content file. The present invention may include returning the adversarial content file to the CMS. The returned adversarial content file may represent an equivalent of the received content file to a content consumer. The present invention may include preventing an application of the returned adversarial content file in at least one machine learning task based on the adversarial noise included in the returned adversarial content file.

Abstract: Various embodiments include methods and devices for identity graphing of network genomes. Embodiments may include processing a node data set having unstructured node identifiers (IDs), determining potential node IDs from the node data set, determining node counts based on the potential node IDs, and classifying probabilities of accuracy of the node counts via a node count machine learning classifier model. Embodiments may further include classifying probabilities of accuracy of node IDs via a node ID machine learning classifier model. Embodiments may further include generating a data structure associating at least a first node ID of the classified node IDs with a network equipment ID. Embodiments may further include associating a classified probability accuracy of the first node ID with the first node ID.

Abstract: A system and method for automatically generating deep neural network architectures for time series prediction. The system includes a processor for: receiving a prediction context associated with a current use case; based on the associated prediction context, selecting a prediction model network configured for a current use case time series prediction task; replicating the selected prediction model network to create a plurality of candidate prediction model networks; inputting a time series data to each of the plurality of the candidate prediction model network; train, in parallel, each respective candidate prediction model network of the plurality with the input time series data; modifying each of the plurality of the candidate prediction model network by applying a respective different set of one or more model parameters while being trained in parallel; and determine a fittest modified prediction model network for solving the current use case time series prediction task.

Abstract: A method of pruning a pre-trained model comprises the steps of (a) constructing a stochastic super net and (b) training the stochastic super net to determine a particular candidate block selection that provides an optimal level of sparsity for each of the layers based upon a cost function. The stochastic super net generally represents a layer-wise search space with a fixed macro-architecture. A number of layers of the macro-architecture and input/output dimensions of each of the layers of the macro-architecture are essentially the same as the pre-trained model. Each layer comprises a plurality of candidate blocks. A sparsity of each of the candidate blocks in a respective layer is different. A training dataset used to train the pre-trained model is used to train the stochastic super net.

Abstract: A computer implemented method includes distributing a plurality of prediction models, where each of a plurality of clients initially includes at least one associated prediction model from the plurality of prediction models, among all of the plurality of clients to provide each of the plurality of clients with each of the plurality of prediction models. The plurality of prediction models is evaluated on at least a portion of a local dataset resident on each of the plurality of clients to output a quantification indicating how each of the prediction models fit at least the portion of the local dataset of each of the plurality of clients. An ensemble model is generated by applying weights to each of the plurality of prediction models based on a value, a gradient, and a Hessian matrix of a user-defined objective.