Abstract: Systems and methods for performing a quantization of artificial neural networks (ANNs) are provided. An example method may include receiving a description of an ANN and sets of inputs to neurons of the ANN, the description including sets of weights of the inputs, the weights being of a first data type, determining a first interval of the first data type to be mapped to a second interval of a second data type; performing computations of sums of products of the weights and the inputs to obtain a set of sum results, wherein the computations are performed using at least one number within the second interval, the number being a result of mapping of a number of the first interval to a number of the second interval, determining a measure of saturations in sum results, and adjusting, based on the measure of saturations, one of the first and second intervals.

Abstract: A factor estimation device is configured to receive information pertaining to objects, to extract state information from the information received, to identify a predetermined state pertaining to a first object from among the objects, to receive state information extracted that corresponds to the predetermined state and classify the predetermined state, to extract condition information from the information received, to identify the condition up until the predetermined state, and to receive condition information that is output by the condition-information extraction unit and corresponds to the condition identified and classify the condition identified. Subsequently, the factor estimation device is configured to estimate the condition that may result in the predetermined state on the basis of the result of classifying the predetermined state and the result of classifying the identified condition.

Abstract: A multi-layered knowledge base system and a processing method thereof are provided. In the system, semantic space learning of converting learning data into a semantic vector, which is a vector of semantic space, by learning a transformation function based on a plurality of learning data is performed. Then, relational knowledge learning of acquiring a relation between the semantic vectors by learning a relation function based on the semantic vectors obtained by the semantic space learning is performed. The acquired relation is converted into graph knowledge. The graph knowledge uses the relation as an edge and the semantic vector corresponding to the relation as a node.

Abstract: Comprehensive molecular profiling provides a wealth of data concerning the molecular status of patient samples. Such data can be compared to patient response to treatments to identify biomarker signatures that predict response or non-response to such treatments. This approach has been applied to identify biomarker signatures that strongly correlate with response of colorectal cancer patients to FOLFOX. Described herein are data structures, data processing, and machine learning models to predict effectiveness of a treatment for a disease or disorder of a subject having a particular set of biomarkers, as well as an exemplary application of such a model to precision medicine, e.g., to methods for selecting a treatment based on a molecular profile, e.g., a treatment comprising administration of 5-fluorouracil/leucovorin combined with oxaliplatin (FOLFOX) or with irinotecan (FOLFIRI).

Abstract: The present disclosure relates to a method for classifying a query information element using the similarity between the query information element and a set of support information elements. A resulting set of similarity scores is transformed using a sharpening function such that the transformed scores are decreasing as negative similarity scores increase and the transformed scores are increasing as positive similarity scores increase. A class of the query information element is determined based on the transformed similarity scores.

Abstract: Disclosed herein is a technique for implementing a framework that enables application developers to enhance their applications with dynamic adjustment capabilities. Specifically, the framework, when utilized by an application on a mobile computing device that implements the framework, can enable the application to establish predictive models that can be used to identify meaningful behavioral patterns of an individual who uses the application. In turn, the predictive models can be used to preempt the individual's actions and provide an enhanced overall user experience. The framework is configured to interface with other software entities on the mobile computing device that conduct various analyses to identify appropriate times for the application to manage and update its predictive models. Such appropriate times can include, for example, identified periods of time where the individual is not operating the mobile computing device, as well as recognized conditions where power consumption is not a concern.

Abstract: An apparatus and method for generating a solution, the apparatus including a user interface configured to receive user data, at least a processor communicatively connected to the use interface and a memory communicatively connected to the processor, the memory containing instructions configuring the processor to analyze a user interaction received through the user interface based on the user data, identify a problem as a function of the user interaction, generate a solution based on the user interaction and user data received from the user interface, wherein the solution includes a plurality of resources for addressing the problem, wherein generating a solution includes, training a web crawler configured to retrieve and index a plurality of resources, and track user progress with a solution.

Abstract: Systems and method are provided for data flattening. A corpus of data is extracted from at least one data source and stored at a data warehousing platform. A workflow is applied to the extracted corpus of data to provide a transformed corpus of data. The workflow includes a sequence of atomic functions selected from a library of atomic functions to perform an associated task on the corpus of data. The transformed corpus of data is provided from the data warehousing platform to a machine learning model as a set of training data.

Abstract: A hardware implementation of a neural network and a method of processing data in such a hardware implementation are disclosed. Input data for a plurality of layers of the network is processed in blocks, to generate respective blocks of output data. The processing proceeds depth-wise through the plurality of layers, evaluating all layers of the plurality of layers for a given block, before proceeding to the next block.

Abstract: Systems and methods include obtaining network data including first data of devices and services in the network, Performance Monitoring (PM) data associated with the devices and services and with associated timestamps, and second data including any of tickets, alarms, and events affecting some of the devices and services and with associated timestamps; obtaining one or more target events from the second data based on associated operational impact in the network; determining the PM data that is statistically correlated with the one or more target events; determining the statistically correlated PM data over a corresponding time based on the associated timestamps of the PM data and the one or more target events; and providing labels for the determined statistically correlated PM data with an associated label based on the associated target event of the one or more target events.

Abstract: Systems and methods are described for training a machine learning model using intelligently selected multiclass vectors. According to an embodiment, a processing resource of a computing system receives a first set of un-labeled feature vectors. The first set feature vectors are homomorphically translated using a T-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm to obtain a second set of feature vectors with reduced dimensionality. The second set of feature vectors are clustered to obtain an initial set of clusters using centroid-based clustering. An optimal set of clusters is identified among the initial set of clusters by performing a convex optimization process on the initial set of clusters. For each cluster of the optimal set of clusters, a representative vector from the cluster is selected for labeling.

Abstract: Embodiments may relate to a system to be used in an oscillating neural network (ONN). The system may include a control node and a plurality of nodes wirelessly communicatively coupled with a control node. A node of the plurality of nodes may be configured to identify an oscillation frequency of the node based on a weight W and an input X. The node may further be configured to transmit a wireless signal to the control node, wherein a frequency of the wireless signal oscillates based on the identified oscillation frequency. Other embodiments may be described or claimed.

Abstract: A second problem Hamiltonian may replace a first problem Hamiltonian during evolution of an analog processor (e.g., quantum processor) during a first iteration in solving a first problem. This may be repeated during a second, or further successive iterations on the first problem, following re-initialization of the analog processor. An analog processor may evolve under a first non-monotonic evolution schedule during a first iteration, and second non-monotonic evolution schedule under second, or additional non-monotonic evolution schedule under even further iterations. A first graph and second graph may each be processed to extract final states versus a plurality of evolution schedules, and a determination made as to whether the first graph is isomorphic with respect to the second graph. An analog processor may evolve by decreasing a temperature of, and a set of quantum fluctuations, within the analog processor until the analog processor reaches a state preferred by a problem Hamiltonian.

Abstract: A recommendation method includes determining one or more aspects of a first item based on at least one descriptive text of the first item. The recommendation method also includes updating a knowledge graph containing nodes that represent multiple items, multiple users, and multiple aspects. Updating the knowledge graph includes linking one or more nodes representing the one or more aspects of the first item to a node representing the first item with one or more first edges. Each of the one or more first edges identifies weights associated with (i) user sentiment about the associated aspect of the first item and (ii) an importance of the associated aspect to the first item. In addition, the recommendation method includes recommending a second item for a user with an explanation based on at least one aspect linked to the second item in the knowledge graph.

Abstract: Pathogens invade and infect humans. Understanding the infection mechanism is essential for determining targets for new therapeutics. Existing methods provide too many false positive results. A method and system for predicting protein-protein interaction between a host and a pathogen has been provided. The disclosure provides a pipeline for predicting HPIs, which is a combination of biological knowledge-based filters, domain-based filter and sequence-based predictions. Biologically feasible interactions are only possible when both the proteins share common localization and overlapping expression profiles. This observation was used as the first filter to remove biologically irrelevant HPIs. Proteins interact with each other through domains. Both interacting and non-interacting protein pairs provide valuable information about the probability of protein-protein interactions and hence both were used to derive statistical inferences to remove improbable HPIs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for executing a signal generation neural network on parallel processing hardware. One of the methods includes receiving weight matrices of a layer of a signal generation neural network. Rows of a first matrix for the layer are interleaved by assigning groups of rows of the first matrix to respective thread blocks of a plurality of thread blocks. A first subset of rows of the one or more other weight matrices are assigned to a first subset of the plurality of thread blocks and a second subset of rows of the one or more other weight matrices are assigned to a second subset of the plurality of thread blocks. The first matrix operation is performed substantially in parallel by the plurality of thread blocks. The other matrix operations are performed substantially in parallel by the plurality of thread blocks.

Abstract: Decentralized machine learning to build models is performed at nodes where local training datasets are generated. A blockchain platform may be used to coordinate decentralized machine learning (ML) over a series of iterations. For each iteration, a distributed ledger may be used to coordinate the nodes communicating via a blockchain network. A node can include self-healing features to recover from a fault condition within the blockchain network in manner that does not negatively impact the overall learning ability of the decentralized ML system. During self-healing, the node can determine that a local ML state is not consistent with the global ML state and trigger a corrective action to recover the local ML state. Thereafter, the node can generate a blockchain transaction indicating that it is in-sync with the most recent iteration of training, and informing other nodes to reintegrate the node into ML.

Abstract: An apparatus of operating a neural network is configured to compress one or more of activations or weights in one or more layer of the neural network. The activations and/or weights may be compressed based on a compression ratio or a system event. The system event may be a bandwidth condition, a power condition, a debug condition, a thermal condition or the like. The apparatus may operate the neural network to compute an inference based on the compressed activations or the compressed weights.

Abstract: An electronic apparatus for executing artificial intelligence algorithm is provided. The electronic apparatus includes a memory which stores input data and a plurality of second kernel data obtained from first kernel data, and a processor which obtains upscaled data in which at least a portion of the input data is upscaled by the first kernel data. The data is upscaled by performing a convolution operation on each of the plurality of second kernel data with the input data. Each of the plurality of second kernel data includes a different first kernel element from among a plurality of first kernel elements in the first kernel data.

Abstract: Embodiments of serial neural network configuration and processing via a common serial bus are disclosed. In some embodiments, the input data and source identification data is sent to nodes of the neural network serially. The nodes can determine whether the source identification data matches with an address for the node. If the address matches, the node can store the input data in its register for further processing. In some embodiments, the serial neural network engine can include a common serial bus that can broadcast data across multiple processor chips or cores.