Abstract: Computer-implemented machines, systems and methods for providing insights about a machine learning model, the machine learning model trained, during a training phase, to learn patterns to correctly classify input data associated with risk analysis. Analyzing one or more features of the machine learning model, the one or more features being defined based on one or more constraints associated with one or more values and relationships and whether said one or more values and relationships satisfy at least one of the one or more constraints. Displaying one or more visual indicators based on an analysis of the one or more features and training data used to train the machine learning model, the one or more visual indicators providing a summary of the machine learning model's performance or efficacy.

Abstract: A neural processing unit includes a mode selector configured to select a first mode or a second mode; and processing element (PE) array operating in one of the first mode and the second mode and including a plurality of processing elements arranged in PE rows and PE columns, the PE array configured to receive an input of first input data and an input of second input data, respectively. In the second mode, the first input data is inputted in a PE column direction of the PE array and is transmitted along the PE column direction while being delayed by a specific number of clock cycles, and the second input data is broadcast to the plurality of processing elements of the PE array to which the first input data is delayed by the specific number of clock cycles.

Abstract: An electronic device that includes a processor configured to execute training iterations during a training process for a neural network, each training iteration including processing a separate instance of training data through the neural network, and a sparsity monitor is described. During operation, the sparsity monitor acquires, during a monitoring interval in each of one or more monitoring periods, intermediate data output by at least some intermediate nodes of the neural network during training iterations that occur during each monitoring interval. The sparsity monitor then generates, based at least in part on the intermediate data, one or more values representing sparsity characteristics for the intermediate data. The sparsity monitor next sends, to the processor, the one or more values representing the sparsity characteristics and the processor controls one or more aspects of executing subsequent training iterations based at least in part on the values representing the sparsity characteristics.

Abstract: A recognition method includes extracting target data corresponding to a current window and padding data subsequent to the target data from sequence data; acquiring a state parameter corresponding to a previous window; and calculating a recognition result for the current window based on the state parameter, the extracted target data, and the extracted padding data using a recurrent model.

Abstract: A facility for generating monotonic fully connected layer blocks for a machine learning model is described. The facility receives an indication of a convex constituent monotonically increasing activation function and a concave constituent monotonically increasing activation function for a monotonic layer. The facility generates a composite monotonic activation function made up of the convex and concave constituent activation functions. The facility receives an indication of a monotonicity indicator vector for the monotonic dense layer block. The facility determines one or more selector weights for the composite activation function. The facility initializes a sign for each weight of one or more kernel weights included in the monotonic layer and initializes a bias vector. The facility generates the monotonic dense layer block based on the composite activation function, the monotonicity indicator vector, the selector weights, the sign for each kernel weight, and the bias vector.

Abstract: Techniques are provided for selection of machine learning algorithms based on performance predictions by trained algorithm-specific regressors. In an embodiment, a computer derives meta-feature values from an inference dataset by, for each meta-feature, deriving a respective meta-feature value from the inference dataset. For each trainable algorithm and each regression meta-model that is respectively associated with the algorithm, a respective score is calculated by invoking the meta-model based on at least one of: a respective subset of meta-feature values, and/or hyperparameter values of a respective subset of hyperparameters of the algorithm. The algorithm(s) are selected based on the respective scores. Based on the inference dataset, the selected algorithm(s) may be invoked to obtain a result. In an embodiment, the trained regressors are distinctly configured artificial neural networks. In an embodiment, the trained regressors are contained within algorithm-specific ensembles.

Abstract: A method and system is disclosed for training a machine learning model by generating first training input that includes a first number of reports at a first point in time. The reports are submitted by the users of the gaming platform and identify incidents where content of the gaming platform violates a policy of use associated with the gaming platform. The method and system generates second training input including a number of resources active at the first point in time. The method and system generates first target output identifies a number of resources sufficient to evaluate the target percentage of the first number of reports. The method and system provide the training data to train the machine learning model on (i) a set of training inputs comprising the first training input and the second training input, and (ii) a set of target outputs comprising the first target output.

Abstract: A neuromorphic system includes a first neuromorphic layer configured to perform a forward operation with an input signal and a first weight, a first operation circuit configured to perform a first operation on a result of the forward operation of the first neuromorphic layer, a second neuromorphic layer configured to perform a forward operation with an output signal of the first operation circuit and a second weight, a second operation circuit configured to perform a second operation on a result of the forward operation of the second neuromorphic layer, a first weight adjustment amount calculation circuit configured to calculate a first weight adjustment amount, and a second weight adjustment amount calculation circuit configured to calculate a second weight adjustment amount.

Abstract: A method of forming a neural network includes specifying layers of neural network neurons. A parameter genome is defined with numerical parameters characterizing connections between neural network neurons in the layers of neural network neurons, where the connections are defined from a neuron in a current layer to neurons in a set of adjacent layers, and where the parameter genome has a unique representation characterized by kilobytes of numerical parameters. Parameter genomes are combined into a connectome characterizing all connections between all neural network neurons in the connectome, where the connectome has in excess of millions of neural network neurons and billions of connections between the neural network neurons.

Abstract: A method and an apparatus for recognizing an intention, and a non-transitory computer-readable recording medium are provided.

Abstract: A method of training and using a machine learning model that controls for consideration of undesired factors which might otherwise be considered by the trained model during its subsequent analysis of new data. For example, the model may be a neural network trained on a set of training images to evaluate an insurance applicant based upon an image or audio data of the insurance applicant as part of an underwriting process to determine an appropriate life or health insurance premium. The model is trained to probabilistically correlate an aspect of the applicant's appearance with a personal and/or health-related characteristic. Any undesired factors, such as age, sex, ethnicity, and/or race, are identified for exclusion. The trained model receives the image (e.g., a “selfie”) of the insurance applicant, analyzes the image without considering the identified undesired factors, and suggests the appropriate insurance premium based only on the remaining desired factors.

Abstract: Aspects of the disclosure generally relate to computing devices and/or systems, and may be generally directed to devices, systems, methods, and/or applications for learning an avatar's or an application's operation in various circumstances, storing this knowledge in a knowledgebase (i.e. neural network, graph, sequences, etc.), and/or enabling autonomous operation of the avatar or the application.

Abstract: Provided is an intelligent analysis system for inner detecting magnetic flux leakage (MFL) data in pipelines, including a complete data set building module, a discovery module, a quantization module and a solution module, wherein: a complete data set building method is adopted in the complete data set building module to obtain a complete magnetic flux leakage data set; a pipeline connecting component discovery method is adopted in the discovery module to obtain the precise position of a weld; an anomaly candidate region search and identification method is adopted in the discovery model to find out magnetic flux leakage signals with defects; a defect quantization method based on a random forest is adopted in the quantization module to obtain a defect size; and a pipeline solution based on an improved ASME B31G standard is adopted in the solution module to output an evaluation result.

Abstract: Some embodiments provide a method for configuring a machine-trained (MT) network that includes multiple configurable weights to train. The method propagates a set of inputs through the MT network to generate a set of output probability distributions. Each input has a corresponding expected output probability distribution. The method calculates a value of a continuously-differentiable loss function that includes a term approximating an extremum function of the difference between the expected output probability distributions and generated set of output probability distributions. The method trains the weights by back-propagating the calculated value of the continuously-differentiable loss function.

Abstract: Disclosed systems and methods predict and visualize outcomes based on past events. For example, an analysis application encodes a sequence of events into a feature vector that includes, for each event, a numerical representation of a respective category and a respective timestamp. The application applies a time-aware recurrent neural network to the feature vector, resulting in one or more of (i) a set of future events in which each event is associated with a probability and a predicted duration and (ii) a sequence embedding that contains information about predicted outcomes and temporal patterns observed in the sequence of events. The application applies a support vector model classifier to the sequence embedding. The support vector model classifier computes a likelihood of a categorical outcome for each of the events in the probability distribution. The application modifies interactive content according to the categorical outcomes and probability distribution.

Abstract: A processor-implemented method for generating a multi-dimensional risk profiling data structure includes identifying one or more dimensions common to a plurality of risks along which all of the plurality of risks may be aggregated, assigning the one or more common dimensions to a top level cube structure, identifying a set of dimensions and risk drivers specific to each of the plurality of risks, and assigning each set of dimensions and risk drivers to each of a plurality of second level cubes.

Abstract: An information processing device according to one embodiment includes a processor. The processor executes an acquisition step of acquiring a plurality of partial layers as a gene pool, the partial layers being candidates for elements of a deep learning model, a generation step of generating a new partial layer from the gene pool by using genetic programming, an evaluation step of evaluating each partial layer by incorporating, into a template of the deep learning model, each partial layer in the gene pool to which the new partial layer is added, and determining a plurality of partial layers to remain in the gene pool, and an output step of outputting the deep learning model into which the partial layer with a highest evaluation value is incorporated.

Abstract: A method and system for teaching an artificial intelligent agent includes giving the agent several examples where it can learn to identify what is important about these example states. Once the agent has the ability to recognize a goal configuration, it can use that information to then learn how to achieve the goal states on its own. An agent may be provided with positive and negative examples to demonstrate a goal configuration. Once the agent has learned certain goal configurations, the agent can learn an option to achieve the goal configuration and a distance function that predicts at least one of a distance and a duration to the goal configuration under the learned option. This distance function prediction may be incorporated as a state feature of the agent.

Abstract: An indication of a plurality of different entities in a social networking service is received, including at least two entities having a different entity type. A plurality of user profiles in the social networking service is accessed. A first machine-learned model is used to learn embeddings for the plurality of different entities in a d-dimensional space. A second machine-learned model is used to learn an embedding for each of one or more query terms that are not contained in the indication of the plurality of different entities in the social networking service, using the embeddings for the plurality of different entities learned using the first machine-learned model, the second-machine learned model being a deep structured semantic model (DSSM). A similarity score between a query term and an entity is calculated by computing distance between the embedding for the query term and the embedding for the entity in the d-dimensional space.

Abstract: A system may include multiple client devices and a processing device communicatively coupled to the client devices. Each client device includes an artificial intelligence (AI) chip and is configured to generate an AI model. The processing device may be configured to (i) receive a respective AI model and an associated performance value of the respective AI model from each of the plurality of client devices; (ii) determine an optimal AI model based on the performance values associated with the respective AI models from the plurality of client devices; and (iii) determine a global AI model based on the optimal AI model. The system may load the global AI model into an AI chip of a client device to cause the client device to perform an AI task based on the global AI model in the AI chip. The AI model may include a convolutional neural network.