Abstract: Embodiments of the present invention disclose system to determine the best model to perform lead scoring for a given data set. The system can perform a multi-step iterative procedure including variable selection, feature set selection, training data selection, model development, model validation and process optimization. The system also performs local and global optimizations iteratively to determine the best possible model for a given scenario.

Abstract: Systems and methods for compressing target content are disclosed. In one embodiment, a system may include non-transient electronic storage and one or more physical computer processors. The one or more physical computer processors may be configured by machine-readable instructions to obtain the target content comprising one or more frames, wherein a given frame comprises one or more features. The one or more physical computer processors may be configured by machine-readable instructions to obtain a conditioned network. The one or more physical computer processors may be configured by machine-readable instructions to generate decoded target content by applying the conditioned network to the target content.

Abstract: A method of deploying a neural network on a target device method includes extracting a number of device dependent error masks from the target device, using the number of device dependent error masks in a training phase of the neural network to generate a device dependent weight matrix for the neural network, and storing the device dependent weight matrix in the target device for use by the target device to perform inference tasks using the neural network.

Abstract: A cooperative fuzzy-neural control method is designed in this present invention. Due to the difficulty for cooperatively controlling the concentrations of the dissolved oxygen and nitrate nitrogen in wastewater treatment process, a cooperative fuzzy-neural control method is investigated. In this proposed method, firstly, a interval type-2 fuzzy neural network is employed to construct the cooperative fuzzy-neural controller. Secondly, a parameter cooperative strategy is proposed to cooperatively optimize the global and local parameters of the cooperative fuzzy-neural controller to meet the control requirements. This proposed cooperative fuzzy-neural control method can cooperatively control the concentrations of the dissolved oxygen and nitrate nitrogen in wastewater treatment process. The results illustrate that the proposed cooperative fuzzy-neural control method can achieve the high control accuracy and guarantee the normal operations of wastewater treatment process under the different operation conditions.

Abstract: Systems and methods for a computer-based visual recognition based upon a spatially forked deep learning architecture, including unification of deep learning and reasoning. A method can include a primary learner with an adjacent structured memory bank that can not only predict the output from a given input, but also relate the input to all past memorized instances and help in creative understanding.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a training data set and defining a window for an initial beta value representing bias tolerated in formulating expectation conditional to each feature vector from the training data set. The conditional expectations are parallelly regularized by use of DNA computer. Amongst numerous combinations of candidate models, a best fit ensemble is produced as the machine learning model for predicting targeted outcomes based on inputs other than the training data set.

Abstract: Method and system for intelligent decision-making photonic signal processing, where the system comprises a multi-functional input unit, an electro-optical conversion module, a signal processing module, a photoelectric conversion module, a multi-functional output unit, and an artificial intelligence chip. The invention combines the advantages of photonic high-speed, wide-band, and electronic flexibility, combined with heterogeneous photoelectron hybrid integration, packaging and other processes, along with deep learning algorithm, is an intelligent electronic information system that may simultaneously realize digital and analog signal processing.

Abstract: In one aspect, a computer implemented method for translating and executing rules using a directed acyclic graph is provided. The method includes transforming a ruleset into a directed acyclic graph. The directed acyclic graph includes a plurality of nodes and a plurality of branches. The method further includes identifying similarities across the plurality of branches. The method further includes grouping branches of the directed acyclic graph based on the identified similarities. The method further includes creating a modified directed acyclic graph based on the grouping. The method further includes selecting and using a method of processing a group of the modified directed acyclic graph based on an aspect of the group.

Abstract: Disclosed is a convolutional neural network (CNN) processing apparatus and method, the apparatus configured to determine a loading space unit for at least one loading space in an input based on a height or a width for an input feature map of the input and an extent of a dimension of a kernel feature map, load target input elements corresponding to a target loading space, among the at least one loading space, from a memory and store the target input elements in an allocated input buffer having a size corresponding to the loading space unit, and perform a convolution operation between the target input elements stored in the input buffer and at least one kernel element of a kernel.

Abstract: Some embodiments provide a neural network inference circuit (NNIC) for executing a neural network that includes multiple computation nodes at multiple layers. The NNIC includes a set of clusters of core computation circuits and a channel, connecting the core computation circuits, that includes separate segments corresponding to each of the clusters. The NNIC includes a fabric controller circuit, a cluster controller circuit for each of the clusters, and a core controller circuit for each of the core computation circuits. The fabric controller circuit receives high-level neural network instructions from a microprocessor and parses the high-level neural network instructions.

Abstract: Cross-point arrays and methods of updating values of the same include input resistive processing units (RPUs), each having a settable resistance, each connected to a common node. Output RPUs each have a settable resistance and are each connected to the common node. An update switch is configured to connect an update voltage to the common node.

Abstract: A deep neural network (DNN) module is disclosed that can dynamically partition neuron workload to reduce power consumption. The DNN module includes neurons and a group partitioner and scheduler unit. The group partitioner and scheduler unit divides a workload for the neurons into partitions in order to maximize the number of neurons that can simultaneously process the workload. The group partitioner and scheduler unit then assigns a group of neurons to each of the partitions. The groups of neurons in the DNN module process the workload in their assigned partition to generate a partial output value. The neurons in each group can then sum their partial output values to generate a final output value for the workload. The neurons can be powered down once the groups of neurons have completed processing their assigned workload to reduce power consumption.

Abstract: An artificial neural network is implemented via an instruction stream. A header of the instruction stream and a format for instructions in the instruction stream are defined. The format includes an opcode, an address, and data. The instruction stream is created using the header, the opcode, the address, and the data. The artificial neural network is implemented by providing the instruction stream to a computer processor for execution of the instruction stream.

Abstract: Embodiments relate to systems, devices, and computing-implemented methods for generating domain name suggestions by obtaining a domain name suggestion input that includes textual data, segmenting the textual data into tokens, obtaining a list of possible affixes to the textual data, determining conditional probabilities for the possible affixes using a language model, ranking the list of possible affixes based on the conditional probabilities to generate a ranked list of affixes, and generating domain name suggestions based on the ranked list of affixes.

Abstract: Techniques are provided herein for creating well-balanced computer-based reasoning systems and using those to control systems. The techniques include receiving a request to determine whether to include one or more particular data elements in a computer-based reasoning model and determining two probability density or mass functions (“PDMFs”), one for the data set including the one or more particular data elements, once for the data set excluding it. Surprisal is determined based on those two PDMFs, and inclusion in the computer-based reasoning model is determined based on surprisal. A system is later controlled using the computer-based reasoning model.

Abstract: A method includes obtaining operating data associated with operation of a cross-directional industrial process controlled by at least one model-based process controller. The method also includes, during a training period, performing closed-loop model identification with a first portion of the operating data to identify multiple sets of first spatial and temporal models. The method further includes identifying clusters associated with parameter values of the first spatial and temporal models. The method also includes, during a testing period, performing closed-loop model identification with a second portion of the operating data to identify second spatial and temporal models. The method further includes determining whether at least one parameter value of at least one of the second spatial and temporal models falls outside at least one of the clusters.

Abstract: Provided are embodiments for a computer-implemented method, a system, and a computer program product for updating an analog crossbar array. Embodiment include receiving a number used in matrix multiplication to represent using pulse generation for a crossbar array, and receiving a bit-length to represent the number. Embodiments also include selecting pulse positions in a pulse sequence having the bit length to represent the number, performing a computation using the selected pulse positions in the pulse sequence, and updating the crossbar array using the computation.

Abstract: Methods and systems for dynamically reconfiguring a deep learning processor by operating the deep learning processor using a first configuration. The deep learning processor then tracking one or more parameters of a deep learning program executed using the deep learning processor in the first configuration. The deep learning processor then reconfigures the deep learning processor to a second configuration to enhance efficiency of the deep learning processor executing the deep learning program based at least in part on the one or more parameters.

Abstract: Systems and methods are disclosed for storing neural networks and weights for neural networks. In some implementations, a method is provided. The method includes storing a plurality of weights of a neural network comprising a plurality of nodes and a plurality of connections between the plurality of nodes. Each weight of the plurality of weights is associated with a connection of the plurality of connections. The neural network comprises a binarized neural network. The method also includes receiving input data to be processed by the neural network. The method further includes determining whether a set of weights of the plurality of weights comprises one or more errors. The method further includes refraining from using the set of weights to process the input data using the neural network in response to determining that the set of weights comprises the one or more errors.

Abstract: Systems and methods for generating regressors based on data sparsity using a machine learning (ML) model are described. A system is configured to provide a plurality of time series datasets to a recurrent neural network (RNN) of a machine learning (ML) model. The RNN generates one or more outputs associated with one or more time series datasets, and the system provides a first portion and a second portion of the one or more outputs to a regressor layer and a classification layer of the ML model, respectively. The regressor layer generates one or more regressors for the one or more time series datasets, and the classification layer generates one or more classifications associated with the one or more regressors (with each indicating whether an associated regressor is valid). Whether a classification indicates a regressor is valid may be based on time series data sparsity.