Abstract: Automatic failure diagnosis and correction may be performed on trained machine learning models. Input data that causes a trained machine learning model may be identified in order to determine different model failures. The model failures may be clustered in order to determine failure scenarios for the trained machine learning model. Examples of the failure scenarios may be generated and truth labels for the example scenarios obtained. The examples and truth labels may then be used to retrain the machine learning model to generate a corrected version of the machine learning model.

Abstract: A method for predicting and controlling a water level of a series water conveyance canal on the basis of a fuzzy neural network is disclosed. The method includes: performing the relationship between a sluice opening degree and an open canal control water level by means of a fuzzy neural network, and constructing an upstream water level controller of a coupled predictive control algorithm; solving an optimal control rate of the upstream water level controller using a gradient optimization algorithm on the basis of a control target of the upstream water level controller; and generating a control strategy by collecting actually measured water level change information and multiplying the actually measured water level change information by the optimal control rate on the basis of the solved optimal control rate, thereby fulfilling the object of predicting and controlling the water level.

Abstract: A computer-implemented method of calibrating a trained classification model. The trained classification model is trained to classify input samples according to a plurality of classes and to provide associated prediction probabilities, and includes a plurality of hidden layers and at least one activation layer. The method includes accessing the trained classification model and accessing a plurality of validation samples, each validation sample having a ground-truth label, the ground-truth label indicating a ground-truth class. The method further includes applying the trained classification model to the plurality of validation samples, obtaining, for each validation sample, an output logit vector from a layer of the trained classification model preceding a last activation layer, and training a calibration module. The calibration module is trained to adjust prediction probabilities, the prediction probabilities being derived from the output logit vectors.

Abstract: Systems and/or methods may include an edge-computing distributed neural processor to effectively reduce the data traffic and physical wiring congestion. A local and global networking architecture may reduce traffic among multi-chips in edge computing. A mixed-signal feature extraction approach with assistance of neural network distortion recovery is also described to reduce the silicon area. High precision in signal features classification with a low bit processing circuitry may be achieved by compensating with a recursive stochastic rounding routine, and provide on-chip learning to re-classify the sensor signals.

Abstract: Methods and systems include a neural network system that includes a neural network accelerator. The neural network accelerator includes multiple processing engines coupled together to perform arithmetic operations in support of an inference performed using the deep neural network system. The neural network accelerator also includes a schedule-aware tensor data distribution circuitry or software that is configured to load tensor data into the multiple processing engines in a load phase, extract output data from the multiple processing engines in an extraction phase, reorganize the extracted output data, and store the reorganized extracted output data to memory.

Abstract: In some implementations, a device may identify an account associated with a user, and the account may be managed by an entity. The device may determine, using at least one machine learning model, a classification of the user that indicates a level of quality of a relationship between the user and the entity. The device may determine, based on the classification determined using the at least one machine learning model, one or more adjustments that are to be applied to one or more charges assessed to the account by the entity. The device may apply the one or more adjustments to the one or more charges.

Abstract: The present invention relates to methods of sparsifying signals over time in multi-bit spiking neural networks, methods of training and converting these networks by interpolating between spiking and non-spiking regimes, and their efficient implementation in digital hardware. Four algorithms are provided that encode signals produced by nonlinear functions, spiking neuron models, supplied as input to the network, and any linear combination thereof, as multi-bit spikes that may be compressed and adaptively scaled in size, in order to balance metrics including the desired accuracy of the network and the available energy in hardware.

Abstract: Methods and systems are disclosed for securely searching for physical resources. Attributes of a plurality of shared physical resources are accessed. An encrypted communication is received and decrypted that provides attributes for a first user. A search is performed, using a first neural network, for physical resources corresponding to attributes of the user to identity a first set of physical resources using decrypted attributes of the user and attributes of the plurality of physical resources. Search match scores are generated for the first set of physical resources. A subset of physical resources that at least one other user has access to is identified. A second neural network identifies users associated with the subset of physical resources that have a temporal usage conflict likelihood with the user. Search match scores may be adjusted. The search results may be ranked using the adjusted search match scores, and the ranked search results may be displayed.

Abstract: Systems and methods for a tightly coupled end-to-end multi-sensor fusion with integrated compensation are described herein. For example, a system includes an inertial measurement unit that produces inertial measurements. Additionally, the system includes additional sensors that produce additional measurements. Further, the system includes one or more memory units. Moreover, the system includes one or more processors configured to receive the inertial measurements and the additional measurements. Additionally, the one or more processors are configured to compensate the inertial measurements with a compensation model stored on the one or more memory units. Also, the one or more processors are configured to fuse the inertial measurements with the additional measurements using a differential filter that applies filter coefficients stored on the one or more memory units.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for predicting one or more properties of a material. One of the methods includes maintaining data specifying a set of known materials each having a respective known physical structure; receiving data specifying a new material; identifying a plurality of known materials in the set of known materials that are similar to the new material; determining a predicted embedding of the new material from at least respective embeddings corresponding to each of the similar known materials; and processing the predicted embedding of the new material using an experimental prediction neural network to predict one or more properties of the new material.

Abstract: The present invention discloses a memory and a training method for neural network based on memory. The training method includes: obtaining one or more transfer functions of a memory corresponding to one or more influence factors; determining a training plan according to an ideal case and the one or more influence factors; training the neural network according to the training plan and the one or more transfer functions to obtain a plurality of weights of the trained neural network; and programming the memory according to the weights.

Abstract: An apparatus for training and inferencing a neural network includes circuitry that is configured to generate a first weight having a first format including a first number of bits based at least in part on a second weight having a second format including a second number of bits and a residual having a third format including a third number of bits. The second number of bits and the third number of bits are each less than the first number of bits. The circuitry is further configured to update the second weight based at least in part on the first weight and to update the residual based at least in part on the updated second weight and the first weight. The circuitry is further configured to update the first weight based at least in part on the updated second weight and the updated residual.

Abstract: Techniques are disclosed for providing a scalable multi-tenant serve pool for chatbot systems. A query serving system (QSS) receives a request to serve a query for a skillbot. The QSS includes: (i) a plurality of deployments in a serving pool, and (ii) a plurality of deployments in a free pool. The QSS determines whether a first deployment from the plurality of deployments in the serving pool can serve the query based on an identifier of the skillbot. In response to determining that the first deployment cannot serve the query, the QSS selects a second deployment from the plurality of deployments in the free pool to be assigned to the skillbot, and loads a machine-learning model associated with the skillbot into the second deployment, wherein the machine-learning model is trained to serve the query for the skillbot. The query is served using the machine-learning model loaded into the second deployment.

Abstract: A system and method for controlling a system, comprising estimating an optimal control policy for the system; receiving data representing sequential states and associated trajectories of the system, comprising off-policy states and associated off-policy trajectories; improving the estimate of the optimal control policy by performing at least one approximate value iteration, comprising: estimating a value of operation of the system dependent on the estimated optimal control policy; using a complex return of the received data, biased by the off-policy states, to determine a bound dependent on at least the off-policy trajectories, and using the bound to improve the estimate of the value of operation of the system according to the estimated optimal control policy; and updating the estimate of the optimimal control policy, dependent on the improved estimate of the value of operation of the system.

Abstract: Methods, systems, and computer program products for localization-based test generation for individual fairness testing of AI models are provided herein. A computer-implemented method includes obtaining at least one artificial intelligence model and training data related to the at least one artificial intelligence model; identifying one or more boundary regions associated with the at least one artificial intelligence model based at least in part on results of processing at least a portion of the training data using the at least one artificial model; generating, in accordance with at least one of the one or more identified boundary regions, one or more synthetic data points for inclusion with the training data; and executing one or more fairness tests on the at least one artificial intelligence model using at least a portion of the one or more generated synthetic data points and at least a portion of the training data.

Abstract: Discussed herein are devices, systems, and methods for classification using a clustering autoencoder. A method can include obtaining content to be classified by the DNN classifier, and operating the DNN classifier to determine a classification of the received content, the DNN classifier including a clustering classification layer that clusters based on a latent feature vector representation of the content, the classification corresponding to one or more clusters that are closest to the latent feature vector providing the classification and a corresponding confidence.

Abstract: Some embodiments provide a method for training multiple parameters of a machine-trained (MT) network subject to a sparsity constraint that requires a threshold portion of the parameters to be equal to zero. A first set of the parameters subject to the sparsity constraint are grouped into groups of parameters. For each parameter of a second set of the parameters subject to the sparsity constraint, the method determines an accuracy penalty associated with the parameter being set to zero. For each group of parameters in the first set of parameters, the method determines a minimum accuracy penalty for each possible number of parameters in the group being set to zero. The method uses the determined accuracy penalties to set to the value zero at least the threshold portion of the plurality of parameters.

Abstract: A device which comprises an array of resistive processing unit (RPU) cells, first control lines extending in a first direction across the array of RPU cells, and second control lines extending in a second direction across the array of RPU cells. Peripheral circuitry comprising readout circuitry is coupled to the first and second control lines. A control system generates control signals to control the peripheral circuitry to perform a first operation and a second operation on the array of RPU cells. The control signals include a first configuration control signal to configure the readout circuitry to have a first hardware configuration when the first operation is performed on the array of RPU cells, and a second configuration control signal to configure the readout circuitry to have a second hardware configuration, which is different from the first hardware configuration, when the second operation is performed on the array of RPU cells.

Abstract: Embodiments of this application disclose a target tracking method performed at an electronic device. The electronic device obtains a first video stream and detects candidate regions within a current video frame in the first video stream. The electronic device then extracts, from the candidate regions, a deep feature corresponding to each candidate region and calculates a feature similarity for each candidate region and a deep feature of a target detected in a previous video frame. Finally, the electronic device determines, based on the feature similarity corresponding to the candidate region, that the target is detected in the current video frame. Target detection is performed in a range of video frames by using a target detection model, and target tracking is performed based on the deep feature, so that occurrence of cases such as a target tracking drift or loss can be effectively prevented, to ensure the accuracy of target tracking.

Abstract: A system includes a data collection engine, a plurality of items including radio-frequency identification chips, a plurality of third party data and insight sources, a plurality of interfaces, client devices, a server and method thereof for preventing suicide. The server includes trained machine learning models, business logic and attributes of a plurality of patient events. The data collection engine sends attributes of new patient events to the server. The server can predict an adverse event risk of the new patient events based upon the attributes of the new patient events utilizing the trained machine learning models.