Abstract: A neural network is configured to suppress an output of a mitigation node in a mitigation layer of the neural network. The neural network is pre-configured to recognize objects from inputs when operating using a processor and a memory. An actual input is sent to the neural network for object recognition, the actual input is an altered input. By suppressing the output of the mitigation node, the neural network is caused to avoid falsely recognizing an object from the actual input, where the altered input is configured to cause the neural network to falsely recognize the object from the actual input.

Abstract: Provided is a neural processing device including a noise classifier configured to perform a preprocessing on input data to determine a noise characteristic of the input data, a network selector configured to select one of a plurality of neural networks based on the noise characteristic, and an operator configured to perform inference on the input data based on selected weights corresponding to the selected neural network.

Abstract: A system includes a processor and a memory device communicatively coupled to the processor. The system also includes a database communicatively coupled to the processor. The database is configured to store a first plurality of prediction sets. Each prediction set is associated with a respective individual within a first population. Each prediction set comprises a plurality of prediction results, and each prediction result corresponds to a selected one of a plurality of features. The processor is configured to receive a request for a distribution value associated with a selected feature and one or more parameters. The distribution value indicate how often the selected feature appears in a second population of individuals, the second population being defined by the one or more parameters.

Abstract: A system for training a machine learning model using a batch based active learning approach. The system includes an information source and an electronic processor. The electronic processor is configured to receive a machine learning model to train, an unlabeled training data set, a labeled training data set, and an identifier of the information source. The electronic processor is also configured to select a batch of training examples from the unlabeled training data set and send, to the information source, a request for, for each training example included in the batch, a label for the training example. The electronic processor is further configured to, for each training example included in the batch, receive a label, associate the training example with the label, and add the training example to the labeled training data set. The electronic processor is also configured to train the machine learning model using the labeled training data.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve data training of a machine learning model using a field-programmable gate array (FPGA). An example system includes one or more computation modules, each of the one or more computation modules associated with a corresponding user, the one or more computation modules training first neural networks using data associated with the corresponding users, and FPGA to obtain a first set of parameters from each of the one or more computation modules, the first set of parameters associated with the first neural networks, configure a second neural network based on the first set of parameters, execute the second neural network to generate a second set of parameters, and transmit the second set of parameters to the first neural networks to update the first neural networks.

Abstract: Systems and methods are provided for performing predictive assignments pertaining to genetic information. One embodiment is a system that includes a genetic prediction server. The genetic prediction server includes an interface that acquires records that each indicate one or more genetic variants determined to exist within an individual, and a controller. The controller selects one or more machine learning models that utilize the genetic variants as input, and loads the machine learning models. For each individual in the records: the controller predictively assigns at least one characteristic to that individual by operating the machine learning models based on at least one genetic variant indicated in the records for that individual. The controller also generates a report indicating at least one predictively assigned characteristic for at least one individual, and transmits a command via the interface for presenting the report at a display.

Abstract: Disclosed herein includes a system, a method, and a device for receiving input data to generate a plurality of outputs for a layer of a neural network. The plurality of outputs are arranged in a first array. Dimensions of the first array may be compared with dimensions of a processing unit (PE) array including a plurality of PEs. According to a result of the comparing, the first array is partitioned into subarrays by the processor. Each of the subarrays has dimensions less than or equal to the dimensions of the PE array. A first group of PEs in the PE array is assigned to a first one of the subarrays. A corresponding output of the plurality of outputs is generated using a portion of the input data by each PE of the first group of PEs assigned to the first one of the subarrays.

Abstract: Disclosed herein is system level occupancy counting in a lighting system configured to obtain an indicator data of a RF spectrum signal (signal) generated at a number of times in an area. At each respective one of the number of times, apply one of a plurality of heurist algorithm heuristic algorithm coefficients to each indicator data of the signal, based on results of the application of the heuristic algorithm coefficients, generate an indicator data metric value for each of the indicator data for the respective time. The lighting system is also configured to process each of the indicator data metric value to compute a plurality of metric values for the respective time and combine the plurality of metric values to compute an output metric value for each of a plurality of probable number of occupants in the area for the respective time. The lighting system is further configured to determine an occupancy count in the area at the respective time based on the computed output metric value.

Abstract: According to an embodiment, a pattern recognition apparatus includes an RNN layer, as a middle layer, that includes an input converting unit and an RNN processor. The input converting unit performs conversion, for each step, on an input vector and a recurrent input vector, and calculates and outputs a converted vector of which the number of dimensions is smaller than the sum of the numbers of dimensions of respective the input vector and the recurrent input vector. The input vector is formed of a feature vector output from an input layer or an output of the RNN processor included in a lower RNN layer. The recurrent input vector is formed of an output of a previous step of the RNN processor. The RNN processor calculates an RNN output vector from the converted vector calculated in the input converting unit and outputs the RNN output vector, for each step.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for generating combined feature embeddings for minority class upsampling in training machine learning models with imbalanced training samples. For example, the disclosed systems can select training sample values from a set of training samples and a combination ratio value from a continuous probability distribution. Additionally, the disclosed systems can generate a combined synthetic training sample value by modifying the selected training sample values using the combination ratio value and combining the modified training sample values. Moreover, the disclosed systems can generate a combined synthetic ground truth label based on the combination ratio value. In addition, the disclosed systems can utilize the combined synthetic training sample value and the combined synthetic ground truth label to generate a combined synthetic training sample and utilize the combined synthetic training sample to train a machine learning model.

Abstract: A method, a system, and a computer program product for performing analysis of data to detect presence of malicious code are disclosed. Reduced dimensionality vectors are generated from a plurality of original dimensionality vectors representing features in a plurality of samples. The reduced dimensionality vectors have a lower dimensionality than an original dimensionality of the plurality of original dimensionality vectors. A first plurality of clusters is determined by applying a first clustering algorithm to the reduced dimensionality vectors. A second plurality of clusters is determined by applying a second clustering algorithm to one or more clusters in the first plurality of clusters using the original dimensionality. An exemplar for a cluster in the second plurality of clusters is added to a training set, which is used to train a machine learning model for identifying a file containing malicious code.

Abstract: Methods and systems are described for training a machine learning (ML) model to predict the gain of a target channel of a multi-channel amplifier device. An ML model may be pre-trained using an existing set of training objects. The trained ML model then can be utilized to suggest further useful training objects to be labelled that will improve the performance of the ML model by predicting more accurate target channel gains given the on/off value for the channel inputs.

Abstract: For various content campaigns (or content), an online system generates a score indicating a likelihood of the content item having deceptive information, such as including a picture or name of a celebrity to promote something that the celebrity has not actually endorsed. The online system receives a request to determine whether a content item comprises deceptive information. The online system extracts features from the content item, and provides the extracted features to a machine learning based model configured to generate score indicating whether a content item comprises deceptive information. The online system executes the machine learning based model to generate the score for the content item. Responsive to the generated score indicating that content item comprises deceptive information, the online system verifies whether the content item conforms to content policies.

Abstract: Example implementations are directed to a method of receiving information associated with an activity, analyzing the information to identify a first pattern and a second pattern, and generating a customized recommendation model for the second pattern based on the first pattern. In response to a detected trigger indicating a transition to the second pattern, the method assesses context factors to verify the transition to the second pattern without interrupting the first pattern. Based on the verification, the method applies the model to provide redirection based on the recommendation.

Abstract: A neuromorphic system includes an address translation device that translates an address corresponding to each of synaptic weights between presynaptic neurons and postsynaptic neurons to generate a translation address, and a plurality of synapse memories that store the synaptic weights based on the translation address. The translation address is generated such that at least two of synaptic weights corresponding to each of the postsynaptic neurons are stored in different synapse memories of the plurality of synapse memories and such that at least two of synaptic weights corresponding to each of the presynaptic neurons are stored in different synapse memories.

Abstract: Techniques are described for implementing automated control systems that manipulate operations of specified target systems, such as by modifying or otherwise manipulating inputs or other control elements of the target system that affect its operation (e.g., affect output of the target system). An automated control system may in some situations have a distributed architecture with multiple decision modules that each controls a portion of a target system and operate in a partially decoupled manner with respect to each other, such as by each decision module operating to synchronize its local solutions and proposed control actions with those of one or more other decision modules, in order to determine a consensus with those other decision modules. Such inter-module synchronizations may occur repeatedly to determine one or more control actions for each decision module at a particular time, as well as to be repeated over multiple times for ongoing control.

Abstract: Implementations include receiving two or more time-series data sequences representative of a target process executed within a physical environment, executing automated time-series process segmentation to provide a plurality of subsequence segments for each of the two or more time-series data sequences, each subsequence segment corresponding to a phase of the target process, processing the two or more subsequence segments using at least one time-series transformation to provide a feature data set for each subsequence segment, applying each feature data set to provide time-series models for anomaly detection and forecasting, respectively, each time-series model being provided as one of a recurrent neural network (RNN), a convolution neural network (CNN), and a generative adversarial network (GAN), determining anomaly scores based on the time-series models, and selectively providing an alert to one or more users, each alert indicating at least one anomaly and a respective probability.

Abstract: At an artificial intelligence-based service, an indication of a similarity group of items of a data stream is obtained. A subset of the stream items is to be included in an ordered collection and presented via an interface which allows one or more types of interactions. Using a first data set which includes interaction records of items in the similarity group, one or more machine learning models are trained to predict a relevance metric associated with a particular type of interaction. A predicted value of the relevance metric is obtained from a trained version of a model and stored.

Abstract: A computer-implemented method for inferring a 3D structure of a genome is provided. The method includes providing genome interaction data and operating an autoencoder including a structured sequence of n autoencoder units, each of which including an encoder unit and a decoder unit, each of which is implemented as a recurrent neural network unit. The method includes additionally training the autoencoder by feeding all vectors of genome interaction data to the encoder units. Thereby, the training of the auto-encoder units is performed stepwise by using inner state of respective previous autoencoder units in the cascaded sequence of autoencoder units and performing backpropagation within each of the plurality of autoencoder units after all autoencoder units have processed their respective input values, and using the output values of the encoder units for deriving a 3D model for a visualization of the genome.

Abstract: A computer-implemented system and method for building context models in real time is provided. A database of models for a user is maintained. Each model represents a contextual situation and includes one or more actions. Contextual data is collected for the user and a contextual situation is identified for that user based on the collected contextual information. Models related to the identified situation are selected and merged. One or more actions from the merged model are then selected.