Abstract: A method can include, for each row of a nonvolatile memory (NVM) cell array, generating a multiply-accumulate (MAC) result for the row by applying input values on bit lines. Each MAC result comprising a summation of an analog current or voltage that is a function of each input value modified by a corresponding weight value stored by the NVM cells of the row. By operation of at least one multiplexer, one of the rows can be connected to an analog-to-digital converter (ADC) circuit to convert the analog current or voltage of the row into a digital MAC value. A storage element of each NVM cell can be configured to store a weight value that can vary between no less than three different values. Corresponding devices and systems are also disclosed.

Abstract: Disclosed are an unsupervised learning method and an apparatus therefor applicable to general inverse problems. An unsupervised learning method applicable to inverse problems includes receiving a training data set and training an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach using the training data set, wherein the receiving of the training data set includes receiving the training data set including unmatched data.

Abstract: A method, system, and arrangement for resetting qubits are disclosed. An example system includes one or more quantum circuit refrigerators for resetting qubits. Each of the quantum circuit refrigerators includes a tunneling junction and a control input for receiving a control signal. Photon-assisted single-electron tunneling takes place across the respective tunneling junction in response to a control signal. Capacitive or inductive coupling elements between the qubits and the quantum circuit refrigerators couple each qubit to the quantum circuit refrigerator(s). The qubits, quantum circuit refrigerators, and coupling elements are located in a cryogenically cooled environment. A common control signal line to the control inputs crosses into the cryogenically cooled environment from a room temperature environment.

Abstract: An apparatus for training a reinforcement learning model according to an embodiment includes a starting point determinator configured to determine starting points from an input value of a combinatorial optimization problem, a multi-explorer configured to generate exploration trajectories by performing exploration from each of the starting points using a reinforcement learning model, a trajectory evaluator configured to calculate an evaluation value of each of the exploration trajectories using an evaluation function of the combinatorial optimization problem, a baseline calculator configured to calculate a baseline for the input value from the evaluation value of each exploration trajectory, an advantage calculator configured to calculate an advantage of each of the exploration trajectories using the evaluation value of each exploration trajectory and the baseline, and a parameter updater configured to update parameters of the reinforcement learning model by using the exploration trajectories and the advantage

Abstract: Digital object library management systems and methods for machine learning applications are taught herein.

Abstract: A novelty detector incudes a generator configured to output reconstructed data from actual data; and a discriminator configured to receive the actual data as well as the reconstructed data and to produce, using the actual data and the reconstructed data, discrimination data representing whether the actual data is normal or abnormal.

Abstract: A neuromorphic system enabling on-chip training includes: synapse arrays where synapse devices are arranged in a cross-bar shape; a final neuron layer including a forward neuron and a backward neuron and connected to an output terminal of a last synapse array; neuron layers including a forward neuron, a backward neuron, and a memory storing signals used during a weighted value update operation of a neural network and arranged between the remaining synapse arrays except for a first and last synapse arrays; and an error calculation circuit detecting and outputting an error value of a target signal and an output signal of the forward neuron of the final neuron layer. Conductances of the synapse devices represent weighted values of the neural network and are changed by the weighted value update operation. Each synapse device is configured with a flash device, and the neuron layers are implemented with ultra-miniature devices.

Abstract: Example systems and methods of developing a learning model are presented. In one example, a sample data set to train a first learning algorithm is accessed. A number of states for each input of the sample data set is determined. A subset of the inputs is selected, and the sample data set is partitioned into a number of partitions equal to a combined number of states of the selected inputs. A second learning algorithm is created for each of the partitions, wherein each second learning algorithm receives the unselected inputs. Each of the second learning algorithms is assigned to a processor and trained using the samples of the partition corresponding to that algorithm. Decision logic is generated to direct each of a plurality of operational data units as input to one of the second learning algorithms based on states of the selected inputs of the operational data unit.

Abstract: The disclosed technology enables, among other things, the identification of persons and the characterization of mental perceptions (e.g., pain, fatigue, mood) and/or intent (e.g., to perform an action) for medical, safety, home care, and other purposes. Of significance are applications that require long-term patient monitoring, such as tracking disease progression (e.g., multiple sclerosis), or monitoring treatment or rehabilitation efficacy. Therefore, longitudinal data must be acquired over time for the person's identity and other characteristics (e.g., pain level, usage of a cane). However, conventional methods of person identification (e.g., photography) acquire unnecessary personal information, resulting in privacy concerns. The disclosed technology allows measurements to be performed while protecting privacy and functions with partial or incomplete measurements, making it robust to real-world (noisy, uncontrolled) settings, such as in a person's home (whether living alone or with others).

Abstract: A method, computer system, and a computer program product for testing a data removal from a trained machine learning model trained with a training data set are provided. A new machine learning model is trained by using an altered data set that includes training data from the training data set. The altered data set is without removal data. A first forgetting mechanism is applied to the trained machine learning model to form a first revised machine learning model. The applying includes removing the removal data from the trained machine learning model. A first membership leakage quantification on the first revised machine learning model is performed to quantify a first membership leakage of the removal data and that uses the new machine learning model for comparison. A first leakage score is determined from the first membership leakage quantification to test the forgetting mechanism.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting likelihoods of conditions being satisfied using recurrent neural networks. One of the systems is configured to process a temporal sequence comprising a respective input at each of a plurality of time steps and comprises: one or more recurrent neural network layers; one or more logistic regression nodes, wherein each of the logistic regression nodes corresponds to a respective condition from a predetermined set of conditions, and wherein each of the logistic regression nodes is configured to, for each of the plurality of time steps: receive the network internal state for the time step; and process the network internal state for the time step in accordance with current values of a set of parameters of the logistic regression node to generate a future condition score for the corresponding condition for the time step.

Abstract: Systems and methods for classifying a test object are provided. For each respective target object in a plurality of target objects, a first procedure is performed comprising (a) posing the test object against the respective target thereby obtaining an interaction between the test and target, and (b) scoring the interaction with a first classifier. Each such score across the plurality of targets forms a test vector that is inputted into a second classifier thereby obtaining an indication of a target object. The second classifier is trained on training vectors, each being the output from instances of the first classifier after inputting a corresponding training object in a plurality of training objects in accordance with the first procedure. Each object in one subset of the training objects is uniquely associated with one of the targets. Another subset of the training objects is not associated with the targets.

Abstract: Methods, systems, and apparatus for accessing a set of feedback items, identifying a candidate feedback item from the set of feedback items using a lexical pattern, generating a gist phrase that summarizes the candidate feedback item, and causing display of a user interface on a client device, the user interface including the gist phrase.

Abstract: Hardware neural network processors, are provided. A neural core includes a weight memory, an activation memory, a vector-matrix multiplier, and a vector processor. The vector-matrix multiplier is adapted to receive a weight matrix from the weight memory, receive an activation vector from the activation memory, and compute a vector-matrix multiplication of the weight matrix and the activation vector. The vector processor is adapted to receive one or more input vector from one or more vector source and perform one or more vector functions on the one or more input vector to yield an output vector. In some embodiments a programmable controller is adapted to configure and operate the neural core.

Abstract: A detecting device includes a memory, and processing circuitry coupled to the memory and configured to collect communication information from a communication device, have a model learn a characteristic of the communication information by the communication device using the communication information collected for each of the communication devices, and input communication information on a detection target to the model, detect whether the communication information on the detection target indicates abnormal communication on the basis of an output result from the model, and have the model relearn at the learning when the number of detected abnormalities about the communication information during a predetermined evaluation period exceeds a first threshold value.

Abstract: The technology disclosed relates to webinterface generation and testing to promote a predetermined target user behavior. In particular, the technology disclosed stores a candidate database having a population of candidate individuals. Each of the candidate individuals identify respective values for a plurality of hyperparameters of the candidate individual. The hyperparameters describe topology of a respective neural network and coefficients for interconnects of the respective neural network. The technology disclosed writes a preliminary pool of candidate individuals into the candidate individual population. The technology disclosed tests each of the candidate individuals in the candidate individual population. The technology disclosed adds to the candidate individual population new individuals based on the testing. The technology disclosed repeats the candidate testing and the addition of the new individuals.

Abstract: In a computer-implemented method, an artificial neural network is trained to identify portions of conversation segments within electronic communication documents, wherein an input layer of the artificial neural network includes a plurality of input parameters each corresponding to a different characteristic of text-based content. The method also includes receiving a first electronic communication document that includes first text-based content, and processing the first text-based content using the trained artificial neural network. Processing the first text-based content includes generating one or more position indicators for the first electronic communication document, and the one or more position indicators include one or more segment portion indicators denoting positions of one or more portions of one or more conversation segments within the first electronic communication document.

Abstract: A computer-implemented method of training an artificial neural network (ANN) by generating a first learned parameter for use in normalising input data values during a subsequent inference phase of the trained ANN. The method includes, for each of a series of batches of training data values, deriving a batch variance of the batch of training data values and a running variance of all training data values already processed in the training phase; generating an approximation of a current value of the first learned parameter so that a first scaling factor dependent upon the approximation of the first learned parameter and the running variance, is constrained to be equal to a power of two; and normalizing the batch of input data values by a second scaling factor dependent upon the approximation of the current value of the first learned parameter and the batch variance.

Abstract: Embodiments generate digital plans for agricultural fields. In an embodiment, a model receives digital inputs including stress risk data, product maturity data, field location data, planting date data, and/or harvest date data. The model mathematically correlates sets of digital inputs with threshold data associated with the stress risk data. The model is used to generate stress risk prediction data for a set of product maturity and field location combinations. In a digital plan, product maturity data or planting date data or harvest date data or field location data can be adjusted based on the stress risk prediction data. A digital plan can be transmitted to a field manager computing device. An agricultural apparatus can be moved in response to a digital plan.

Abstract: The present disclosure generally relates to techniques for constructing an artificial-intelligence (AI) architecture. The present disclosure relates to techniques for executing the AI architecture to detect whether or not characters in a digital document have been manipulated. The AI architecture can be configured to classify each character in a digital document as manipulated or not manipulated by constructing a graph for each character, generating features for each node of the graph, and inputting a vector representation of the graph into a trained machine-learning model to generate the character classification.