Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing long-short term memory layers with compressed gating functions. One of the systems includes a first long short-term memory (LSTM) layer, wherein the first LSTM layer is configured to, for each of the plurality of time steps, generate a new layer state and a new layer output by applying a plurality of gates to a current layer input, a current layer state, and a current layer output, each of the plurality of gates being configured to, for each of the plurality of time steps, generate a respective intermediate gate output vector by multiplying a gate input vector and a gate parameter matrix. The gate parameter matrix for at least one of the plurality of gates is a structured matrix or is defined by a compressed parameter matrix and a projection matrix.

Abstract: This invention comprises a method of simulating an ecological environment, where digital agents within the environment are capable of processing data, and agents that successfully process data are permitted to reproduce to generate new algorithms. The invention is a groundbreaking advance in artificial intelligence and machine learning and enables processes that were once considered computationally impossible.

Abstract: A machine learning device includes a state observation unit for observing state variables that include at least one of the state of an assembly constituted of first and second components, an assembly time and information on a force, the result of a continuity test on the assembly, and at least one of position and posture command values for at least one of the first and second components and direction, speed and force command values for an assembly operation; and a learning unit for learning, in a related manner, at least one of the state of the assembly, the assembly time and the information on the force, the result of the continuity test on the assembly, and at least one of the position and posture command values for at least one of the first and second components and the direction, speed and force command values for the assembly operation.

Abstract: A method using a fast algorithm automated analysis of time series sensor data that can find an optimal clustering value k for k-means analysis by using statistical analysis of the results of clustering for a stated maximal upper value of k.

Abstract: The computing device generates a classification model providing prediction data indicating predicted users in a target population who will respond to a target stimulus according to a predefined user response category. The computing device displays in GUI a graphical representation of a generated classification model and a plurality of options each specifying one of different objectives for determining a proportion of users in the target population to expose to the target stimulus. The computing device predicts proportion data indicating the proportion of users in the target population to expose to the target stimulus based on the determined location of the cut-off. The computing device issues one or more indications as to whether to use the classification model as a basis for exposing the proportion of users in the target population to the target stimulus according to the proportion data.

Abstract: Systems, methods, and computer-readable media are disclosed for performing image processing in connection with phenotypic analysis. For example, at least one processor may be configured to receive electronic numerical information corresponding to pixels reflective of at least one external soft tissue image of an individual and access geographically dispersed genetic information stored in a database. The geographically dispersed genetic information may include numerical data that correlates anomalies in pixels in soft tissue images of a plurality of geographically dispersed individuals to specific genes or to specific genetic variants.

Abstract: A method for estimating confidence bounds for adjusted rainfall values for a set of geo-locations using agricultural data comprises using a server computer system that receives, via a network, agricultural data records that are used to estimate rainfall values for the set of geo-locations. Within the server computer system, rainfall calculation instructions receive digital data including observed radar and rain-gauge agricultural data records. The computer system then aggregates the agricultural data records and creates and stores the agricultural data sets. The agricultural data records are then used to estimate adjusted rainfall values for a set of geo-locations. Rainfall confidence bounds instructions estimate a set of confidence bounds for each of the adjusted rainfall values for the set of geo-locations. The set of confidence bounds provide a range for each of the adjusted rainfall values that represents a particular level of confidence associated with each of the adjusted rainfall values.

Abstract: An apparatus for artificial intelligence acceleration is provided. The apparatus includes a storage and compute system having a distributed, redundant key value store for metadata. The storage and compute system having distributed compute resources configurable to access, through a plurality of authorities, data in the solid-state memory, run inference with a deep learning model, generate vectors for the data and store the vectors in the key value store.

Abstract: Apparatus, methods, and systems for cross-domain time series data conversion are disclosed. In an example embodiment, a first time series of a first type of data is received and stored. The first time series of the first type of data is encoded as a first distributed representation for the first type of data. The first distributed representation is converted to a second distributed representation for a second type of data which is different from the first type of data. The second distributed representation for the second type of data is decoded as a second time series of the second type of data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.

Abstract: Various systems and methods are disclosed for accessing and traversing disparate, complex, and multi-dimensional data structures to dynamically and interactively generate reports based on automated modeling of complex and non-uniformly formatted data. Automated analysis of probabilistic functions and temporal-based data records enable non-technical users to quickly and dynamically act on time-sensitive information. In response to various user inputs, the system automatically accesses and traverses complex data structures (including, for example, frequency distribution models) calculates complex data based on the traversals, displays the calculated complex data to the user, and enters the calculated complex data into the reports.

Abstract: The present invention provides an improved docket search and analytics engine for determining the outcome of a case for a particular entity or party, for predicting the outcome of a case for a particular entity or party, or for predicting the time to resolution of a case for a particular entity or party. More specifically, the present invention provides a system and engine for accessing and retrieving docket and other data from a plurality of databases and applying by one or more engines a set of models to the retrieved data to make a determination or prediction as to the outcome of a case for an entity or party involved in the case.

Abstract: A method, system and computer product for performing storage maintenance is described. A training set for storage volume reclamation is received. The training set includes a set of storage parameters, each set of storage parameters corresponds to a respective candidate storage volume of a set of candidate storage volumes. The training set also includes a set of user decisions made whether a respective candidate storage volume is reclaimable. The training set is used to train a machine learning system to recognize common features of reclaimable candidate storage volumes. A set of candidate storage volumes is provided for potential reclamation, each with a set of storage parameters. A graphical user interface presents respective members of the set of candidate storage volumes for reclamation if a confidence level is calculated that the respective candidate storage volume is reclaimable exceeds a threshold.

Abstract: A machine provides a system and interface to allow domain experts and other users to develop, deploy, and iterate on analytical models. The system facilitates building, deploying, and/or training analytical models, by, e.g., exposing analytical model configuration parameters to a user while abstracting model building and model deployment activities. The system can also determine resource loads or execution times for various analytical models and can schedule model execution accordingly. The system also provides a dynamically reconfigurable user interface for controlling the system.

Abstract: Systems and methods for forecasting events can be provided. A measurement database can store sensor measurements, each having been provided by a non-portable electronic device with a primary purpose unrelated to collecting measurements from a type of sensor that collected the measurement. A measurement set identifier can select a set of measurements. The electronic devices associated with the set of measurements can be in close geographical proximity relative to their geographical proximity to other devices. An inter-device correlator can access the set and collectively analyze the measurements. An event detector can determine whether an event occurred. An event forecaster can forecast a future event property. An alert engine can identify one or more entities to be alerted of the future event property, generate at least one alert identifying the future event property, and transmit the at least one alert to the identified one or more entities.

Abstract: Generating a computing specification to be executed by a quantum processor includes: accepting a problem specification that corresponds to a second-quantized representation of a fermionic Hamiltonian, and transforming the fermionic Hamiltonian into a first qubit Hamiltonian including a first set of qubits that encode a fermionic state specified by occupancy of spin orbitals. An occupancy of any spin orbital is encoded in a number of qubits that is logarithmic in the number of spin orbitals, and a parity for a transition between any two spin orbitals is encoded in a number of qubits that is logarithmic in the number of spin orbitals. An eigenspectrum of a second qubit Hamiltonian, including the first set of qubits and a second set of qubit, includes a low-energy subspace and a high-energy subspace, and an eigenspectrum of the first qubit Hamiltonian is approximated by a set of low-energy eigenvalues of the low-energy subspace.

Abstract: An assessment dataset is selected from an input dataset using a first stratified sampling process based on a value of an event assessment variable. A remainder of the input dataset is allocated to a training/validation dataset that is partitioned into an oversampled training/validation dataset using an oversampling process based on a predefined value of the event assessment variable. A validation sample is selected from the oversampled training/validation dataset using a second stratified sampling process based on the value of the event assessment variable. A training sample is selected from the oversampled training/validation dataset using the second stratified sampling process based on the value of the event assessment variable. The validation sample and the training sample are mutually exclusive. A predictive type model is trained using the selected training sample. A plurality of predictive type models are trained, validated, and scored using the samples to select a best predictive model.

Abstract: Provided herein is a system for creating, modifying, deploying and running intelligent systems by combining and customizing the function and operation of reusable component modules arranged into neural processing graphs which direct the flow of signals among the modules, analogous in part to biological brain structure and operation as compositions of variations on functional components and subassemblies.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains validated training data containing a first set of content items and a first set of classification tags for the first set of content items. Next, the system uses the validated training data to produce a statistical model for classifying content using a set of dimensions represented by the first set of classification tags. The system then uses the statistical model to generate a second set of classification tags for a second set of content items. Finally, the system outputs one or more groupings of the second set of content items by the second set of classification tags to improve understanding of content related to the set of dimensions without requiring a user to manually analyze the second set of content items.

Abstract: A recommendation system uses artificial intelligence to identify, based on negative sentiment cues from users, item attributes, such as keywords, that users may find offensive or undesirable. The negative sentiment cues may be explicit (e.g., a user selects an option not to view a particular recommendation again), implicit (e.g., a user does not interact with recommendations relating to an attribute), or both. The system may use a computer model generated based on these identified attributes to filter or modify recommendations to a user or group of users. For instance, if a particular keyword is identified as highly offensive to a group of users, items associated with the keyword may be filtered from item recommendations presented to the group of users. If an attribute is identified as moderately offensive to a user, items associated with the attribute may be down-weighted in item recommendations presented to the user.