A technique is described herein for automatically logging journeys taken by a user, and then automatically classifying the purposes of the journeys. In one implementation, the technique obtains journey data from one or more movement-sensing devices as a user travels from a starting location to an ending location in a vehicle. The technique generates a set of features based on the journey data, and then uses a machine-trainable model (such as a neural network) to make its classification based on the features. The machine-trainable model accepts at least one feature that is based on statistical information regarding at least one aspect of prior journeys that the user has taken. Overall, the technique provides a resource-efficient solution that rapidly provides personalized results to individual respective users. In some implementations, the technique performs its personalization without sharing journey data with a remote server.

Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency, such as accuracy of learning, accuracy of prediction, speed of learning, performance of learning, and energy efficiency of learning. An array of processing elements performs flow-based computations on wavelets of data. Each processing element has a respective compute element and a respective routing element. Each compute element has processing resources and memory resources. Each router enables communication via wavelets with at least nearest neighbors in a 2D mesh. Stochastic gradient descent, mini-batch gradient descent, and continuous propagation gradient descent are techniques usable to train weights of a neural network modeled by the processing elements. Reverse checkpoint is usable to reduce memory usage during the training.

Techniques in advanced deep learning provide improvements in one or more of accuracy, performance, and energy efficiency, such as accuracy of learning, accuracy of prediction, speed of learning, performance of learning, and energy efficiency of learning. An array of processing elements performs flow-based computations on wavelets of data. Each processing element has a respective compute element and a respective routing element. Each compute element has processing resources and memory resources. Each router enables communication via wavelets with at least nearest neighbors in a 2D mesh. Stochastic gradient descent, mini-batch gradient descent, and continuous propagation gradient descent are techniques usable to train weights of a neural network modeled by the processing elements. Reverse checkpoint is usable to reduce memory usage during the training.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

Briefly stated, the invention is directed to retrieving a semantically matched knowledge structure. A question and answer pair is received, wherein the answer is received from a query of a search engine. A question is constraint-matched with the answer based on maximizing a plurality of constraints, wherein at least one of the plurality of the constraints is a similarity score between question and answer, wherein the constraint matching generates a matched sequence. For one or more answer sequences, a subsequence is found that are not parsed as answer slots. Query results are obtained from another search engine based on a combination of the answer or question, and the non-answer subsequence. And a KB based is refined on the query results and the constraint matching and based on a neural network training, for a further subsequent semantic matching, wherein the KB includes a dense semantic vector indication of concepts.

In various embodiments, methods, systems, and vehicle apparatuses are provided. A method for implementing torque control using a Neural Network (NN) for a torque prediction model to receive a set of measured vehicle operating inputs associated with torque prediction; substituting a set of multiple independent variables into the torque prediction model so that the NN is then taking the form of a simplified pseudo-NN that contains a reduced variable set of one independent variable; processing, the set of measured vehicle operating inputs by the pseudo-NN based on the NN prediction model by using only one independent variable in a pseudo-NN's simplified mathematical expression; and solving for at least one root of the pseudo-NN's simplified mathematical expression by obtaining a root value without having to rely on an inversion operation of a mathematical expression that consists of an entire set of independent variables.

In various embodiments, methods, systems, and vehicle apparatuses are provided. A method for implementing torque control using a Neural Network (NN) for a torque prediction model to receive a set of measured vehicle operating inputs associated with torque prediction; substituting a set of multiple independent variables into the torque prediction model so that the NN is then taking the form of a simplified pseudo-NN that contains a reduced variable set of one independent variable; processing, the set of measured vehicle operating inputs by the pseudo-NN based on the NN prediction model by using only one independent variable in a pseudo-NN's simplified mathematical expression; and solving for at least one root of the pseudo-NN's simplified mathematical expression by obtaining a root value without having to rely on an inversion operation of a mathematical expression that consists of an entire set of independent variables.

During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.

A computer-implemented method for combined indoor and outdoor tracking using a tracking device is disclosed. In at least one embodiment of the method, a fingerprint of radio signals is generated by the device at a location to be determined. The location of the device is determined by applying trained functions to the fingerprint wherein the trained functions have been end-to-end trained using a plurality of fingerprints generated at known locations. Environmental sensor data may be used to predict a lifetime of a component tracked by the tracking device.