A system for transportation includes a vehicle having a user interface, and a robotic process automation system wherein a set of data is captured for each user in a set of users as each user interacts with the user interface, and wherein an artificial intelligence system is trained using the set of data to interact with the vehicle to automatically undertake actions with the vehicle on behalf of the user.

A method of optimizing an operating state of a vehicle includes classifying, using a first neural network of a hybrid neural network, social media data sourced from a plurality of social media sources as affecting a transportation system. The method further includes predicting, using a second neural network of the hybrid neural network, one or more effects of the classified social media data on the transportation system. The method further includes optimizing, using a third neural network of the hybrid neural network, a state of at least one vehicle of the transportation system, wherein the optimizing addresses an influence of the predicted one or more effects on the at least one vehicle.

The present invention relates to metalearning of deep neural network (DNN) architectures and hyperparameters. Precisely, the present system and method utilizes Evolutionary Population-Based Based Training (EPBT) that interleaves the training of a DNN's weights with the metalearning of loss functions. They are parameterized using multivariate Taylor expansions that EPBT can directly optimize. Further, EPBT based system and method uses a quality-diversity heuristic called Novelty Pulsation as well as knowledge distillation to prevent overfitting during training. The discovered hyperparameters adapt to the training process and serve to regularize the learning task by discouraging overfitting to the labels. EPBT thus demonstrates a practical instantiation of regularization metalearning based on simultaneous training.

A search method for a neural network model structure, includes: generating an initial generation population of network model structure based on multi-objective optimization hyper parameters, as a current generation population of network model structure; performing selection and crossover on the current generation population of network model structure; generating a part of network model structure based on reinforcement learning mutation, and generating a remaining part of network model structure based on random mutation on the selected and crossed network model structure; generating a new population of network model structure based on the part of network model structure generated by reinforcement learning mutation and the remaining part of network model structure generated by random mutation; and searching a next generation population of network model structure based on the current generation population of network model structure and the new population of network model structure.

A search method for a neural network model structure, includes: generating an initial generation population of network model structure based on multi-objective optimization hyper parameters, as a current generation population of network model structure; performing selection and crossover on the current generation population of network model structure; generating a part of network model structure based on reinforcement learning mutation, and generating a remaining part of network model structure based on random mutation on the selected and crossed network model structure; generating a new population of network model structure based on the part of network model structure generated by reinforcement learning mutation and the remaining part of network model structure generated by random mutation; and searching a next generation population of network model structure based on the current generation population of network model structure and the new population of network model structure.

A learning data processing unit accepts, as input, a plurality of pieces of learning data for a respective plurality of tasks, and calculates, for each of the tasks, a batch size which meets a condition that a value obtained by dividing a data size of corresponding one of the pieces of learning data by the corresponding batch size is the same between the tasks. A batch sampling unit samples, for each of the tasks, samples from corresponding one of the pieces of learning data with the corresponding batch size calculated by the learning data processing unit. A learning unit updates a weight of a discriminator for each of the tasks, using the samples sampled by the batch sampling unit.

A learning data processing unit accepts, as input, a plurality of pieces of learning data for a respective plurality of tasks, and calculates, for each of the tasks, a batch size which meets a condition that a value obtained by dividing a data size of corresponding one of the pieces of learning data by the corresponding batch size is the same between the tasks. A batch sampling unit samples, for each of the tasks, samples from corresponding one of the pieces of learning data with the corresponding batch size calculated by the learning data processing unit. A learning unit updates a weight of a discriminator for each of the tasks, using the samples sampled by the batch sampling unit.

A device, system, and method is provided for storing a sparse neural network. A plurality of weights of the sparse neural network may be obtained. Each weight may represent a unique connection between a pair of a plurality of artificial neurons in different layers of a plurality of neuron layers. A minority of pairs of neurons in adjacent neuron layers are connected in the sparse neural network. Each of the plurality of weights of the sparse neural network may be stored with an association to a unique index. The unique index may uniquely identify a pair of artificial neurons that have a connection represented by the weight. Only non-zero weights may be stored that represent connections between pairs of neurons (and zero weights may not be stored that represent no connections between pairs of neurons).

A quantum contextual measurement is generated from a quantum device capable of performing continuous time evolution, by generating a first measurement result and a second measurement result and combining the first measurement result and the second measurement result to generate the quantum contextual measurement. The first measurement result may be generated by initializing the quantum device to a first initial quantum state, applying a first continuous time evolution to the first initial state to generate a first evolved state, and measuring the first evolved state to generate the first measurement result. A similar process may be applied to generate a second evolved state which is at least approximately equal to the first evolved state, and then applying another continuous time evolution to the second evolved state to generate a third evolved state, and measuring the third evolved state to generate the second measurement result.

The present invention discloses a networked control system (NCS) time-delay compensation method based on predictive control. The method comprises the following steps: (1) acquiring random time-delay data in an NCS, and preprocessing the data; (2) predicting the current time-delay by using a fuzzy neural network (FNN) optimized by a particle swarm optimization (PSO) algorithm; (3) compensating the predicted time-delay by using an implicit proportional-integral-based generalized predictive control (PIGPC) algorithm; (4) determining whether a preset work end time is up according to a clock in the NCS; if yes, ending the process; if no, returning to step (2). The method disclosed by the present invention can accurately predict and effectively compensate the NCS time-delay and has excellent development prospect.