A system for transportation includes a vehicle interface for gathering physiological sensed data of a rider in the vehicle. The system includes an artificial intelligence-based circuit that is trained on a set of outcomes related to rider in-vehicle experience and that induces, responsive to the sensed rider physiological data, variation in one or more of the user experience parameters to achieve at least one desired outcome in the set of outcomes. The inducing variation includes control of timing and extent of the variation.

A system for transportation includes a vehicle interface for gathering physiological sensed data of a rider in the vehicle. The system includes an artificial intelligence-based circuit that is trained on a set of outcomes related to rider in-vehicle experience and that induces, responsive to the sensed rider physiological data, variation in one or more of the user experience parameters to achieve at least one desired outcome in the set of outcomes. The inducing variation includes control of timing and extent of the variation.

A memory circuit configured to perform multiply-accumulate (MAC) operations for performance of an artificial neural network includes a series of synapse cells arranged in a cross-bar array. Each cell includes a memory transistor connected in series with a memristor. The memory circuit also includes input lines connected to the source terminal of the memory transistor in each cell, output lines connected to an output terminal of the memristor in each cell, and programming lines coupled to a gate terminal of the memory transistor in each cell. The memristor of each cell is configured to store a conductance value representative of a synaptic weight of a synapse connected to a neuron in the artificial neural network, and the memory transistor of each cell is configured to store a threshold voltage representative of a synaptic importance value of the synapse connected to the neuron in the artificial neural network.

This disclosure describes techniques that include using an automatically trained machine learning system to generate a prediction. In one example, this disclosure describes a method comprising: based on a request for the prediction: training each respective machine learning (ML) model in a plurality of ML models to generate a respective training-phase prediction in a plurality of training-phase predictions; automatically determining a selected ML model in the plurality of ML models based on evaluation metrics for the plurality of ML; and applying the selected ML model to generate the prediction based on data collected from a network that includes a plurality of network devices.

Described is a system for continuously predicting and adapting optimal strategies for attacker elicitation. The system includes a global bot controlling processor unit and one or more local bot controlling processor units. The global bot controlling processor unit includes a multi-layer network software unit for extracting attacker features from diverse, out-of-band (OOB) media sources. The global controlling processing unit further includes an adaptive behavioral game theory (GT) software unit for determining a best strategy for eliciting identifying information from an attacker. Each local bot controlling processor unit includes a cognitive model (CM) software unit for estimating a cognitive state of the attacker and predicting attacker behavior. A generative adversarial network (GAN) software unit predicts the attacker's strategies. The global bot controlling processor unit and the one or more local bot controlling processor units coordinate to predict the attacker's next action and use the prediction to disrupt an attack.

The method of the present disclosure includes: obtaining an image to be processed and a question text corresponding to the image; using an optimized dialogue model to encode the image into an image vector and encode the question text into a question vector; generating a state vector based on the image vector and the question vector; decoding the state vector to obtain and output an answer text. A discriminator needs to be introduced in an optimization process of the optimized dialogue model. The dialogue model and the discriminator are alternately optimized until a value of a hybrid loss function of the dialogue model and a value of a loss function of the discriminator do not decrease or fall below a preset value, thereby accomplishing the optimization process.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learned communication over multi-input-multi-output (MIMO) channels. One of the methods includes: determining a transmitter and a receiver, at least one of which implements a machine-learning network; determining a MIMO channel model; determining first information; using the transmitter to process the first information and generate first RF signals representing inputs to the MIMO channel model; determining second RF signals representing outputs of the MIMO channel model, each second RF signal representing aggregated reception of the first RF signals altered by transmission through the MIMO channel model; using the receiver to process the second RF signals and generate second information as a reconstruction of the first information; calculating a measure of distance between the second and first information; and updating the machine-learning network based on the measure of distance between the second and first information.

A neural network accelerating method and device includes: reading a total video memory size available for a GPU to execute computing of a neural network, setting a size of a configurable level, and determining a finest granularity of a factor used for splitting a workspace; generating an optimal acceleration solution architecture for determining an optimal batchsize and an optimal network layer configuration that enable fastest convolution execution; generating a state transition equation for a multiple knapsack problem by taking a convolution operation efficiency boundary condition in the optimal acceleration solution architecture as a fitness function; iterating the state transition equation by using a genetic algorithm taking a forward and back convolution function as evaluation bases until a convergent batchsize and network layer configuration are obtained, and accelerating the neural network by taking the convergent batchsize and the network layer configuration as the optimal batchsize and the optimal network layer configuration.

The present disclosure discloses an adaptive high-precision compression method and system based on a convolutional neural network model, and belongs to the fields of artificial intelligence, computer vision, and image processing. According to the method of the present disclosure, coarse-grained pruning is performed on a neural network model by using a differential evolution algorithm first, and the coarse-grained space is quickly searched through an entropy importance criterion and an objective function with good guidance to obtain a near-optimal neural network structure. Then fine-grained search space is built on the basis of an optimal individual obtained from the coarse-grained search, and fine-grained pruning is performed on the neural network model by a differential evolution algorithm to obtain a network model with an optimal structure. Finally, the performance of the optimal model is restored by using a multi-teacher multi-step knowledge distillation network to reach the precision of an original model.

An adaptive search method includes: receiving a search condition set comprising target hardware platform information, network structure information of a source neural network, and one or more evaluation metrics; performing a training process on a to-be-trained super network based on a training dataset to obtain a trained super network, by extending a network structure of the source neural network; and performing a subnet search process on the trained super network based on the one or more evaluation metrics to obtain network structure information of a target neural network, which represents the target neural network and an evaluation result of the target neural network running on a target hardware platform is better than an evaluation result of the source neural network running on the target hardware platform.