System and method for processing a graph that defines a set of nodes and a set of edges, the nodes each having an associated set of node attributes, the edges each representing a relationship that connects two respective nodes, comprising: generating a first node embedding for each node by: generating, for the node and each of a plurality of neighbour nodes, a respective first edge attribute defining a respective relationship type between the node and the neighbour node based on the node attributes of the node and the node attributes of the neighbour node; generating a first neighborhood vector that aggregates information from the generated first edge attributes and the node attributes of the neighbour nodes; generating the first node embedding based on the node attributes of the node and the generated first neighborhood vector.

An all-optical hologram reconstruction system and method is disclosed that can instantly retrieve the image of an unknown object from its in-line hologram and eliminate twin-image artifacts without using a digital processor or a computer. Multiple transmissive diffractive layers are trained using deep learning so that the diffracted light from an arbitrary input hologram is processed all-optically to reconstruct the image of an unknown object at the speed of light propagation and without the need for any external power. This passive diffractive optical network, which successfully generalizes to reconstruct in-line holograms of unknown, new objects and exhibits improved diffraction efficiency as well as extended depth-of-field at the hologram recording distance. The system and method can find numerous applications in coherent imaging and holographic display-related applications owing to its major advantages in terms of image reconstruction speed and computer-free operation.

A system can implement, in a first hyperparameter configuration state, a first set of hyperparameter search operations. The first set of hyperparameter search operations includes selecting a first set of hyperparameters. Each hyperparameter of the first set of hyperparameters having a corresponding configuration. Additionally, the first set of hyperparameter search operations includes obtaining a first set of performance data that includes information indicating a performance of each hyperparameter of the first set of hyperparameters, and assigning a value to each hyperparameter of the first set of hyperparameters based on the corresponding performance data.

Systems, methods, and protocols for developing invasive brain computer interface (iBCI) decoders non-invasively by using emulated brain data are provided. A human operator can interact in real-time with control algorithms designed for iBCI. An operator can provide input to one or more computer models (e.g., via body gestures), and this process can generate emulated brain signals that would otherwise require invasive brain electrodes to obtain.

Systems and methods for forecasting time series data are provided. In one implementation, a method includes the steps of obtaining time series data from a network. The method also comprises the step of determining one or more forecasters to be used based on a type of the time series data and based on previous training that determine that the one or more forecasters from a number of forecasters are best suited for the type of time series data. The method further comprises making a forecast of the time series data using the one or more forecasters and to save and/or display the forecast.

Embodiments of the present disclosure relate to a model optimization method, an electronic device, and a computer program product. This method includes: determining an initial learning rate combination for a deep learning model, wherein the initial learning rate combination includes a plurality of learning rates, each learning rate being determined for one of a plurality of layers of the deep learning model, and the plurality of learning rates including static learning rates and dynamic learning rates; and adjusting the initial learning rate combination to obtain a target learning rate combination, wherein an accuracy rate achieved when the target learning rate combination is used to train the deep learning model is higher than or equal to a first threshold accuracy rate. With the technical solution of the present disclosure, a deep learning model can be optimized by setting learning rates for each layer of the deep learning model.

This disclosure relates generally to time series forecasting, and, more particularly, to a system and method for online time series forecasting using spiking reservoir. Existing systems do not cater for efficient online time-series analysis and forecasting due to their memory and computation power requirements. System and method of the present disclosure convert a time series value F(t) at time ‘t’ to an encoded multivariate spike train and extracts temporal features from the encoded multivariate spike train by the excitatory neurons of a reservoir, predict a time series value Y(t + k) at time ‘t’ by performing a linear combination of extracted temporal features with read-out weights, compute an error for predicted time series value Y(t + k) with input time series value F(t + k), employs a FORCE learning on read-out weights using the error to reduce error in future forecasting. Feeding a feedback value back to the reservoir to optimize memory of the reservoir.

Embodiments described herein are related to systems and methods for forecasting demands for a transportation service. In one aspect, a set of neural network models may be implemented, where each neural network model can be configured to predict a booking status of a category of carriers on a corresponding date from a range of dates before a departure date. In one aspect, for each neural network model, a corresponding set of configuration values can be determined. Examples of the corresponding set of configuration values includes at least one of a number of layers, a number of neurons, and an activation function of the each neural network model. The set of neural network models can be constructed, according to corresponding sets of configuration values, and the constructed neural network models can be trained.

A learning device relating to one embodiment includes: an input unit configured to input a plurality of datasets of different feature spaces; a first generation unit configured to generate a feature latent vector indicating a property of an individual feature of the dataset for each of the datasets; a second generation unit configured to generate an instance latent vector indicating the property of observation data for each of observation vectors included in the datasets; a prediction unit configured to predict a solution by a model for solving a machine learning problem of interest by using the feature latent vector and the instance latent vector; and a learning unit configured to learn a parameter of the model by optimizing a predetermined objective function by using the feature latent vector, the instance latent vector and the solution for each of the datasets.

In various examples, an adaptive eye tracking machine learning model engine (“adaptive-model engine”) for an eye tracking system is described. The adaptive-model engine may include an eye tracking or gaze tracking development pipeline (“adaptive-model training pipeline”) that supports collecting data, training, optimizing, and deploying an adaptive eye tracking model that is a customized eye tracking model based on a set of features of an identified deployment environment. The adaptive-model engine supports ensembling the adaptive eye tracking model that may be trained on gaze vector estimation in surround environments and ensemble based on a plurality of eye tracking variant models and a plurality of facial landmark neural network metrics.