A method of generating a pre-training model, an electronic device and a storage medium, which relate to a field of an artificial intelligence technology, in particular to a computer vision and deep learning technology. The method includes: determining a performance index set corresponding to a candidate model structure set, the candidate model structure set is determined from a plurality of model structures included in a search space, and the search space is a super-network-based search space; determining, from the candidate model structure set, a target model structure corresponding to each chip according to the performance index set, each target model structure is a model structure meeting a performance index condition; and determining, for each chip, the target model structure corresponding to the chip as a pre-training model corresponding to the chip, the chip is configured to run the pre-training model corresponding to the chip.

The present invention is a molecular graph representation learning method based on contrastive learning, the method comprising: obtaining a molecular fingerprint representation of each molecule, and calculating a similarity between each two molecular fingerprints; collecting a full amount of chemical functional group information, and matching a corresponding functional group for each atom in the molecule; using a heterogeneous graph to model a molecular graph; using a RGCN in the structure-aware molecular encoder to encode the representation of each atom in the molecule and the representation of the functional group to which the atom belongs, and mapping the molecule to a feature space through an aggregation function to obtain a structure-aware feature representation; according to the fingerprint similarity between molecules, selecting positive and negative samples, and carrying out a comparative learning in the feature space; obtaining the structure-aware molecular encoder by using the contrastive learning method for training on a large-sample molecular dataset, and applying the structure-aware molecular encoder to a prediction task of downstream molecular attributes. The present invention helps to capture more abundant molecular structure information and solve the problem on molecular property prediction.

Embodiments of this application disclose a data labeling system and method, and a data labeling manager. The system includes a data labeling manager, a labeling model storage repository, and a basic computing unit storage repository. The data labeling manager receives a data labeling request, obtains a target basic computing unit, allocates a hardware resource to the target basic computing unit, establishes a target computing unit, obtains first storage path information of basic parameter data of a first labeling model, and sends the first storage path information to the target computing unit. The target computing unit obtains the basic parameter data of the to-be-used labeling model by using the first storage path information, combines a target model inference framework and the basic parameter data of the first labeling model to obtain the first labeling model, and labels to-be-labeled data by using the first labeling model.

The present disclosure relates to neural network optimization methods and apparatuses in the field of artificial intelligence. One example method includes sampling preset hyperparameter search space to obtain multiple hyperparameter combinations. Multiple iterative evaluations are performed on the multiple hyperparameter combinations to obtain multiple performance results of each hyperparameter combination. Any iterative evaluation comprises obtaining at least one performance result of each hyperparameter combination, and if a hyperparameter combination meets a first preset condition, re-evaluating the hyperparameter combination to obtain a re-evaluated performance result of the hyperparameter combination. An optimal hyperparameter combination is determined. If the optimal hyperparameter combination does not meet a second preset condition, a preset model is updated, based on the multiple performance results of each hyperparameter combination, for next sampling. Or if the optimal hyperparameter combination meets a second preset condition, the optimal hyperparameter combination is used as a hyperparameter combination of a neural network.

A method for configuring a neural network which is designed to map measured data to one or more output variables. The method includes: transformation(s) of the measured data is/are specified which when applied to the measured data, is/are meant to induce the output variables supplied by the neural network to exhibit an invariant or equivariant behavior; at least one equation is set up which links a condition that the desired invariance or equivariance be given with the architecture of the neural network; by solving the at least one equation a feature is obtained that characterizes the desired architecture and/or a distribution of weights of the neural network in at least one location of this architecture; a neural network is configured in such a way that its architecture and/or its distribution of weights in at least one location of this architecture has/have all of the features ascertained in this way.

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 method of using a computing device to self-train a machine learning model with an incomplete dataset including original observational data. The method includes receiving a labeled training data, the labeled training data for training a machine learning model. Counterfactual unlabeled training data is received. One or more labels are predicted for the counterfactual unlabeled training data. The machine learning model is trained based upon the labeled training data, the counterfactual unlabeled training data, and the predicted one or more labels for the unlabeled training data. The machine learning model reduces bias in original observational data. An evaluation of the predicted one or more labels is received based on corresponding artificial intelligence explanations provided by an artificial intelligence explainability model.

The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops. The improvement is achieved by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, and then creating shop-specific versions of the recommendation model for each of the shops in the subset. Each shop-specific model is created by optimizing the baseline model to predict user-item interactions in a first training dataset for the applicable shop. Each of the shop-specific models is then tested using a second training dataset for the shop. A loss is calculated for each shop-specific model based on the model's predicted user-item interactions and the actual user-item interactions in the second training dataset for the shop. A global loss is calculated based on each of the shop-specific losses, and the baseline model is updated to minimize the global loss.

A method for creating a machine learning system. The method includes: providing a directed graph including an input node and an output node, a probability being in each case assigned to each edge which characterizes the probability with which an edge is drawn. The probabilities are manipulated as a function of a characteristic degree of an exploration of the architectures of the directed graph prior to a random drawing of the architectures.

A computer-implemented method for generating a control signal by locating at least one instrument by way of a combination of machine learning systems on the basis of digital images is described. In this case, the method includes determining parameter values of a movement context by using the at least two digital images and determining an influence parameter value which controls an influence of one of the digital images and the parameter values of the movement context on the input data which are used within a first trained machine learning system, which has a first learning model, for generating the control signal.