Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an action selection policy of an execution device for completing a task in an environment. The method includes computing a hybrid sampling policy at a state of the execution device based on a sampling policy and an exploration policy, wherein the exploration policy specifies a respective exploration probability corresponding to each of multiple possible actions in the state, wherein the exploration probability is negatively correlated with a number of times that the each of the multiple possible actions in the state has been sampled; sampling an action among the multiple possible actions in the state according to a sampling probability of the action specified in the hybrid sampling policy; and updating an action selection policy in the state by performing Monte Carlo counterfactual regret minimization based on the action.

Abstract: A machine learning device provided in a controller for controlling a wire electrical discharge machine uses state variables (including data relating to a correction amount, a machining path, machining conditions, and a machining environment) observed by a state observation unit and determination data acquired by a determination data acquisition unit to machine-learn a correction for a machining path. Using the learning result, the machining path can be corrected automatically and accurately on the basis of a partial machining path, the machining conditions and the machining environment of the machining performed by the wire electrical discharge machine.

Abstract: Evolution and coevolution of neural networks via multitask learning is described. The foundation is (1) the original soft ordering, which uses a fixed architecture for the modules and a fixed routing (i.e. network topology) that is shared among all tasks. This architecture is then extended in two ways with CoDeepNEAT: (2) by coevolving the module architectures (CM), and (3) by coevolving both the module architectures and a single shared routing for all tasks using (CMSR). An alternative evolutionary process (4) keeps the module architecture fixed, but evolves a separate routing for each task during training (CTR). Finally, approaches (2) and (4) are combined into (5), where both modules and task routing are coevolved (CMTR).

Abstract: A system and method for evolving a deep neural network structure that solves a provided problem includes: a memory storing a candidate supermodule genome database having a pool of candidate supermodules having values for hyperparameters for identifying a plurality of neural network modules in the candidate supermodule and further storing fixed multitask neural networks; a training module that assembles and trains N enhanced fixed multitask neural networks and trains each enhanced fixed multitask neural network using training data; an evaluation module that evaluates a performance of each enhanced fixed multitask neural network using validation data; a competition module that discards supermodules in accordance with assigned fitness values and saves others in an elitist pool; an evolution module that evolves the supermodules in the elitist pool; and a solution harvesting module providing for deployment of a selected one of the enhanced fixed multitask neural networks, instantiated with supermodules selected fr

Abstract: A heterogeneous log pattern editing recommendation system and computer-implemented method are provided. The system has a processor configured to identify, from heterogeneous logs, patterns including variable fields and constant fields. The processor is also configured to extract a category feature, a cardinality feature, and a before-after n-gram feature by tokenizing the variable fields in the identified patterns. The processor is additionally configured to generate target similarity scores between target fields to be potentially edited and other fields from among the variable fields in the heterogeneous logs using pattern editing operations based on the extracted category feature, the extracted cardinality feature, and the extracted before-after n-gram feature. The processor is further configured to recommend, to a user, log pattern edits for at least one of the target fields based on the target similarity scores between the target fields in the heterogeneous logs.