Abstract: In many environments, rules are trained on historical data to predict an outcome likely to be associated with new data. Described is a ruleset which predicts the probability of a particular outcome. Roughly described, an individual identifies a ruleset, where each of the rules has a plurality of conditions and also indicates a rule-level probability of a predetermined classification. The conditions indicate a relationship (e.g. ‘<’ or ‘!<’) between an input feature and a corresponding value. The rules are evaluated against input data to derive a certainty for each condition, and aggregated to a rule-level certainty. The rule probabilities are combined using the rule-level certainty values to derive a probability output for the ruleset, which can be used to provide a basis for decisions. In an embodiment, the per-condition certainty values are fuzzy values aggregated by fuzzy logic. A novel genetic algorithm can be used to derive the ruleset.

Abstract: The technology disclosed introduces a concept of training a neural network to create an embedding space. The neural network is trained by providing a set of K+2 training documents, each training document being represented by a training vector x, the set including a target document represented by a vector xt, a favored document represented by a vector xs, and K>1 unfavored documents represented by vectors xiu, each of the vectors including input vector elements, passing the vector representing each document set through the neural network to derive an output vectors yt, ys and yiu, each output vector including output vector elements, the neural network including adjustable parameters which dictate an amount of influence imposed on each input vector element to derive each output vector element, adjusting the parameters of the neural network to reduce a loss, which is an average over all of the output vectors yiu of [D(yt,ys)?D(yt, yiu)].

Abstract: A residual estimation with an I/O kernel (“RIO”) framework provides estimates of predictive uncertainty of neural networks, and reduces their point-prediction errors. The process captures neural network (“NN”) behavior by estimating their residuals with an I/O kernel using a modified Gaussian process (“GP”). RIO is applicable to real-world problems, and, by using a sparse GP approximation, scales well to large datasets. RIO can be applied directly to any pretrained NNs without modifications to model architecture or training pipeline.

Abstract: Roughly described, a computer-implemented evolutionary data mining system implements a genetic algorithm. The Genetic algorithm includes a requirements checkpoint, which selects individuals for discarding from the pool of candidate genomes which do not meet a predetermined minimum behavioral requirement for operating in production. The requirements checkpoint enforces an absolute minimum threshold for a behavioral characteristic of the individual, and is different from a competition step in which individuals are selected for removal on the basis of comparisons with each other. A requirements checkpoint may be inserted at various points within the genetic algorithm flow or at reasonable intervals during the training cycle. If at any of these checkpoints the minimum requirement is not met, the candidate individual may be removed from the candidate pool.

Abstract: Roughly described, anomalous behavior of a machine-learned computer-implemented individual can be detected while operating in a production environment. A population of individuals is represented in a computer storage medium, each individual identifying actions to assert in dependence upon input data. As part of machine learning, the individuals are tested against samples of training data and the actions they assert are recorded in a behavior repository. The behavior of an individual is characterized from the observations recorded during training. In a production environment, the individuals are operated by applying production input data, and the production behavior of the individual is observed and compared to the behavior of the individual represented in the behavior repository. A determination is made from the comparison of whether the individual's production behavior during operation is anomalous.

Abstract: Roughly described, a computer system uses a behavior-driven algorithm that is better able to find optimum solutions to a problem by balancing the use of fitness and novelty measures in evolutionary optimization. In competition among candidate individuals, a domination estimate between a pair of individuals is determined by both their fitness estimate difference and their behavior difference relative to one another. An increase in the fitness estimate difference of one individual of the pair over the other increases the domination estimate of the first individual. An increase in the behavior distance between the pair of individuals decreases the domination estimate of both of the individuals. Individuals with a higher domination estimate are more likely to survive competitions among the candidate individuals.

Abstract: A surrogate-assisted evolutionary optimization method, ESP, discovers decision strategies in real-world applications. Based on historical data, a surrogate is learned and used to evaluate candidate policies with minimal exploration cost. Extended into sequential decision making, ESP is highly sample efficient, has low variance, and low regret, making the policies reliable and safe. As an unexpected result, the surrogate also regularizes decision making, making it sometimes possible to discover good policies even when direct evolution fails.

Abstract: A process for training and sharing generic functional modules across multiple diverse (architecture, task) pairs for solving multiple diverse problems is described. The process is based on decomposing the general multi-task learning problem into several fine-grained and equally-sized subproblems, or pseudo-tasks. Training a set of (architecture,task) pairs then corresponds to solving a set of related pseudo-tasks, whose relationships can be exploited by shared functional modules. An efficient search algorithm is introduced for optimizing the mapping between pseudo-tasks and the modules that solve them, while simultaneously training the modules themselves.

Abstract: The technology disclosed uses a combination of an object detector and an object tracker to process video sequences and produce tracks of real-world images categorized by objects detected in the video sequences. The tracks of real-world images are used to iteratively train and re-train the object detector and improve its detection rate during a so-called “training cycle”. Each training cycle of improving the object detector is followed by a so-called “training data generation cycle” that involves collaboration between the improved object detector and the object tracker. Improved detection by the object detector causes the object tracker to produce longer and smoother tracks tagged with bounding boxes around the target object. Longer and smoother tracks and corresponding bounding boxes from the last training data generation cycle are used as ground truth in the current training cycle until the object detector's performance reaches a convergence point.

Abstract: The technology disclosed uses a combination of an object detector and an object tracker to process video sequences and produce tracks of real-world images categorized by objects detected in the video sequences. The tracks of real-world images are used to iteratively train and re-train the object detector and improve its detection rate during a so-called “training cycle”. Each training cycle of improving the object detector is followed by a so-called “training data generation cycle” that involves collaboration between the improved object detector and the object tracker. Improved detection by the object detector causes the object tracker to produce longer and smoother tracks tagged with bounding boxes around the target object. Longer and smoother tracks and corresponding bounding boxes from the last training data generation cycle are used as ground truth in the current training cycle until the object detector's performance reaches a convergence point.

Abstract: Roughly described, a computer system uses a behavior-driven algorithm that is better able to find optimum solutions to a problem by balancing the use of fitness and novelty measures in evolutionary optimization. In competition among candidate individuals, a domination estimate between a pair of individuals is determined by both their fitness estimate difference and their behavior difference relative to one another. An increase in the fitness estimate difference of one individual of the pair over the other increases the domination estimate of the first individual. An increase in the behavior distance between the pair of individuals decreases the domination estimate of both of the individuals. Individuals with a higher domination estimate are more likely to survive competitions among the candidate individuals.

Abstract: Roughly described, anomalous behavior of a machine-learned computer-implemented individual can be detected while operating in a production environment. A population of individuals is represented in a computer storage medium, each individual identifying actions to assert in dependence upon input data. As part of machine learning, the individuals are tested against samples of training data and the actions they assert are recorded in a behavior repository. The behavior of an individual is characterized from the observations recorded during training. In a production environment, the individuals are operated by applying production input data, and the production behavior of the individual is observed and compared to the behavior of the individual represented in the behavior repository. A determination is made from the comparison of whether the individual's production behavior during operation is anomalous.

Abstract: A genetic algorithm is described to determine a near-optimal schedule for assigning heterogeneous computations to resources in a heterogeneous computational environment. The genetic algorithm evolves a computation-to-compute resource mapping optimized with respect to a set of inter-dependent, and possibly conflicting objectives including cost of computation, data transfer cost, time to complete computation, profitability, etc. A set of scheduling plans are randomly created and then evaluated and assigned a fitness value based on the ability to meet a set of weighted objectives. Scheduling plans having desirable fitness values are selected as parents to procreate one or more new scheduling plans, each new plan inheriting resource mappings from at least two parents. This evolutionary process is repeated until the fitness values across scheduling plans converge or a time threshold is exceeded. At the end of evolution, a scheduling plan with the best assigned value is chosen for scheduling.

Abstract: An evolutionary AutoML framework called LEAF optimizes hyperparameters, network architectures and the size of the network. LEAF makes use of both evolutionary algorithms (EAs) and distributed computing frameworks. A multiobjective evolutionary algorithm is used to maximize the performance and minimize the complexity of the evolved networks simultaneously by calculating the Pareto front given a group of individuals that have been evaluated for multiple obj ectives.

Abstract: A genetic algorithm is described to determine a near-optimal schedule for assigning heterogeneous computations to resources in a heterogeneous computational environment. The genetic algorithm evolves a computation-to-compute resource mapping optimized with respect to a set of inter-dependent, and possibly conflicting objectives including cost of computation, data transfer cost, time to complete computation, profitability, etc. A set of scheduling plans are randomly created and then evaluated and assigned a fitness value based on the ability to meet a set of weighted objectives. Scheduling plans having desirable fitness values are selected as parents to procreate one or more new scheduling plans, each new plan inheriting resource mappings from at least two parents. This evolutionary process is repeated until the fitness values across scheduling plans converge or a time threshold is exceeded. At the end of evolution, a scheduling plan with the best assigned value is chosen for scheduling.

Abstract: A system and process for generalizing an evolutionary process applied to a particular domain involving different problems includes a researcher module for generating a configuration specification applicable to a particular problem. An evolution module parses the configuration specification into a representative tree structure, assembles policies for each node in the tree structure, and generates candidate genomes using the policies for each node in the tree structure. The policies may be applied to new data or data from prior runs to generate candidate genomes. The evolution module translates internal representations of the generated candidate genomes into known representations of the candidate genome for evaluation in accordance with the particular domain parameters by a candidate evaluation module.

Abstract: Described herein is a process which facilitates segmented security between domain-specific data sets being evaluated as part of a candidate evaluation service and third-party evolution services, wherein the data sets are not transmitted to the evolution service which is evolving candidates for evaluation. This enables customers with secure data sets to use candidate evolution services securely by obtaining a population of potentially optimal candidate models to evaluate and then optimizing on those data sets in their own secure fashion.

Abstract: A system for outputting an action signal to a controlled system is provided. The system includes a memory storing individuals to be deployed to a production environment as an actor, wherein each of the individuals has a rule associated therewith for asserting an action, and the actor includes one or more individuals, is associated with the controlled system and is configured to transmit an intermediate action signal for asserting the action. The system includes a management server configured to receive the intermediate action signal, select, from a set of available operations, a selected operation to perform with respect to the intermediate action signal, and the set of available operations including allowance and a blocking of the intermediate action signal. Further, in response to the selected operation being the allowance, transmitting the intermediate action signal, and in response to the selected operation being the blocking, blocking the intermediate action signal.

Abstract: Roughly described, an evolutionary data mining system includes at least two processing units, each having a pool of candidate individuals in which each candidate individual has a fitness estimate and experience level. A first processing unit tests candidate individuals against training data, updates an individual's experience level, and assigns each candidate to one of multiple layers of the candidate pool based on the individual's experience level. Individuals within the same layer of the same pool compete with each other to remain candidates. The first processing unit selects a set of candidates to retain based on the relative novelty of their responses to the training data. The first processing unit reports successful individuals to the second processing unit, and receives individuals for further testing from the second processing unit. The second processing unit selects individuals to retain based on their fitness estimate.

Abstract: A composite novelty method approach to deceptive problems where a secondary objective is available to diversify the search is described. In such cases, composite objectives focus the search on the most useful tradeoffs and allow escaping deceptive areas. Novelty-based selection increases exploration in the focus area, leading to better solutions, faster and more consistently and it can be combined with other fitness-based methods.