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 system and method for evolving a recurrent neural network (RNN) that solves a provided problem includes: a memory storing a candidate RNN genome database having a pool of candidate RNN nodes, each of the candidate RNN nodes representing a neural network as a unique tree structure; an assembly module that assembles N RNN layers; an evolution module that evolves the H candidate RNN nodes of each respective RNN layer; a training module that trains the candidate RNN nodes of each of the N RNN layers using training data; an evaluation module that evaluates a performance of each candidate RNN node of each RNN layer using validation data and assigns a fitness value to each candidate RNN node; a competition module that forms an elitist pool of candidate RNN nodes in dependence on their assigned fitness values; and a solution harvesting module providing for deployment of RNN layers instantiated with candidate RNN nodes from the elitist pool.

Abstract: The technology disclosed identifies parallel ordering of shared layers as a common assumption underlying existing deep multitask learning (MTL) approaches. This assumption restricts the kinds of shared structure that can be learned between tasks. The technology disclosed demonstrates how direct approaches to removing this assumption can ease the integration of information across plentiful and diverse tasks. The technology disclosed introduces soft ordering as a method for learning how to apply layers in different ways at different depths for different tasks, while simultaneously learning the layers themselves. Soft ordering outperforms parallel ordering methods as well as single-task learning across a suite of domains. Results show that deep MTL can be improved while generating a compact set of multipurpose functional primitives, thus aligning more closely with our understanding of complex real-world processes.

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-implemented evolutionary system evolves candidate solutions to provided problems. It includes a memory storing a candidate gene database containing active and epigenetic individuals; a gene pool processor which tests only active individuals on training data and updates their fitness estimates; a competition module which selects active individuals for discarding in dependence upon both their updated fitness estimate and their testing experience level; and a gene harvesting module providing for deployment selected ones of the individuals from the gene pool. The gene database has an experience layered elitist pool, and individuals compete only with other individuals in their same layer. Certain individuals are made epigenetic in the procreation module, after which they are not subjected to testing and competition. Epigenetic individuals are retained in the candidate gene pool regardless of their fitness.

Abstract: A method for identifying a desired document is provided to include forming K clusters of documents and, for each cluster: for each respective document of the cluster determining a sum of distances between (i) the respective document and (ii) each of the other documents of the cluster; and identifying a medoid document of the cluster as the document of the cluster having the smallest sum of determined distances of all of the documents of the cluster. The method also includes selecting M representative documents for each cluster, identifying for dynamic display toward the user K groupings of documents, wherein each of the K groupings of documents identifies the selected M representative documents of a corresponding cluster, and, in response to user selection of one of the K groupings of documents, identifying for dynamic display toward the user P documents of the cluster that corresponds to the selected grouping.

Abstract: Roughly described, in an evolutionary technique for finding optimal solutions to a provided problem, a computer system uses a grouping algorithm that is better able to find diverse and optimum solutions in data mining environment with multiple solution landscapes and a plurality of candidate individuals. Each candidate individual identifies with a potential solution, and is associated with a testing experience level and one or more partition tags. Each candidate individual is assigned into one of a plurality of competition groups in dependence upon the individual's testing experience level and partition tag. During competition among candidate individuals, a candidate individual can only replace another candidate individual if both the candidate individuals have a common partition tag and are in the same competition group. A candidate individual cannot replace another candidate individual if they have different partition tags or are in different competition groups.

Abstract: A method for identifying a desired document is provided to include calculating a Prior probability score for each document of a candidate list including a portion of documents of an embedding space, the Prior probability score indicating a preliminary probability, for each document of the candidate list, that the document is the desired document, and identifying an initial (i=0) collection of N0>1 candidate documents from the candidate list in dependence on the calculated Prior probability scores, the initial collection of candidate documents having fewer documents than the candidate list. The method further includes, for each i'th iteration in a plurality of iterations, beginning with a first iteration (i=1) and in response to user selection of an i'th selected document from the (i?1)'th collection of candidate documents, identifying an i'th collection of Ni>1 candidate documents from the candidate list in dependence on Posterior probability scores.

Abstract: The technology disclosed proposes a novel asynchronous evaluation strategy (AES) that increases throughput of evolutionary algorithms by continuously maintaining a queue of K individuals ready to be sent to the worker nodes for evaluation and evolving the next generation once a fraction Mi of the K individuals have been evaluated by the worker nodes, where Mi<<K. A suitable value for Mi is determined experimentally, balancing diversity and efficiency. The technology disclosed is extended to coevolution of deep neural network supermodules and blueprints in the form of AES for cooperative evolution of deep neural networks (CoDeepNEAT-AES). Applied to image captioning domain, a threefold speedup is observed on 200 graphics processing unit (GPU) worker nodes, demonstrating that the disclosed AES and CoDeepNEAT-AES are promising techniques for evolving complex systems with long and variable evaluation times.

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: The technology disclosed is generally directed to massively multivariate testing, conversion rate optimization, and product recommendation and, in particular, directed to automatically and autonomously placing conversion code (e.g., scripts) in webpages of a host website without requiring any affirmative action on the part of the host. The conversion code modifies display and functionality of a particular portion of a host webpage without modifying other portions of the host webpage. The conversion code is placed by a website modification service which is limitedly authorized by the host to modify only the particular portion of the host webpage under a product recommendation and/or conversion rate optimization scheme.

Abstract: A method for finding a solution to a problem is provided. The method includes storing candidate individuals in a candidate pool and evolving the candidate individuals by performing steps including (i) testing each of the candidate individuals to obtain test results, (ii) assigning a performance measure to the tested candidate individuals, (iii) discarding candidate individuals from the candidate pool in dependence upon their assigned performance measure, and (iv) adding, to the candidate pool, a new candidate individual procreated from candidate individuals remaining in the candidate pool.

Abstract: Roughly described, a training database contains N segments of data samples. Candidate individuals identify a testing experience level, a fitness estimate, a rule set, and a testing set TSi of the data samples on which it is tested. The testing sets have fewer than all of the data segments and they are not all the same. Testing involves testing on only the individual's assigned set of data segments, updating the fitness estimates and testing experience levels, and discarding candidates through competition. If an individual reaches a predetermined maturity level of testing experience, then validating involves further testing it on samples of the testing data from a testing data segment other than those in the individual's testing set TSi. Those individuals that satisfy validation criteria are considered for deployment.

Abstract: The technology disclosed relates to providing expanded data object correlations for user-generated web customizations.

Abstract: The technology disclosed relates to neural network-based systems and methods of preparing a data object creation and recommendation database.

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: The technology disclosed relates to evolving deep neural network structures. A deep neural network structure includes a plurality of modules with submodules and interconnections among the modules and the submodules. In particular, the technology disclosed relates to storing candidate genomes that identify respective values for a plurality of hyperparameters of a candidate genome. The hyperparameters include global topology hyperparameters, global operational hyperparameters, local topology hyperparameters, and local operational hyperparameters. It further includes evolving the hyperparameters by training, evaluating, and procreating the candidate genomes and corresponding modules and submodules.

Abstract: Roughly described, a problem solving platform distributes the solving of the problem over a evolvable individuals, each of which also evolves its own pool of actors. The actors have the ability to contribute collaboratively to a solution at the level of the individual, instead of each actor being a candidate for the full solution. Populations evolve both at the level of the individual and at the level of actors within an individual. In an embodiment, an individual defines parameters according to which its population of actors can evolve. The individual is fixed prior to deployment to a production environment, but its actors can continue to evolve and adapt while operating in the production environment. Thus a goal of the evolutionary process at the level of individuals is to find populations of actors that can sustain themselves and survive, solving a dynamic problem for a given domain as a consequence.

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.