Abstract: A process for optimizing loss functions includes progressively building better sets of parameters for loss functions represented as multivariate Taylor expansions in accordance with an iterative process. The optimization process is built upon CMA-ES. At each generation (i.e., each CMA-ES iteration), a new set of candidate parameter vectors is sampled. These candidate parameter vectors are sampled from a multivariate Gaussian distribution representation that is modeled by the CMA-ES covariance matrix and the current mean vector. The candidates are then each evaluated by training a model (neural network) using the candidates and determining a fitness value for each candidate against a validation data set.

Abstract: System and method for prevention of counterfeiting of products using combination of packaging codes and blockchain technology is provided. Hash of a first product code is generated by encrypting scanned product data associated with a product received. Second product code is generated by encrypting first product code for combining with distinct first product code Quick Response (QR) part values. Hash of a third product code is generated by combining hash of first product code and hash of second product code. Hash of third product code is divided into a hash of a first sub-code and a hash of a second sub-code. Lastly, a comparison of a scanned third product code placed on the product is performed with requested user ID, generated hash of first product code, second product code and hash of third product code to ascertain a match therebetween for preventing counterfeiting of the product.

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 objectives.

Abstract: A system and method for developing unified digital platform based virtual power banks is provided. A second data type is derived by analyzing record types. The record types are obtained from the first data type received from multiple sources. Virtual power banks are generated by employing the first and second data types fetched from database. Dynamic actionable items relating to the virtual power banks are generated from the first data type and the second data type. One or more variables are identified that correspond to different types of dynamic actionable items for categorizing the dynamic actionable items based on the identified variables. Lastly, optimization operations are performed on values of each of the identified variables to obtain an optimized final weightage value of the virtual power banks, accessed via a unified digital platform, based on which one or more operational parameters associated with the virtual power banks are determined.

Abstract: The present invention provides for a system and a method for implementing artificial intelligence-based optimised data stewardship. The system comprises a memory for storing program instructions, a processor executing instructions stored in the memory and a digital data stewardship engine executed by the processor. One or more events are identified based on nature of the events and a sequence is determined for invoking one or more units of the digital data stewardship engine based on the identified event. Machine learning-based intelligent analysis is performed on additional information obtained through third-party websites associated with the identified event. Rules are applied on the results of the intelligent analysis for augmenting the results as per pre-defined requirements and outcome generated based on application of rules are delivered as an executable file.

Abstract: User-driven exploration functionality, referred to herein as a Scratchpad, is a post-learning extension for machine learning systems. For example, in ESP, consisting of the Predictor (a surrogate model of the domain) and Prescriptor (a solution generator model), the Scratchpad allows the user to modify the suggestions of the Prescriptor, and evaluate each such modification interactively with the Predictor. Thus, the Scratchpad makes it possible for the human expert and the AI to work together in designing better solutions. This interactive exploration also allows the user to conclude that the solutions derived in this process are the best found, making the process trustworthy and transparent to the user.

Abstract: A domain-independent problem-solving system and process addresses domain-specific problems with varying dimensionality and complexity, solving different problems with little or no hyperparameter tuning, and adapting to changes in the domain, thus implementing lifelong learning.

Abstract: A system and method for generating a modernization sequence for application modernization is provided. The present invention provides for generating a database of hierarchies between a plurality of technology stacks based on analysis of historic modernization data and user inputs. Further, the present invention provides for evaluating in real-time an optimal sequence for implementing modernization of two or more technologies associated with the application based on the database. A hierarchy between each of the technology stacks corresponding to the two or more technologies is derived based on the database, and the technology stacks are arranged in a chronological order based on the derived hierarchy. The modernization sequence of the two or more technologies is same as the chronological order of their corresponding technology stacks.

Abstract: A multi-task (MTL) process is adapted to the single-task learning (STL) case, i.e., when only a single task is available for training. The process is formalized as pseudo-task augmentation (PTA), in which a single task has multiple distinct decoders projecting the output of the shared structure to task predictions. By training the shared structure to solve the same problem in multiple ways, PTA simulates the effect of training towards distinct but closely-related tasks drawn from the same universe. Training dynamics with multiple pseudo-tasks strictly subsumes training with just one, and a class of algorithms is introduced for controlling pseudo-tasks in practice.

Abstract: A genetic loss function optimization (hereafter “GLO”) process uses a genetic algorithm to construct candidate loss functions as trees. The process takes the best candidate loss functions from this set and optimizes the coefficients thereof using covariance-matrix adaptation evolutionary strategy (hereafter “CMA-ES”), resulting in new loss functions showing substantial improvements in accuracy, convergence speed, and data requirements.

Abstract: A computer-implemented method optimizing genetic algorithms for finding solutions to a provided problem is described. The method implements a multi-arm bandit algorithm to determine performance scores for candidate individuals from a candidate pool in dependence on successes and failures of the one or more candidates. The method evolves the candidate individuals in the candidate pool by performing evolution steps including: determining a fitness score for each of the candidate individuals in the candidate pool in dependence on the performance scores for the candidate individuals, discarding candidate individuals from the candidate pool in dependence upon their assigned performance measure, and adding, to the candidate pool, a new candidate individual procreated from candidate individuals remaining in the candidate pool after the discarding of the candidate individuals.

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: 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: 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: 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: 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: A genetic loss function optimization (hereafter “GLO”) process uses a genetic algorithm to construct candidate loss functions as trees. The process takes the best candidate loss functions from this set and optimizes the coefficients thereof using covariance-matrix adaptation evolutionary strategy (hereafter “CMA-ES”), resulting in new loss functions showing substantial improvements in accuracy, convergence speed, and data requirements.

Abstract: A process for discovering optimal Generative Adversarial Networks (GAN) includes jointly optimizing the three functions of a GANs process including (i) a real component of a discriminator network's loss that is a function of D(x), wherein D(x) is the discriminator network's output for a real sample from an input dataset; (ii) a synthetic component of the discriminator network's loss that is a function of D(G(z)), wherein D(G(z)) is the discriminator network's output for a generator network's synthetic samples z from a latent distribution; and (iii) a generator network's loss which is a function of D(G(z)), with the discriminator network's total loss being the sum of components (i) and (ii).

Abstract: 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.

Abstract: A method for injecting metadata into an existing artifact is described. The method generates metadata related to an existing artifact having a predetermined structure and encodes the metadata in accordance with the predetermined structure. The encoded metadata is embedded within the existing artifact in accordance with the predetermined structure and is delineated within the predetermined structure as one or more individual records. The artifact, including embedded metadata, is stored within a storage entity and is accessible to processes related to the artifact. Additional records may be generated and embedded over time, thus creating a timeline if event related to the artifact.