Abstract: Techniques are disclosed for systems and methods for learning the behavior of and/or for performing automated testing of a system under test (SUT). The learning/testing is accomplished solely via the graphical user interface (GUI) of the SUT and requires no a priori metadata/knowledge about the GUI objects. The learning engine operates by performing actions on the GUI and by observing the results of these actions. If the actions result in a change in the screen/page of the GUI then a screenshot is taken for further processing. Objects are detected from the screenshot, new actions that need to be performed on the objects are guessed, those actions are performed, the results are observed and the process repeats. Text labels on the screens are also read and are used for generating contextualized inputs for the screens. The learning process continues until any predetermined learning/testing criteria are satisfied.

Abstract: An embodiment of the present invention provides a quantization method for weights of a plurality of batch normalization layers, including: receiving a plurality of previously learned first weights of the plurality of batch normalization layers; obtaining first distribution information of the plurality of first weights; performing a first quantization on the plurality of first weights using the first distribution information to obtain a plurality of second weights; obtaining second distribution information of the plurality of second weights; and performing a second quantization on the plurality of second weights using the second distribution information to obtain a plurality of final weights, and thereby reducing an error that may occur when quantizing the weight of the batch normalization layer.

Abstract: Methods and apparatus for quantum assisted optimization. In one aspect, a method includes obtaining a set of initial input states, applying one or more of (i) dynamical thermal fluctuations and (ii) cluster update algorithms to the set of input states and subsequent input states when the states evolve within the classical information processors, applying dynamical quantum fluctuations to the set of input states and subsequent states when the states evolve within the quantum systems and repeating the application steps until a desirable output state is obtained.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for federal learning are disclosed. One exemplary method may include receiving, by a client device from a server device, model parameters of a global machine learning model being collaboratively trained by the client device and the server device; constructing, by the client device, a local machine learning model based on the model parameters of the global machine learning model, wherein the local machine learning model comprises two branches corresponding to two loss functions; training, by the client device, the local machine learning model based on local training data, wherein the training comprises updating the model parameters to minimize a first loss function of the two loss functions and maximize a second loss function of the two loss functions; and sending, by the client device, the updated model parameters back to the server device.

Abstract: A processing device can establish a vector-trained, deep learning model to produce software dependency recommendations. The processing device can build a list of software dependencies and corresponding metatags for each of the software dependencies, and generate a probability distribution from the list. The processing device can sample the probability distribution to produce a latent vector space that includes representative vectors for the software dependencies. The processing device can train a hybrid deep learning model to produce software dependency recommendations using the latent vector space as well as collaborative data for the software dependencies.

Abstract: A plant control supporting apparatus includes a segment selector configured to select, from among a plurality of segments defined in a plant, a segment for which learning for acquiring an optimal value of at least one parameter representing an operation state is executed, a reward function definer configured to define a reward function used for the learning, a parameter extractor configured to extract at least one parameter that is a target for the learning in the selected segment on the basis of input and output information of a device used in the plant and segment information representing a configuration of a device included in the selected segment, and a learner configured to perform the learning for acquiring the optimal value for each segment on the basis of the reward function and the at least one parameter.

Abstract: A system and method are shown for transferring weight information to analog non-volatile memory elements wherein the programming pulse duration is directly proportional to the difference in weights. Furthermore, the system and method avoid weight transfers when the weights are already well-matched.

Abstract: A system and method design and optimize neural networks. The system and method include a data store that stores a plurality of gene vectors that represent diverse and distinct neural networks and an evaluation queue stored with the plurality of gene vectors. Secondary nodes construct, train, and evaluate the neural network and automatically render a plurality of fitness values asynchronously. A primary node executes a gene amplification on a select plurality of gene vectors, a crossing-over of the amplified gene vectors, and a mutation of the crossing-over gene vectors automatically and asynchronously, which are then transmitted to the evaluation queue. The process continuously repeats itself by processing the gene vectors inserted into the evaluation queue until a fitness level is reached, a network's accuracy level plateaus, a processing time period expires, or when some stopping condition or performance metric is met or exceeded.

Abstract: In disclosed approaches of neural network processing, a host computer system copies an input data matrix from host memory to a shared memory for performing neural network operations of a first layer of a neural network by a neural network accelerator. The host instructs the neural network accelerator to perform neural network operations of each layer of the neural network beginning with the input data matrix. The neural network accelerator performs neural network operations of each layer in response to the instruction from the host. The host waits until the neural network accelerator signals completion of performing neural network operations of layer i before instructing the neural network accelerator to commence performing neural network operations of layer i+1, for i?1. The host instructs the neural network accelerator to use a results data matrix in the shared memory from layer i as an input data matrix for layer i+1 for i?1.

Abstract: Automatically generating and/or automatically transmitting a status of a user. The status is transmitted for presentation to one or more additional users via corresponding computing device(s) of the additional user(s). Some implementations are directed to determining both: a status of a user, and a predicted duration of that status; and generating a status notification that includes the status and that indicates the predicted duration. Some implementations are additionally or alternatively directed to utilizing at least one trust criterion in determining whether to provide a status notification of a user to an additional user and/or in determining what status notification to provide to the additional user. Some implementations are additionally or alternatively directed to training and/or use of machine learning model(s) in determining a status of a user and/or a predicted duration of that status.

Abstract: A computer-implemented method is provided for modified Lexicographic Reinforcement Learning. The computer implemented method includes obtaining, by a hardware processor, a sequence of tasks. Each of the tasks corresponds to, and has a one-to-one correspondence with, a respective award from among set of rewards. The method further includes performing, by the hardware processor for each of the tasks, reinforcement learning and deep learning for both of (i) one or more policies and (ii) one or more value functions, with a plurality of sets of samples. A plurality of solutions in a form of the one or more policies and the one or more value functions are parametrized by a single neural network with a selector which selects an input of the single neural network from among the plurality of sets of samples.

Abstract: An artificial intelligence testing apparatus may include processing circuitry configured to execute instructions that, when executed, cause the apparatus to create initial sample points based on a simulation received at the apparatus, and employ cyclic evaluation of the simulation until a stopping criteria is met. Employing the cyclic evaluation includes running the simulation at design points for a set of queries associated with a current iteration of the cyclic evaluation, training a set of meta-models of parameter space associated with the simulation for the current iteration, computing a set of metrics for the current iteration, and employing a selected sampling approach to select a new set of design points for a next iteration of the cyclic evaluation.

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: A method for pruning a neural network includes initializing a plurality of threshold values respectively corresponding to a plurality of layers included in the neural network; selecting one of the plurality of layers; adjusting the threshold value of the selected layer; and adjusting a plurality of weights respectively corresponding to a plurality of synapses included in the neural network.

Abstract: A location history manager may be configured to determine a location history associated with a user, and a resource usage manager may be configured to determine a computing resource usage history associated with the user. A location monitor may be configured to determine a location of the user. A resource predictor may be configured to generate a prediction of a computing resource, based on the location history, the computing resource usage history, and the location. A resource provider may be configured to provide the computing resource, based on the prediction.

Abstract: Systems, methods, and computer readable media related to determining one or more responses to provide that are responsive to an electronic communication that is generated through interaction with a client computing device. For example, determining one or more responses to provide for presentation to a user as suggestions for inclusion in a reply to an electronic communication sent to the user. Some implementations are related to training and/or using separate input and response neural network models for determining responses for electronic communications. The input neural network model and the response neural network model can be separate, but trained and/or used cooperatively.

Abstract: Systems and techniques for neuromorphic accelerator multitasking are described herein. A neuron address translation unit (NATU) may receive a spike message. Here, the spike message includes a physical neuron identifier (PNID) of a neuron causing the spike. The NATU may then translate the PNID into a network identifier (NID) and a local neuron identifier (LNID). The NATU locates synapse data based on the NID and communicates the synapse data and the LNID to an axon processor.

Abstract: Methods and systems for determining an optimized setting for one or more process parameters of a machine learning training process are described. One of the methods includes processing a current network input using a recurrent neural network in accordance with first values of the network parameters to obtain a current network output, obtaining a measure of the performance of the machine learning training process with an updated setting defined by the current network output, and generating a new network input that includes (i) the updated setting defined by the current network output and (ii) the measure of the performance of the training process with the updated setting defined by the current network output.

Abstract: A weld production knowledge system for processing welding data collected from one of a plurality of welding systems, the weld production knowledge system comprising a communication interface communicatively coupled with a plurality of welding systems situated at one or more physical locations. The communication interface may be configured to receive, from one of said plurality of welding systems, welding data associated with a weld. The weld production knowledge system may comprise an analytics computing platform operatively coupled with the communication interface and a weld data store. The weld data store employs a dataset comprising (1) welding process data associated with said one or more physical locations, and/or (2) weld quality data associated with said one or more physical locations. The analytics computing platform may employ a weld production knowledge machine learning algorithm to analyze the welding data vis-à-vis the weld data store to identify a defect in said weld.

Abstract: A method and associated systems provide real-time response to a request received from a real-time system like a self-driving vehicle or a device that communicates interactively with its environment. The response is selected from a set of candidate feasible responses by a group of computerized agents that each sort the feasible responses in order of that agent's specific preferences, based on that agent's particular priorities or expertise. The agents then reconcile their differences through an iterative procedure. During each iteration, each agent decides whether to retain its current preferences or to adopt the preferences of another agent. This decision is made by determining which preferences are most similar to that agent's own initial preferences, and by which preferences would be most useful in helping to achieve that agent's particular goals. When the agents reach consensus, the group's most-preferred response is returned quickly enough to provide real-time, interactive response.