A slicer in a material drop ejecting three-dimensional (3D) object printer identifies the positions and local densities for a plurality of infill lines within a perimeter to be formed within a layer of an object to be formed by the printer. The local density of each infill line is filtered and a control law is applied to the filtered local density to identify an error in the local density compared to a target density. This process is performed iteratively until the error is within a predetermined tolerance range about the target local density. The error is used to generate machine ready instructions to operate the 3D object printer to achieve the target density for the infill lines.

A Dual-Filtering (DF) system to provide a robust Machine Learning (ML) platform against adversarial attacks. It employs different filtering mechanisms (one at the input and the other at the output/decision end of the learning system) to thwart adversarial attacks. The developed dual-filter software can be used as a wrapper to any existing ML-based decision support system to prevent a wide variety of adversarial evasion attacks. The DF framework utilizes two filters based on positive (input filter) and negative (output filter) verification strategies that can communicate with each other for higher robustness.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network used to select actions performed by an agent interacting with an environment by performing actions that cause the environment to transition states. One of the methods includes training the neural network on one or more transitions selected from a replay memory, including: generating, using the neural network, an action selection output for the current observation; determining, based on the action selection output and the current action performed by the agent in response to the current observation, a state-action target for the current observation; determining a gradient of a temporal difference (TD) loss function with respect to parameters of the neural network, wherein the TD loss function comprises a first term that depends on the state-action target for the current observation; and adjusting current parameter values of the neural network based on the gradient.

A system for training a neurome that emulates a brain of a user comprises a non-invasive brain interface assembly configured for detecting neural activity of the user in response to analog instances of a plurality of stimuli peripherally input into the brain of the user from at least one source of content, memory configured for storing a neurome configured for outputting a plurality of determined brain states of an avatar in response to inputs of the digital instances of the plurality of stimuli, and a neurome training processor configured for determining a plurality of brain states of the user based on the detected neural activity of the user, and modifying the neurome based on the plurality of determined brain states of the user and the plurality of determined brain states of the avatar.

An autonomous chat bot monitors actions of users on a messaging platform and generates self-initiated chat sessions with the user to gauge users' interest and intent with respect to a target subject matter and the conversations of the chat sessions. Based on the gauged interest and intent, profiles or preferences are generated for the users independent of or relevant to the target subject matter. In an embodiment, customer contact information for the users are provided by the autonomous chat bot to a Customer Relationship Management (CRM) system for further engaging the customer with respect to the target subject matter or other subject matters determined to be relevant from the profiles or preferences.

A machine learning system receives a witness function that is determined based on an initial sample of a dataset comprising multiple pairs of stimuli and responses. Each stimulus includes multiple features. The system receives a holdout sample of the dataset comprising one or more pairs of stimuli and responses that are not used to determine the witness function. The system generates a simulated sample based on the holdout sample. Values of a particular feature of the stimuli of the simulated sample are predicted based on values of features other than the particular feature of the stimuli of the simulated sample. The system applies the holdout sample to the witness function to obtain a first result. The system applies the simulated sample to the witness function to obtain a second result. The system determines whether to select the particular feature based on a comparison between the first result and the second result.

One embodiment provides a method, including: receiving, at a digital assistant of an information handling device, a query from a user comprising at least two response portions; determining responses for the at least two response portions, wherein the determining comprises separately processing each of the at least two response portions; and providing a response to the user comprising the responses. Other aspects are described and claimed.

Embodiments of the present disclosure relate to a model training method, a data processing method, an electronic device, and a computer program product. The method includes: acquiring storage information associated with a simulated network environment; and training a reinforcement learning model using simulated data and based on a simulated-data read request for a node among multiple nodes included in the simulated network environment and each having a cache. With the technical solutions of the present disclosure, the cache allocation and cache replacement problems can be simultaneously solved by using a reinforcement learning model to determine in a dynamic environment a data caching scheme that meets predetermined criteria, so that it is possible to not only improve the accuracy and efficiency of determining the data caching scheme with less cost overhead, but also improve the user experience of users using the caching system.

An autonomous vehicle and a system and method for operating the autonomous vehicle. The system includes a control system and a cognitive system. The control system performs a driving action at the autonomous vehicle. The cognitive system generates the driving action using an evaluation model. The evaluation model is generated by operating the cognitive system in response to a training set of data to generate a planned action for operating the autonomous vehicle by the cognitive system, evaluating the planned action to obtain a system performance grade, and updating the cognitive system based on a comparison of the system performance grade to a human-based performance grade.

Embodiments of the present disclosure provide a method and apparatus for man-machine conversion, and an electronic device. The method includes: outputting question information to a user based on a first task of a first conversation scenario; judging, in response to receiving reply information returned by the user, whether to trigger a second conversation scenario based on the reply information; generating, in response to determining the second conversation scenario being triggered based on the reply information, response information corresponding to the reply information based on the second conversation scenario; and outputting the response information to the user.