Abstract: Methods and computational devices for the implementation thereof that enable real-time Context Resets in conversational artificial intelligence (AI) systems are provided. The methods and computational devices improve the functioning of conversational AI systems by reducing non-productive computation, preventing propagation of irrelevant Active Context, and optimizing memory use during AI sessions. These operations restore conversational coherence by reducing Misalignment or Confusion between User Inputs and System Outputs. Accordingly, the invention provides a measurable improvement to computer functionality through adaptive, User-guided context management.

Abstract: Provided is a method for classifying data in an electronic apparatus, including obtaining target data, obtaining first classification information by using a classifier set including a plurality of classifiers based on the target data, obtaining second classification information by using a neural network model based on the target data, comparing the first classification information and the second classification information, and verifying the classifier set based on a result of comparing the first classification information and the second classification information.

Abstract: A device, computer program and computer-implemented method for machine learning. The method comprises providing a task comprising an action space of a multi-armed bandit problem or a contextual bandit problem and a distribution over rewards that is conditioned on actions, providing a hyperprior, wherein the hyperprior is a distribution over the action space, determining, depending on the hyperprior, a hyperposterior for that a lower bound for an expected reward on future bandit tasks has as large a value as possible, when using priors sampled from the hyperposterior, and wherein the hyperposterior is a distribution over the action space.

Abstract: The described technology is generally directed towards automated development of machine learning pipelines. An automated framework can extract topics from a data science workspace such as a machine learning notebook, transform and annotate cells of the machine learning notebook to various machine learning pipeline stages, and orchestrate the machine learning pipeline stages in a workflow that can be deployed into production data infrastructures.

Abstract: A computer-implemented method includes receiving an incorrect prediction output by a trained machine learning model, which has been trained using training data items. The method includes identifying a training data item used to train the model that is a cause of the incorrect prediction, by determining an impact on performance of the trained machine learning model associated with removing the training data item from the plurality of training data. The trained model can then be updated to remove the effect of the identified training data item, allowing the model to be automatically corrected in view of poor quality training data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes an attention neural network configured to perform the machine learning task, the attention neural network including one or more attention layers, each attention layer comprising an attention sub-layer and a feed-forward sub-layer that applies an element-wise multiplication between two vectors generated as a result of two different linear transformations performed on the same attended layer input.

Abstract: Techniques described herein involve providing an automated continual learning system for machine learning models. Embodiments include generating, using a machine learning model, an output based on a sample input provided to the machine learning model. Embodiments include evaluating the output based on comparing the output to an associated training output. Embodiments include creating a natural language rule based on the evaluating using a language processing machine learning model and storing the natural language rule in a rule library. Embodiments include receiving an input to the machine learning model and retrieving, in response to the input, one or more relevant rules from the rule library. Embodiments include generating, using the machine learning model, a response based on the input and the one or more relevant rules and performing an action based on the response.

Abstract: A machine learning system and a machine learning method capable of selecting a pretrained model to be used in transfer learning in a short time without actually executing the transfer learning includes a pretrained model acquisition unit which acquires a pretrained model from a pretrained model storage unit storing a plurality of pretrained models obtained by learning a transfer source task under respective conditions; a transfer learning dataset storage unit configured to store dataset related to a transfer target task; a pretrained model adaptability evaluation unit configured to evaluate adaptability of each pretrained model acquired by the pretrained model acquisition unit to the dataset related to the transfer target task; and a transfer learning unit configured to execute, based on an evaluation result of the pretrained model adaptability evaluation unit, transfer learning using a selected pretrained model and the dataset, and outputs a learning result as a trained model.

Abstract: Techniques for training an agricultural inference machine learning model to generate valid agricultural inferences of agricultural conditions based on ground truth sensor data that falls within a plurality of ground truth sensor value ranges associated with a particular agricultural area, and to generate invalid or ambiguous agricultural inferences of agricultural conditions based on ground truth sensor data that falls outside of the plurality of ground truth sensor value ranges associated with a particular agricultural area. The agricultural inference machine learning model is trained, based on ground truth sensor data for the particular agricultural area, to determine if the subsequently received ground truth sensor data falls within or outside of that plurality of ground truth sensor value ranges that correspond to the particular agricultural area.

Abstract: An agentic workflow system and method generate question and answer pairs and prompts that may be used to aligns generative artificial intelligence (a large language model (LLM) or a large multimodal model (LMM)) with the principles of a specific domain so that the generative artificial intelligence is better able to respond to a user query in the specific domain. The system and method may also generate aligning processes that may be used to post-train an already trained generative artificial intelligence system or fine tune the training of the generative artificial intelligence system to align that generative artificial intelligence system with the principles of the specific domain. The system and method may be used to align the generative artificial intelligence system to a plurality of different domains.

Abstract: Some embodiments provide a method for improving structural sparsity of a machine-trained (MT) network. The method receives a network having multiple layers. Each layer of a set of the layers includes multiple filters of weight values. The method replaces the filters of a particular layer of the network with (i) a first set of filters of weight values, (ii) a set of scale values for the first set of filters, and (iii) a second set of filters of weight values. Each scale value corresponds to a different one of the filters of the first set of filters. The method trains the network by applying constraints to bias at least a subset of the scale values towards zero. When a particular scale value falls below a threshold value, the particular scale value is set to zero.

Abstract: Some embodiments provide a method for training a machine-trained (MT) network. The method receives a network having multiple layers. Each layer of a set of the layers includes multiple weight values. The method trains the network by alternately (1) propagating inputs through the network to generate outputs and adjusting the weight values based on differences between the generated outputs and expected outputs and (2) identifying sets of the weight values for removal according to a set of constraints that accounts for (i) a total number of weight values and (ii) an amount of time required to execute the network on a particular type of integrated circuit.

Abstract: A system and method for neural network confidence regularization is disclosed. A classification system uses a neural network training model to generate prediction. The confidence of the neural network training model is adjusted based on feature prevalence. The system processes mixed data types (binary, categorical, continuous, and date) through type-specific transformations and tensor construction. A tempering factor is calculated from the unweighted sum of features and applied to intermediate neural network outputs. This tempering mechanism reduces model confidence when several low-weight features are present, enabling faster convergence, better generalization, and improved classification accuracy compared to standard neural networks, particularly for complex non-linear relationships in tabular data domains.

Abstract: An object is to obtain a failure predictor detection device that is capable of more adequately detecting a failure predictor. A failure predictor detection device according to the present disclosure includes: an acquisition unit to acquire estimation data and comparison data of targeted equipment for failure predictor detection in a targeted time period for the failure predictor detection; an estimation unit to calculate an estimated value of the comparison data during a normal operation from the estimation data using a learning model; and a detection unit to detect a failure predictor of the equipment on the basis of comparison results at multiple times between the estimated values and measured values shown by the comparison data.

Abstract: A computer-implemented method for training of a machine learning model for determining a confidence value during at least one test cycle of a vision testing procedure is disclosed. The confidence value is designated to determine at least one action in at least one subsequent test cycle of the vision testing procedure. Further, a trained machine learning model, a computer program having instructions for training of the machine learning model and a training apparatus are disclosed. Additionally, a computer-implemented method for performing the vision testing procedure on a person, a computer program having instructions for performing the vision testing procedure, a vision test apparatus, and a method for producing a geometrical model of at least one spectacle lens for manufacturing of at least one spectacle lens are disclosed.

Abstract: A search agent training system includes a trainer device. The trainer device includes a trainer network simulation of variable size, which further includes at least one selectable action, at least one selectable node, and a trainer knowledge base, which further includes at least one selectable action outcome probability value. The trainer knowledge base is populated by a quantification system. The trainer device receives an incoming action message from a search agent device including a selected action and a selected node. Next, based upon: a resulting action outcome probability value, the selected action, and the selected node, a resulting observation and a resulting reward is sent to the search agent device. The trainer device blocks node count report messages to the search agent device from the trainer device.

Abstract: Computer-implemented systems and methods are disclosed for automatically generating predictive models using data driven featurization. The systems and methods provide for obtaining data associated with a target event, annotating the data to identify a target event and establishing one or more limits on the data, censoring the data based on the annotations, determining features of the censored data, and analyzing the features to determine a predictive model. In some embodiments, the systems and methods further provide for converting the features into a binary representation and analyzing the binary representation to produce the predictive model.

Abstract: The present disclosure provides a big data-based modular AI engine server and a driving method thereof. The modular AI engine server of the present disclosure includes: a communication part configured to perform communication with at least one IoT device and a big data server; and a control part configured to determine an AI analysis model suitable for analyzing at least one piece of sensor data received from the IoT device, and analyze the sensor data by using the determined AI analysis model.

Abstract: In a training phase, training data may be used to train a supervised machine learning prediction model and an unsupervised machine learning segmentation model. Then, in a testing phase, the supervised machine learning prediction model may be used to predict a target outcome for a test data observation. Also, the unsupervised machine learning segmentation model may be used to evaluate the novelty of the test data observation relative to the training data.

Abstract: One embodiment of the present invention sets forth a technique for creating a machine learning model. The technique includes generating a user interface comprising one or more components for visually generating the machine learning model. The technique also includes modifying source code specifying a plurality of mathematical expressions that define the machine learning model based on user input received through the user interface. The technique further includes compiling the source code into compiled code that, when executed, causes one or more parameters of the machine learning model to be learned during training of the machine learning model.