Abstract: An approach is provided for enhancing a generative large language model (LLM). An encoder, decoder, and generative associative memory network set are jointly trained to learn to store sentence encodings in a memory matrix used during decoding. The encoder and decoder are included in the generative LLM. The generative associative memory network set is included in an external memory unit. The external memory unit is external to the encoder and decoder. The generative LLM is augmented with the external memory unit in a framework that enhances the generative LLM. The external memory unit is updated with new information. Using the new information in the updated external memory unit, a knowledge update of the decoder is performed during an inference without fine-tuning or re-training the generative LLM. A response to a prompt during the inference is generated. The response is based on the knowledge update of the decoder.

Abstract: A computer-implemented method for discovering causality includes accessing time-series data describing past events. The time-series data is input into a machine learning model, the machine learning model implementing an intensity function including a kernel function, where the kernel function determines a causal strength value computed from a transformer model, and where the kernel function contributes to an additive function that sums intensity of repeated individual events of the past events. In response to the inputting, an output is received from the machine learning model that indicates a causality that links two or more events of the past events.

Abstract: A lighting device for a vehicle configured to create a segmented light function. The device includes a holding frame, a light source holder having first and second light source groups mounted thereto; and at least two optical elements. The light source holder, the first optical element (FOE), and the second optical element (SOE) are configured to be mounted to the holding frame. The FOE has a first protrusion, and the SOE has a second protrusion, and the holding frame includes first and second receiving elements configured to receive the first and second protrusions, respectively. The holding frame includes a first stopping element configured to engage a first contact surface of the FOE and a second stopping element configured to engage a second contact surface of the SOE. The lighting device further includes a cover element configured to secure the FOE and SOE against movement opposite to a main beam direction.

Abstract: A computer implemented method of performing large-scale machine learning experiments includes expanding on one or more input datasets by systematically generating several data set drift splits. A set of experimental jobs corresponding to the generated data set drift splits are executed to generate experimental results. The experimental results are processed, consolidated, and clustered according to the generated data set drift splits.

Abstract: An embodiment for generating causal association rankings for candidate events within a window of candidate events using dynamic deep neural network generated embeddings. The embodiment may automatically receive a window of candidate events including events of a first type preceding one or more target events of interest. The embodiment may automatically generate contrastive windows of candidate events, each of the contrastive windows of candidate events of the first type corresponding to a different dropped candidate event from the received window of candidate events. The embodiment may automatically identify matching historical windows of events having resulting embeddings that are close in distance to the embeddings corresponding to the embeddings of the contrastive windows and calculate a first score for each match. The embodiment may automatically identify matching incident windows and calculate a corresponding second score.

Abstract: A technique for generating a performance prediction of a machine learning model with uncertainty intervals includes obtaining a first model configured to perform a task and a production dataset. At least one metric predicting a performance of the first model at performing the task on the production dataset is generated using a second model. The second model is a meta-model associated with the first model. At least one value predicting an uncertainty of the at least one metric predicting the performance of the first model at performing the task on the production dataset is generated using a third model. The third model is a meta-meta-model associated with the second model. An indication of the at least one metric and the at least one value is provided.

Abstract: A solid electrolytic capacitor comprising a capacitor element, anode lead extending from a surface of the capacitor element, an anode termination that is in electrical connection with the anode lead, a cathode termination that is in electrical connection with the solid electrolyte, and a casing material that encapsulates the capacitor element and anode lead is provided. A barrier coating is disposed on at least a portion of the capacitor element and is in contact with the casing material. The coating contains a polymeric material that includes a fluorinated component and a non-fluorinated component. The polymeric material has a glass transition temperature of from about 10° C. to about 120° C. and a thermal decomposition temperature of about 200° C. to about 300° C.

Abstract: A computer-implemented method, a computer program product, and a system for reducing labeled sample quantities required to update test sets. The computer-implemented method includes inputting a portion of unlabeled production data into a base model and generating labeled output relating to the unlabeled production data. The computer-implemented method also includes inputting the labeled output into a performance predictor. The performance predictor is a meta model of the base model that is trained with another portion of the unlabeled production data, a training set used to train the base model, and a test set portioned from the training set. The computer-implemented method further includes outputting, by the performance predictor, a performance metric relating to the labeled output produced by the trained base model. The performance metric can be any metric capable of measuring the output performance of the base model.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: A solid electrolytic capacitor comprising a capacitor element, anode lead extending from a surface of the capacitor element, an anode termination that is in electrical connection with the anode lead, a cathode termination that is in electrical connection with the solid electrolyte, and a casing material that encapsulates the capacitor element and anode lead is provided. A barrier coating is disposed on at least a portion of the anode termination and/or cathode termination and is in contact with the casing material. The coating contains a hydrophobic resinous material that includes an olefin polymer having a glass transition temperature of from about 20° C. to about 160° C.

Abstract: A solid electrolytic capacitor comprising a capacitor element, anode lead extending from a surface of the capacitor element, an anode termination that is in electrical connection with the anode lead, a cathode termination that is in electrical connection with the solid electrolyte, and a casing material that encapsulates the capacitor element and anode lead is provided. A barrier coating is disposed on at least a portion of the capacitor element and is in contact with the casing material. The coating contains a polymeric material that includes a fluorinated component and a non-fluorinated component. The polymeric material has a glass transition temperature of from about 10° C. to about 120° C. and a thermal decomposition temperature of about 200° C. to about 300° C.

Abstract: A computer implemented method of performing large-scale machine learning experiments includes expanding on one or more input datasets by systematically generating several data set drift splits. A set of experimental jobs corresponding to the generated data set drift splits are executed to generate experimental results. The experimental results are processed, consolidated, and clustered according to the generated data set drift splits.

Abstract: A solid electrolytic capacitor is provided that contains a casing material that encapsulates the capacitor element. The casing material is formed from a curable resinous matrix that has a coefficient of thermal expansion of about 42 ppm/° C. or less at a temperature above the glass transition temperature of the resinous matrix. Further, the capacitor exhibits an initial equivalence series resistance of about 200 mohms or less as determined at an operating frequency of 100 kHz and temperature of 23° C., and the ratio of the equivalence series resistance of the capacitor after being exposed to a temperature of 125° C. for 560 hours to the initial equivalence series resistance of the capacitor is about 2.0 or less.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: A computer-implemented method, a computer program product, and a system for reducing labeled sample quantities required to update test sets. The computer-implemented method includes inputting a portion of unlabeled production data into a base model and generating labeled output relating to the unlabeled production data. The computer-implemented method also includes inputting the labeled output into a performance predictor. The performance predictor is a meta model of the base model that is trained with another portion of the unlabeled production data, a training set used to train the base model, and a test set portioned from the training set. The computer-implemented method further includes outputting, by the performance predictor, a performance metric relating to the labeled output produced by the trained base model. The performance metric can be any metric capable of measuring the output performance of the base model.

Abstract: A technique for generating a performance prediction of a machine learning model with uncertainty intervals includes obtaining a first model configured to perform a task and a production dataset. At least one metric predicting a performance of the first model at performing the task on the production dataset is generated using a second model. The second model is a meta-model associated with the first model. At least one value predicting an uncertainty of the at least one metric predicting the performance of the first model at performing the task on the production dataset is generated using a third model. The third model is a meta-meta-model associated with the second model. An indication of the at least one metric and the at least one value is provided.

Abstract: A module of capacitor assemblies is provided. To increase the capacitance and efficiency of the module, capacitor assemblies may be stacked. A variety of aspects of the module are controlled in the present invention, including the number of capacitor assemblies, the manner in which the capacitor assemblies are arranged and incorporated into the module, and the manner in which the capacitor assemblies are formed. For example, the anode terminations of each capacitor assembly are electrically connected and the cathode terminations of each capacitor assembly are electrically connected. The capacitance and efficiency of the module can be improved while maintaining the footprint of a single capacitor assembly.

Abstract: A solid electrolytic capacitor comprising a capacitor element, anode lead extending from a surface of the capacitor element, an anode termination that is in electrical connection with the anode lead, a cathode termination that is in electrical connection with the solid electrolyte, and a casing material that encapsulates the capacitor element and anode lead is provided. A barrier coating is disposed on at least a portion of the anode termination and/or cathode termination and is in contact with the casing material. The coating contains a hydrophobic resinous material that includes an olefin polymer having a glass transition temperature of from about 20° C. to about 160° C.

Abstract: A method is provided that includes generating answer-passage pairs, each associated with a respective one of multiple feature vectors. The method includes, for each answer in the pairs, merging the feature vectors associated with any of the pairs that include the answer to obtain a merged answer vector. The method includes, for each passage in the pairs, (i) merging the feature vectors associated with any of the pairs that includes the passage to obtain a merged passage vector, (ii) merging the feature vectors from the merged answer vector for each answer that is associated with the passage via at least one of the pairs to obtain a merged passage-answer vector, and (iii) concatenating the merged passage vector and the merged passage-answer vector to obtain a concatenated passage vector. The method includes ranking the concatenated passage vector for each passage to obtain a ranked list of passages with associated confidence scores.

Abstract: According to one embodiment, a method, computer system, and computer program product for continuously ranking components in a live information is provided. The present embodiment may include receiving search feedback derived from interactions between users and information retrieval systems; assigning weights to each of the ranking components; adjusting the assigned weights based on search feedback; modifying the current set of ranking components based on the search feedback by adding new ranking components and deleting old ranking components; transmitting a query from the users to the current set of ranking components; aggregating ranking results from the transmitted query into a single ranking based on the weights; and transmitting the single ranking to the users.