FIDELITY-BASED EXPLANABILITY FOR GNNS

    公开(公告)号:US20250103866A1

    公开(公告)日:2025-03-27

    申请号:US18890888

    申请日:2024-09-20

    Abstract: Methods and systems include processing an input graph using a graph neural network (GNN) to generate an output. An explanation sub-graph is generated using an explainer that identifies parts of the input graph that most influence the output. A fidelity measure of the explanation sub-graph is determined that is robust against distribution shifts. An action is performed responsive to the output, the explanation sub-graph, and the fidelity measure.

    VERIFYING COMPLEX SENTENCES WITH ARTIFICIAL INTELLIGENCE

    公开(公告)号:US20250103812A1

    公开(公告)日:2025-03-27

    申请号:US18888763

    申请日:2024-09-18

    Abstract: Systems and methods for verifying complex sentences with artificial intelligence. Claim sentences can be filtered with source texts using a confirmation threshold, an unsupported threshold, and entailment probabilities computed by a natural language inference (NLI) classifier to obtain initial verification pairs. A trained imagination model can generate entailment outputs by employing initial verification pairs. A trained generalization model can generate generalized outputs by generalizing entailment outputs. Missing evidence generalizations can be chosen from sampled generalized outputs based on overlaps between sampled generalized outputs The NLI classifier can compute a final verification decision of the source texts against the missing evidence generalizations to obtain verified claim sentences. A corrective action for a monitored entity can be performed using the verified claim sentences.

    CORRELATION-AWARE EXPLAINABLE ONLINE CHANGE POINT DETECTION

    公开(公告)号:US20250062953A1

    公开(公告)日:2025-02-20

    申请号:US18800726

    申请日:2024-08-12

    Abstract: Systems and methods for correlation-aware explainable online change point detection. Collected data metrics from the cloud system can be transformed to correlation matrices. Correlation shifts from the correlation matrices can be captured as differences of correlation between batches of collected data metrics through determined statistics of the batches of collected data metrics across timesteps. Change points in the cloud system can be detected based on the correlation shifts to obtain detected change points. System maintenance can be performed autonomously based on the detected change points from identified system entities to optimize the cloud system with an updated configuration.

    LANGUAGE MODELS WITH DYNAMIC OUTPUTS

    公开(公告)号:US20250053774A1

    公开(公告)日:2025-02-13

    申请号:US18776926

    申请日:2024-07-18

    Abstract: Methods and systems for answering a query include generating first tokens in response to an input query using a language model, the first tokens including a retrieval rule. A retrieval rule is used to search for information to generate dynamic tokens. The retrieval rule in the first tokens is replaced with the dynamic tokens to generate a dynamic partial response. Second tokens are generated in response to the input query. The second tokens are appended to the dynamic partial response to generate an output responsive to the input query.

    Enhanced word embedding
    6.
    发明授权

    公开(公告)号:US12205026B2

    公开(公告)日:2025-01-21

    申请号:US17674461

    申请日:2022-02-17

    Abstract: Methods and systems for language processing include augmenting an original training dataset to produce an augmented dataset that includes a first example that includes a first scrambled replacement for a first word and a definition of the first word, and a second example that includes a second scrambled replacement for the first word and a definition of an alternative to the first word. A neural network classifier is trained using the augmented dataset.

    Fiber sensing on roadside applications

    公开(公告)号:US12154007B2

    公开(公告)日:2024-11-26

    申请号:US16229676

    申请日:2018-12-21

    Abstract: A fiber-based roadside condition sensing system is provided. The system includes a fiber optic cable arranged in various roadside locations for Distributed Vibration Sensing (DVS) and Distributed Acoustic Sensing (DAS) at the various roadside locations. The system further includes a machine-learning-based analyzer for selectively providing any of an early warning and a prevention of various detected conditions responsive to a machine-learning-based analysis of results from the DVS and the DAS.

    OPTIMIZING MODELS FOR OPEN-VOCABULARY DETECTION

    公开(公告)号:US20240378454A1

    公开(公告)日:2024-11-14

    申请号:US18659738

    申请日:2024-05-09

    Abstract: Systems and methods for optimizing models for open-vocabulary detection. Region proposals can be obtained by employing a pre-trained vision-language model and a pre-trained region proposal network. Object feature predictions can be obtained by employing a trained teacher neural network with the region proposals. Object feature predictions can be filtered above a threshold to obtain pseudo labels. A student neural network with a split-and-fusion detection head can be trained by utilizing the region proposals, base ground truth class labels and the pseudo labels. The pseudo labels can be optimized by reducing the noise from the pseudo labels by employing the trained split-and-fusion detection head of the trained student neural network to obtain optimized object detections. An action can be performed relative to a scene layout based on the optimized object detections.

Patent Agency Ranking