A latent representation calculation unit (131) uses a first model to calculate, from samples belonging to a domain, a latent representation representing a feature of the domain. A domain-by-domain objective function generation unit (132) and an all-domain objective function generation unit (133) generate, from the samples belonging to the domain and from the latent representation of the domain calculated by the latent representation calculation unit (131), an objective function related to a second model that calculates an anomaly score of each of the samples. An update unit (134) updates the first model and the second model so as to optimize the objective functions of a plurality of the domains calculated by the domain-by-domain objective function generation unit (132) and the all-domain objective function generation unit (133).

An information processing apparatus includes a training unit configured to share encoding layers from a first layer to a (N-n)-th layer having parameters trained in advance by a first model and a second model, and train parameters of a third model through multi-task training including training of the first model and retraining of the second model for a predetermined task, wherein N and n are integers equal to or greater than 1, and satisfies N>n, and in the third model, encoding layers from an ((N-n)+1)-th layer to an N-th layer having parameters trained in advance are divided into the first model and the second model.

A method, a system, and non-transitory computer readable medium for power and ground (P/G) routing for an integrated circuit (IC) design are provided. The method includes generating input features for a machine-learning (ML) model based on IR drop and routing congestion analysis for a P/G network for the IC design, and modifying a set of P/G vias or a set of P/G wires in the P/G network according to modifications identified by the ML model. The ML model comprises a feature extractor pre-trained using a plurality of images of P/G vias and P/G wires.

Methods, systems, and apparatus, including computer programs encoded on computer-readable media, for obtaining, from a first sensor, first sensor data corresponding to an object, wherein the first sensor data is of a first modality; providing the first sensor data to a trained neural network; and generating second sensor data corresponding to the object based at least on an output of the trained neural network, wherein the second sensor data is of a second modality that is different than the first modality.

Techniques described herein relate to a method for predicting results using ensemble models. The method may include receiving trained model data sets from a model source nodes, each trained model data set comprising a trained model, an important feature list, and a missing feature generator; receiving a prediction request data set; making a determination that the prediction request data set does not include an input feature for a trained model; generating, based on the determination and using a missing feature generator, a substitute feature to replace the input feature; executing the trained model using the prediction request data set and the substitute feature to obtain a first prediction; executing a second trained model using the prediction request data set to obtain a second prediction; and obtaining a final prediction using the first prediction, the second prediction, and an ensemble model.

Methods and systems for performing transfer learning with basis scaling and pruning. One method includes obtaining a pre-trained deep convolutional neural network (DCNN), decomposing each weight matrix of the DCNN, and decomposing each convolutional layer by applying the respective decomposed weight matrix to the convolution layer to form a first layer which comprises the left matrix for convolution, and a second layer which comprises the right matrix for convolution. The method also includes providing a basis-scaling convolutional layer having a weight matrix that is derived by a function of singular values and the right singular vectors and training the basis scaling factors of the basis-scaling convolutional layers.

Systems and methods to analyzes images of lateral flow assays are disclosed herein. An example image analysis system includes processor circuitry to (a) determine whether a format of an image of a lateral flow assay device satisfies a format threshold, (b) in response to determining the format of the image satisfies the format threshold, determine whether the lateral flow assay device in the image is authentic, (c) in response to determining the lateral flow assay device is authentic, determine whether a position of the lateral flow assay device in the image satisfies a position threshold, (d) in response to determining the position of the lateral flow assay device satisfies the position threshold, analyze the image to determine the result of the diagnostic test, and (e) abort the sequence of the operations during performance of the sequence of operations at the time any one of operations fails.

Described herein are means for implementing annotation-efficient deep learning models utilizing sparsely-annotated or annotation-free training, in which trained models are then utilized for the processing of medical imaging. An exemplary system includes at least a processor and a memory to execute instructions for learning anatomical embeddings by forcing embeddings learned from multiple modalities; initiating a training sequence of an AI model by learning dense anatomical embeddings from unlabeled date, then deriving application-specific models to diagnose diseases with a small number of examples; executing collaborative learning to generate pretrained multimodal models; training the AI model using zero-shot or few-shot learning; embedding physiological and anatomical knowledge; embedding known physical principles refining the AI model; and outputting a trained AI model for use in diagnosing diseases and abnormal conditions in medical imaging. Other related embodiments are disclosed.

Systems and methods are provided for utilizing polarization parameters obtained from an optical network to determine vibrations in optical fibers using coherent optics equipment and machine learning techniques. A method, according to one implementation, includes the step of obtaining a time-series dataset that includes measurements of polarization characteristics of light traversing an optical fiber of an optical network. The method also includes the step of detecting vibration characteristics of the optical fiber based on the time-series dataset. In some implementations, the time-series dataset may be a multi-variate dataset and the polarization characteristics may be related to transients in a State of Polarization (SOP). The SOP, for example, may be represented by an amplitude and a phase of an electric field vector and may be defined as having one of a linear polarization, elliptical polarization, and circular polarization.

Techniques for extending sensitive data tagging without reannotating training data are described. A method for extending sensitive data tagging without reannotating training data may include hosting a plurality of models at a model endpoint in a machine learning service, each model trained to identify a different sensitive data type in a transcript of content, adding a new model to the model endpoint, the new model trained to identify a new sensitive data entity in the transcript of content, identifying sensitive entities in the transcript by each of the plurality of models and the new model, merging inference responses generated by each of the plurality of models and the new model using at least one inference policy, and returning a merged inference response identifying a plurality of sensitive entities in the transcript.