Redes Neuronais

METHOD AND SYSTEM FOR IDENTIFYING HIERARCHICAL RELATIONSHIPS BETWEEN DATA ELEMENTS OF DOCUMENT

Resumen de: US2024320483A1

Disclosed is a method for identifying multi-level hierarchical relationships between data elements of a document, the method comprising receiving a plurality of sample documents each having a plurality of data elements arranged in a multi-level hierarchical data structure; classifying each of the plurality of data elements into a key entity field or a key field value based on a hierarchical relationship therebetween; identifying key entity fields, from among the classified key entity field of the plurality of data elements, having the hierarchical relationship therebetween; pairing the key entity field, with a corresponding key field value or an identified key entity field, to form a training dataset; and employing the training dataset on a neural network framework, having at least one of a textual modality or a visual modality, to identify the multi-level hierarchical relationships between the data elements of the document.

METHODS AND SYSTEMS FOR PERFORMING A SPARSE SUBMANIFOLD CONVOLUTION USING AN NNA

Resumen de: US2024320298A1

Methods of implementing a sparse submanifold convolution using a neural network accelerator. The methods include: receiving, at the neural network accelerator, an input tensor in a sparse format; performing, at the neural network accelerator, for each position of a kernel of the sparse submanifold convolution, a 1×1 convolution between the received input tensor and weights of filters of the sparse submanifold convolution at that kernel position to generate a plurality of partial outputs; and combining appropriate partial outputs of the plurality of partial outputs to generate an output tensor of the sparse submanifold convolution in sparse format.

OPTICAL INFORMATION READING DEVICE

Resumen de: US2024320455A1

To suppress an increase in processing time due to a load of inference processing while improving reading accuracy by the inference processing of machine learning. An optical information reading device includes a processor including: an inference processing part that inputs a code image to a neural network and executes inference processing of generating an ideal image corresponding to the code image; and a decoding processing part that executes first decoding processing of decoding the code image and second decoding processing of decoding the ideal image generated by the inference processing part. The processor executes the inference processing and the first decoding processing in parallel, and executes the second decoding processing after completion of the inference processing.

RULE VISUALIZATION

Resumen de: US2024320501A1

A computer that includes a processor and a memory, the memory including instructions executable by the processor to train a neural network to input data and output a prediction. A policy can be generated based on the data. Force features can be generated based on the policy. Decision nodes can be trained based on force features and a binary vector from the trained neural network. A decision tree can be generated based on the decision nodes. A decision can be generated by inputting a policy to the decision tree. The decision can be compared to the prediction and the neural network re-trained based on a difference between the decision and the prediction.

EXPLAINING NEURO-SYMBOLIC REINFORCEMENT LEARNING REASONING

Resumen de: US2024320503A1

Examples described herein provide a method for explaining neuro-symbolic reinforcement learning reasoning in a neuro-symbolic neural network for neuro-symbolic artificial intelligence. The method includes selecting an action from among possible candidates taken in an environment, wherein the action comprises a pair of a verb and an entity and displaying one or more logical facts that are extracted from natural observation sentences of the environment. The method also includes visualizing contrastive information for a current state and a goal state which is from external knowledge and displaying trained rules in the neuro-symbolic neural network for neuro-symbolic artificial intelligence, wherein, in response to a first user selection of the action, highlighting each pair of the verb and the entity and a fired predicate corresponding to the first user selection.

ASSIGNING OBSTACLES TO LANES USING NEURAL NETWORKS FOR AUTONOMOUS MACHINE APPLICATIONS

Resumen de: US2024320986A1

In various examples, live perception from sensors of an ego-machine may be leveraged to detect objects and assign the objects to bounded regions (e.g., lanes or a roadway) in an environment of the ego-machine in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as output segmentation masks—that may correspond to a combination of object classification and lane identifiers. The output masks may be post-processed to determine object to lane assignments that assign detected objects to lanes in order to aid an autonomous or semi-autonomous machine in a surrounding environment.

THIRD-PARTY SERVICE FOR SUGGESTING RESOURCES FOR A RECEIVED MESSAGE

Resumen de: US2024320686A1

A third-party service may be used to assist entities in responding to requests of users by determining a suggested resource corresponding to a received communication. The third party service may receive a request from a first entity, such as via an application programming interface request, that includes a message in a conversation. A conversation feature vector may be computed by processing the message with a first neural network. A suggested resource may be determined using the conversation feature vector. The third-party service may then return the suggested resource for use in the conversation. The third-party service may similarly be used to assist other entities in responding to requests of users.

NEURAL NETWORK CONFIGURATION PARAMETER TRAINING AND DEPLOYMENT METHOD AND APPARATUS FOR COPING WITH DEVICE MISMATCH

Resumen de: US2024320337A1

A neural network (NN) configuration parameter training and deployment method and apparatus are disclosed. The method and the apparatus include searching for simulated attacked NN configuration parameters on a basis of NN configuration parameters, so that the attacked NN configuration parameters move in a direction of maximal divergence from an NN output result corresponding to the NN configuration parameters; taking a difference in an NN output result between the current NN configuration parameters and the attacked NN configuration parameters as a robustness loss function which serves as a part of a total loss function; and finally, optimizing the NN configuration parameters on a basis of the total loss function. Especially for sub-threshold and mixed-signal circuits with ultra-low power consumption, the solution can solve a problem of perturbations of configuration parameters caused by device mismatch, and achieve the technical effect of low-cost and high-efficiency deployment of parameters of NN accelerators.

ENHANCING HYBRID TRADITIONAL NEURAL NETWORKS WITH LIQUID NEURAL NETWORK UNITS FOR CYBER SECURITY AND OFFENSE PROTECTION

Resumen de: US2024323203A1

Aspects of the disclosure relate to enhancing hybrid traditional neural networks with liquid neural networks for cyber security and offense protection. A computing platform may receive a request to access enterprise organization data. The computing platform may compare the current request to previous requests to determine whether a similar request was previously processed. If a similar request was not previously processed, the computing platform may flag the request as a threat and may analyze the request. The computing platform may extract data from the request and may use the extracted data to generate rules, threat detection algorithms, and training models. The computing platform may use the rules, threat detection algorithms, and training models to train a deep learning neural network to identify and handle threats to an enterprise organization.

MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD, AND MACHINE LEARNING DEVICE

Resumen de: WO2024195280A1

Problem To input the feature of causal relation between words into a causal relation extraction model and perform machine learning. Solution A learning device 10 acquires, in correspondence with individual words included in the text of training data 135, third correspondence information that is generated on the basis of first correspondence information in which words and vectors are associated on the basis of word embedding and second correspondence information in which words and vectors are associated on the basis of the correlation of a word pair between a first word indicating a cause and a second word indicating a result that is based on the cause indicated by the first word. The learning device 10 uses the acquired third correspondence information to execute training of a neural network that performs natural language processing.

EFFICIENT HARDWARE ACCELERATOR CONFIGURATION EXPLORATION

Resumen de: US2024311267A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a surrogate neural network configured to determine a predicted performance measure of a hardware accelerator having a target hardware configuration on a target application. The trained instance of the surrogate neural network can be used. in addition to or in place of hardware simulation, during a search process for determining hardware configurations for application-specific hardware accelerators. i.e., hardware accelerators on which one or more neural networks can be deployed to perform one or more target machine learning tasks.

SYSTEM AND METHOD FOR NEURAL NETWORK ORCHESTRATION

Resumen de: US2024312184A1

Methods and systems for training one or more neural networks for transcription and for transcribing a media file using the trained one or more neural networks are provided. One of the methods includes: segmenting the media file into a plurality of segments; inputting each segment, one segment at a time, of the plurality of segments into a first neural network trained to perform speech recognition; extracting outputs, one segment at a time, from one or more layers of the first neural network; and training a second neural network to generate a predicted-WER (word error rate) of a plurality of transcription engines for each segment based at least on outputs from the one or more layers of the first neural network.

FOVEATING NEURAL NETWORK

Nº publicación: US2024314452A1 19/09/2024

Solicitante:

VARJO TECH OY [FI]
Varjo Technologies Oy