Ministerio de Industria, Turismo y Comercio LogoMinisterior
 

Neural networks

Resultados 37 results.
LastUpdate Updated on 10/02/2025 [07:14:00]
pdfxls
Solicitudes publicadas en los últimos 30 días / Applications published in the last 30 days
previousPage Results 25 to 37 of 37  

MULTIMODAL DATA-BASED METHOD AND SYSTEM FOR RECOGNIZING COGNITIVE ENGAGEMENT IN CLASSROOM

Publication No.:  US2025022314A1 16/01/2025
Applicant: 
CENTRAL CHINA NORMAL UNIV [CN]
CENTRAL CHINA NORMAL UNIVERSITY
CN_117237766_PA

Absstract of: US2025022314A1

A method and system are introduced for recognizing cognitive engagement in classrooms by utilizing multimodal data. Associated modalities of cognitive engagement are learned from visual and audio data. This approach involves constructing a multidimensional representation model for cognitive engagement that includes behaviors, emotions, and speech. To identify engagement, three distinct deep learning models are employed: You Only Look Once version 8 (Yolov8) for analyzing body posture, Efficient Network (EfficientNet) for facial expressions, and Text Convolution Neural Network (TextCNN) for speech text. These models are trained and refined with the aid of student engagement surveys, leading to a decision-making process that integrates the results from the different modalities. Additionally, a dataset and a data annotation system are developed for engagement recognition. This innovative method aims to achieve detailed engagement recognition, addressing various perception needs in real-world applications.

Multi-Node Influence Based Artificial Intelligence Topology With Processing Influence

Publication No.:  US2025021798A1 16/01/2025
Applicant: 
FANTAGIC HOLDINGS LLC [US]
Fantagic Holdings LLC
US_2025021798_PA

Absstract of: US2025021798A1

A multi-node artificial intelligence topology adapts to service many different overall purposes. Support processing nodes, discriminative AI elements, generative AI elements along with input, output and communication circuitry along with other outside interactions provide the nodal basis for the overall topology. Therewithin, outputs of several nodes drive a single node which uses influence balancing to optimize its own output. Influence is delivered in feed forward and feed back manner. Segmented processing is provided where sections of an overall output goal is processed through the topology in segments, e.g., chapter by chapter of a novel, episode by episode, a full topology processing using internal cross node influence followed by a second full topology processing using both internal cross node and cross segment influence. Pseudo random templating providing constraints used to progress through segments to control an output flow. AI elements can be fully software, use acceleration circuitry, and employ neural network circuitry such as analog and digital versions thereof. Topologies also adapt between local and remote processing locations on a node by node basis, where, for example, some AI elements or nodes operate in the cloud, while other AI elements operate on a particular user's device or other user devices located remotely. Topologies adapt in real time to move nodes to away from a user's device to a cloud counterpart and vice versa as circumstances change.

Multi-Node Influence Based Artificial Intelligence Topology Selection

Publication No.:  US2025021796A1 16/01/2025
Applicant: 
FANTAGIC HOLDINGS LLC [US]
Fantagic Holdings LLC
US_2025021796_PA

Absstract of: US2025021796A1

A multi-node artificial intelligence topology adapts to service many different overall purposes. Support processing nodes, discriminative AI elements, generative AI elements along with input, output and communication circuitry along with other outside interactions provide the nodal basis for the overall topology. Therewithin, outputs of several nodes drive a single node which uses influence balancing to optimize its own output. Influence is delivered in feed forward and feed back manner. Segmented processing is provided where sections of an overall output goal is processed through the topology in segments, e.g., chapter by chapter of a novel, episode by episode, a full topology processing using internal cross node influence followed by a second full topology processing using both internal cross node and cross segment influence. Pseudo random templating providing constraints used to progress through segments to control an output flow. AI elements can be fully software, use acceleration circuitry, and employ neural network circuitry such as analog and digital versions thereof. Topologies also adapt between local and remote processing locations on a node by node basis, where, for example, some AI elements or nodes operate in the cloud, while other AI elements operate on a particular user's device or other user devices located remotely. Topologies adapt in real time to move nodes to away from a user's device to a cloud counterpart and vice versa as circumstances change.

Multi-Node Influence Based Artificial Intelligence Topology Adaptation

Publication No.:  US2025021790A1 16/01/2025
Applicant: 
FANTAGIC HOLDINGS LLC [US]
Fantagic Holdings LLC
US_2025021790_PA

Absstract of: US2025021790A1

A multi-node artificial intelligence topology adapts to service many different overall purposes. Support processing nodes, discriminative AI elements, generative AI elements along with input, output and communication circuitry along with other outside interactions provide the nodal basis for the overall topology. Therewithin, outputs of several nodes drive a single node which uses influence balancing to optimize its own output. Influence is delivered in feed forward and feed back manner. Segmented processing is provided where sections of an overall output goal is processed through the topology in segments, e.g., chapter by chapter of a novel, episode by episode, a full topology processing using internal cross node influence followed by a second full topology processing using both internal cross node and cross segment influence. Pseudo random templating providing constraints used to progress through segments to control an output flow. AI elements can be fully software, use acceleration circuitry, and employ neural network circuitry such as analog and digital versions thereof. Topologies also adapt between local and remote processing locations on a node by node basis, where, for example, some AI elements or nodes operate in the cloud, while other AI elements operate on a particular user's device or other user devices located remotely. Topologies adapt in real time to move nodes to away from a user's device to a cloud counterpart and vice versa as circumstances change.

Multi-Node Influence Based Artificial Intelligence Topology With Influence Data

Publication No.:  US2025021797A1 16/01/2025
Applicant: 
FANTAGIC HOLDINGS LLC [US]
Fantagic Holdings LLC
US_2025021797_PA

Absstract of: US2025021797A1

A multi-node artificial intelligence topology adapts to service many different overall purposes. Support processing nodes, discriminative AI elements, generative AI elements along with input, output and communication circuitry along with other outside interactions provide the nodal basis for the overall topology. Therewithin, outputs of several nodes drive a single node which uses influence balancing to optimize its own output. Influence is delivered in feed forward and feed back manner. Segmented processing is provided where sections of an overall output goal is processed through the topology in segments, e.g., chapter by chapter of a novel, episode by episode, a full topology processing using internal cross node influence followed by a second full topology processing using both internal cross node and cross segment influence. Pseudo random templating providing constraints used to progress through segments to control an output flow. AI elements can be fully software, use acceleration circuitry, and employ neural network circuitry such as analog and digital versions thereof. Topologies also adapt between local and remote processing locations on a node by node basis, where, for example, some AI elements or nodes operate in the cloud, while other AI elements operate on a particular user's device or other user devices located remotely. Topologies adapt in real time to move nodes to away from a user's device to a cloud counterpart and vice versa as circumstances change.

METHOD AND A SYSTEM FOR PERFORMING A REAL-TIME PREDICTIVE MODELING OF AN ARTIFICIAL NEURAL NETWORK MODEL AT A CLIENT DEVICE

Publication No.:  US2025021845A1 16/01/2025
Applicant: 
AFFLE MEA FZ LLC [AE]
Affle MEA FZ-LLC
US_2025021845_PA

Absstract of: US2025021845A1

According to an aspect of one or more embodiments, a system for performing a real-time predictive modeling at a client device may include an ANN model in the client device configured to generate an inference performance associated with the trainable ANN model associated with an action performed at the client device based on data comprising a plurality of features associated with the client device, wherein the inference performance is transmitted. The trainable ANN model is configured to receive a loss calculation generated based on the inference performance, indicating a requirement to correct the trainable ANN model, wherein the trainable ANN model generates one or more corrections for coefficients of the trainable ANN model based on the loss calculation. The trainable ANN model is configured to generate one or more coefficients associated with the trainable ANN model and the data, by convoluting the data, and the trainable model. The trainable ANN model is configured to transmit one or more of the one or more corrections and the one or more coefficients indicating a successful predictive modeling of the trainable ANN model with the generation of the trainable ANN model.

Multi-Node Influence Based Artificial Intelligence Topology With Segment Influence

Publication No.:  US2025021843A1 16/01/2025
Applicant: 
FANTAGIC HOLDINGS LLC [US]
Fantagic Holdings LLC
US_2025021843_PA

Absstract of: US2025021843A1

A multi-node artificial intelligence topology adapts to service many different overall purposes. Support processing nodes, discriminative AI elements, generative AI elements along with input, output and communication circuity along with other outside interactions provide the nodal basis for the overall topology. Therewithin, outputs of several nodes drive a single node which uses influence balancing to optimize its own output. Influence is delivered in feed forward and feed back manner. Segmented processing is provided where sections of an overall output goal is processed through the topology in segments, e.g., chapter by chapter of a novel, episode by episode, a full topology processing using internal cross node influence followed by a second full topology processing using both internal cross node and cross segment influence. Pseudo random templating providing constraints used to progress through segments to control an output flow. AI elements can be fully software, use acceleration circuitry, and employ neural network circuitry such as analog and digital versions thereof. Topologies also adapt between local and remote processing locations on a node by node basis, where, for example, some AI elements or nodes operate in the cloud, while other AI elements operate on a particular user's device or other user devices located remotely. Topologies adapt in real time to move nodes to away from a user's device to a cloud counterpart and vice versa as circumstances change.

TRAINING NEURAL NETWORKS FOR VEHICLE RE-IDENTIFICATION

Publication No.:  US2025022092A1 16/01/2025
Applicant: 
NVIDIA CORP [US]
NVIDIA Corporation
CN_118609067_PA

Absstract of: US2025022092A1

In various examples, a neural network may be trained for use in vehicle re-identification tasks—e.g., matching appearances and classifications of vehicles across frames—in a camera network. The neural network may be trained to learn an embedding space such that embeddings corresponding to vehicles of the same identify are projected closer to one another within the embedding space, as compared to vehicles representing different identities. To accurately and efficiently learn the embedding space, the neural network may be trained using a contrastive loss function or a triplet loss function. In addition, to further improve accuracy and efficiency, a sampling technique—referred to herein as batch sample—may be used to identify embeddings, during training, that are most meaningful for updating parameters of the neural network.

ARTIFICIAL INTELLIGENCE DEVICE FOR A DIGITIAL AVATAR WITH 3D INTERATION CAPABILITIES AND CONTROL METHOD THEREOF

Publication No.:  US2025022200A1 16/01/2025
Applicant: 
LG ELECTRONICS INC [KR]
LG ELECTRONICS INC
US_2025022200_PA

Absstract of: US2025022200A1

A method for controlling an artificial intelligence (AI) device for implementing a digital avatar can include receiving an audio signal corresponding to a user query, converting, by a speech-to-text neural network model, the audio signal into a text query, inputting the text query into a large language gesture instruction model to generate high level movement instructions, inputting the text query and the high level movement instructions into an information retrieval model to generate a text response including at least one sentence and digital avatar control information, and inputting the text response into a text-to-speech neural network model to generate an audio response. Also, the method can include inputting the audio response into an audio-to-facial animation model and an audio-to-conversational gesture model to generate updated digital avatar control information including gesture information, and outputting the audio response and the updated digital avatar control information for controlling the digital avatar.

DEVICE AND COMPUTER IMPLEMENTED METHOD FOR MACHINE LEARNING, TECHNICAL SYSTEM COMPRISING THE DEVICE

Publication No.:  EP4492083A1 15/01/2025
Applicant: 
BOSCH GMBH ROBERT [DE]
Robert Bosch GmbH
EP_4492083_PA

Absstract of: EP4492083A1

A device and a computer implemented method for machine learning, wherein the method comprises providing a first model (300), in particular a neural network that comprises weights, that is configured to map data (302) of a first radar spectrum, in particular data from a region of interest of the first radar spectrum, to first features (304) that represent the data (302), providing the data (302) and a physical attribute of the data, in particular a range (108), an azimuth, a velocity or an indication of the polarizations of the sent and received radar signals that the data is based on, providing a first output (306) that is configured to map the first features (304) to a prediction of the physical attribute, in particular a prediction (310) of the range, a prediction (314) of the azimuth, a prediction (316) of the velocity or a prediction (322, ..., 328) of the indication of the polarizations of the sent and received radar signals, mapping the data (302) with the first model (300) to the first features (304), mapping the first features (304) with the first output (306) to the prediction of the physical attribute, and learning the first model (300), in particular learning the weights, depending on a difference between the prediction of the physical attribute and the physical attribute. A technical system comprising the device.

Method and system for predicting biological entities

Publication No.:  GB2631816A 15/01/2025
Applicant: 
BENEVOLENTAL TECH LIMITED [GB]
BenevolentAl Technology Limited
GB_2631816_PA

Absstract of: GB2631816A

Computer-implemented method comprising: providing an inference knowledge base comprising a corpus of textual data; receiving a user query defining a biological requirement for which a biological entity is to be predicted; obtaining, based on the query, a query sentence text describing the requirement and including mention of an entity, wherein the entity is masked; selecting a candidate entity for the masked entity and retrieving a plurality of evidence sentences from the knowledge base, each including mention of the candidate, based on computing a similarity of the query sentence to sentences within the knowledge base; inputting each training query sentence and a plurality of retrieved evidence sentences into a reasoner model, where the candidate is masked in the query sentence and evidence sentences, the reasoner model trained to predict a probability that the candidate is the masked entity based on the retrieved evidence sentences. Also disclosed is a method of training the machine learning reasoner model; and a method in which a contribution of each evidence sentence used in the prediction to the predicted probability is computed and the evidence sentences that have the greatest contribution are output. Model may comprise artificial neural network. Entity may comprise drug target.

COGNITIVE COMPUTING METHODS AND SYSTEMS BASED ON BIOLOGICAL NEURAL NETWORKS

Nº publicación: EP4492294A2 15/01/2025

Applicant:

FINALSPARK SARL [CH]
FinalSpark Sarl

EP_4492294_A2

Absstract of: EP4492294A2

A Biological Operating System (750) comprising an in vitro biological culture of neural cells (BNN culture (120)) core unit (100); an input stimulation unit SU (110) configured to apply an input spatio-temporal stimulation signal (605) into a first set of the neural cells; an output readout unit RU (130) configured to capture an output spatio-temporal readout signal (635) from a second set of the neural cells; an automated vascularization system (300) configured to provide nutrients and additives to the BNN culture (120) and to collect nutrients and additives waste therefrom; one or more sensors to measure at least one environmental parameter of the BNN culture (120); a BNN health control unit (710), configured to monitor the health and regulate the performance through time of the BNN cell culture (120), wherein the BNN health control unit (710) comprises a chemical control unit, configured to control the supply of the nutrients and additives to the BNN cell culture (120)as well as the waste collection therefrom; and an environmental control unit configured to control the at least one environmental parameter; a BNN health control software (700), configured for real time control of the operation of the BNN health control unit (710); a BNN functional interface (730) operatively connected to the input stimulation unit SU (110) and the output readout unit RU (130) and configured to process in real-time the input spatio-temporal stimulation signal (605) and the output spatio-tempo

traducir