Alerta

MODULAR CONCEPT-BASED LANGUAGE PROCESSING WITH TRACE-DRIVEN RESOURCE TIERING AND DYNAMIC CACHING

Absstract of: US20260211817A1

0000 Modular systems and methods for concept-based processing of natural language are provided. An ontology dictionary stores concepts each having a concept identifier, attributes, and typed relationships. Natural language inputs are mapped to concept identifiers, optionally by deriving intermediate units using transforms or statistical analysis and mapping the intermediate units to concepts, or by mapping raw tokens to concepts. A neural network model processes the concept identifiers to generate outputs. During inference and/or training, a trace engine records activation information associated with concepts and stores activation information or derived statistics in a trace data structure. A resource controller uses the trace data structure to reconfigure, during inference for subsequent inputs, a resource allocation policy that allocates frequently used concept data to a faster memory tier and allocates infrequently used concept data to a slower tier or specialized tail handling. Predictive prefetching and relational group caching may be performed.

HYBRID DEEP LEARNING FRAMEWORK FOR FLOOD SUSCEPTIBILITY MAPPING

Absstract of: US20260212194A1

0000 A method for training deep neural network for flood susceptibility prediction includes receiving training data including flood conditioning factor data for spatial units of geographic region together with ground truth data. The method includes inputting training data into deep neural network. The method includes generating plurality of candidate solutions, each candidate solution including parameter vector of weights and biases encoding relationships between flood conditioning factors and flood susceptibility outcomes. Further, the method includes refining each retained candidate solution by applying local search optimization process to minimize cost function computed relative to ground truth data. The method further includes selecting trained set of weights and biases for deep neural network from among refined solutions. Further, the method includes applying trained set of weights and biases to deep neural network to generate trained deep neural network configured to produce flood susceptibility probabilities for input flood conditioning factor data.

SYSTEMS, APPARATUSES, AND METHODS FOR DISEASE PREDICTION

Absstract of: WO2026155960A1

A system for training a graph neural network (GNN) for disease prediction includes at least one memory configured to store instructions and at least one processor configured to execute the instructions to cause the system to obtain a plurality of first parameter values of parameters from individuals, determine a causal structure indicative of one or more causal relationships between the plurality of parameters based on the plurality of parameters, and train the at least one GNN with the one or more causal relationships to create a trained GNN, the trained GNN configured to output a disease prediction based on second parameter values, the second parameter values being parameter values of parameters from a patient.

METHOD AND SYSTEM FOR AI-BASED REAL-TIME ANALYSIS OF ENTITY DATA

Absstract of: US20260212410A1

A system for an automated real-time analysis and generation of predictive entity scoring based on entity data including a processor of a predictive scoring server (PSS) node configured to host a machine learning (ML) module coupled to at least one target user-entity node and to a plurality of remote nodes associated with the at least one target entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire target entity profile data from the at least one target entity node, the target entity profile data including action metrics associated with the at least one target entity and the plurality of remote nodes; perform normalization of the target entity profile data based on the action metrics; parse the normalized data to derive a plurality of classifying features; generate a feature vector based on the plurality of classifying features; ingest the feature vector into the ML module coupled to an Artificial Neural Network (ANN); receive a plurality of predictive scoring parameters from at least one entity scoring predictive model generated by the ML module using outputs of the ANN based on the feature vector; and generate at least one score for the at least one entity node based on the plurality of predictive scoring parameters.

APPARATUS AND METHOD FOR OBJECT DETECTION USING SPIKING NEURAL NETWORK

Absstract of: KR20260114892A

스파이킹 뉴럴 네트워크를 이용한 객체 탐지 장치 및 방법이 개시되며, 본원의 일 실시예에 따른 스파이킹 뉴럴 네트워크를 이용한 객체 탐지 방법은, (a) 입력된 대상 영상을 상기 스파이킹 뉴럴 네트워크의 백본(Backbone) 네트워크에 입력하여 상기 대상 영상으로부터 공간적 특징을 추출하는 단계, (b) 상기 공간적 특징을 상기 스파이킹 뉴럴 네트워크의 넥(Neck) 네트워크에 입력하여 상기 공간적 특징을 다중 스케일 특징으로 정제하는 단계 및 (c) 상기 다중 스케일 특징을 통합하여 상기 스파이킹 뉴럴 네트워크의 헤드(Head) 네트워크에 입력하여 상기 대상 영상에 포함된 타겟 객체에 대한 인식 정보를 도출하는 단계를 포함할 수 있다.

CONTENT RECOMMENDATION METHOD, CONTENT FEATURE EXTRACTION METHOD, AND APPARATUS

Absstract of: WO2026152788A1

A content recommendation method, relating to the technical field of artificial intelligence. The method comprises: acquiring a semantic embedding vector, a positional embedding vector, and a temporal embedding vector of each behavior item in a historical behavior sequence of a user; in a neural network model, performing attention processing on a first channel feature, and performing linear processing on a second channel feature to obtain a user feature, wherein the first channel feature comprises the semantic embedding vector, and the second channel feature comprises at least one of the positional embedding vector and the temporal embedding vector; and on the basis of the user feature, recommending to the user content that matches preferences of the user. In this way, by separating at least one of semantic information, positional information, and temporal information of each behavior item in the historical behavior sequence, the limitation of positional and/or temporal relationships can be removed, thereby achieving better efficiency and enabling finer-grained modeling of interactions among items in different dimensions, thus achieving better accuracy.

LIGHT RENDERING METHOD AND APPARATUS, COMPUTER DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM

Absstract of: US20260212595A1

A light rendering method includes: performing light effect detection on a rendered image, to obtain a detection result; in response to the detection result indicating that a first object vertex not meeting a light rendering condition exists in the rendered image, obtaining, along a light path on which the first object vertex is located, light information of a second object vertex that is in the rendered image and that meets the light rendering condition; training a neural network based on the light information of the second object vertex, to obtain a trained neural network; extracting light information of object vertexes including the first object vertex in a target image by using the trained neural network, to obtain the light information of the object vertexes; and performing light rendering on the target image based on the light information of the object vertexes.

SELF-DEVELOPING NEURAL NETWORK DESIGN METHOD INSPIRED BY DNA DAMAGE REPAIR MECHANISM, AND STORAGE MEDIUM

Absstract of: WO2026152352A1

A self-developing neural network design method inspired by a DNA damage repair mechanism, and a storage medium. The method comprises: selecting a neural network model and defining hyperparameters thereof; acquiring an image dataset, and dividing the image dataset into a training set, a validation set and a test set, in order to form sequential tasks; on the basis of data of the first task in the training set, training the neural network model; on the basis of data of the first task in the validation set, testing a trained neural network model; performing self-developing growth on the neural network model in the width and depth directions, in order to increase the scale of the neural network model; repeating the above training and testing processes, determining whether it is necessary to further increase the scale of the neural network model, and if the increase is stopped, acquiring the classification accuracy of the model based on task data in the test set; and repeating the above process until the testing of all the task data in the test set is completed. The scale of a neural network model is dynamically adjusted during a training process, and new neurons are grown to adapt to changing tasks and environments, thereby promoting the intelligent development of neural networks in image classification tasks and the practical application thereof.

LATENCY-BASED STRUCTURED PRUNING OF NEURAL NETWORKS

Absstract of: US20260212182A1

0000 Systems and methods are disclosed for pruning artificial deep neural networks. The systems and methods receive input comprising a target latency associated with executing a machine learning model on a specified device. The systems and methods modify a set of parameters of the machine learning model to reduce a latency associated with the machine learning model based on the target latency. The systems and methods apply the machine learning model with the modified set of parameters to a data set to generate an output.

ELASTIC ADAPTER FOR FINE-TUNING NEURAL NETWORK

Absstract of: WO2026152640A1

A pretrained neural network may be fine-tuned using one or more elastic adapters, each of which may be inserted into the pretrained neural network at a position that is immediately after a corresponding layer of the pretrained neural network. An elastic adapter may include a first linear layer and a second linear layer. During the fine-tuning, one or more internal parameters (e.g., weights) of the elastic adapter may be updated based on a loss function, while internal parameters of the corresponding layer (e.g., pretrained weights) may be fixed. After the fine-tuning, the first linear layer may be merged with the corresponding layer to form a new layer. The new layer may replace the corresponding layer in the neural network. The updated neural network, which has the new layer and the second linear layer, may be a fine-tuned neural network and may be used to perform one or more AI tasks.

TRAINING REINFORCEMENT LEARNING AGENTS TO LEARN FARSIGHTED BEHAVIORS BY PREDICTING IN LATENT SPACE

Absstract of: US20260208355A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection policy neural network used to select an action to be performed by an agent interacting with an environment. In one aspect, a method includes: receiving a latent representation characterizing a current state of the environment; generating a trajectory of latent representations that starts with the received latent representation; for each latent representation in the trajectory: determining a predicted reward; and processing the state latent representation using a value neural network to generate a predicted state value; determining a corresponding target state value for each latent representation in the trajectory; determining, based on the target state values, an update to the current values of the policy neural network parameters; and determining an update to the current values of the value neural network parameters.

ABSTRACTION LIBRARY TO ENABLE SCALABLE DISTRIBUTED MACHINE LEARNING

Absstract of: US20260212440A1

One embodiment provides for a non-transitory machine readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising providing an interface to define a neural network using machine-learning domain specific terminology, wherein the interface enables selection of a neural network topology and abstracts low-level communication details of distributed training of the neural network.

MACHINE LEARNING MODELS FOR BEHAVIOR UNDERSTANDING

Absstract of: US20260212162A1

0000 A method for performing one or more tasks, wherein each of the one or more tasks includes predicting behavior of one or more agents in an environment, the method comprising: obtaining a three-dimensional (3D) input tensor representing behaviors of the one or more agents in the environment across a plurality of time steps; generating an encoded representation of the 3D input tensor by processing the 3D input tensor using an encoder neural network, wherein 3D input tensor comprises a plurality of observed cells and a plurality of masked cells; and processing the encoded representation of the 3D input tensor using a decoder neural network to generate a 4D output tensor.

AUTOMATED ANEUPLOIDY SCREENING USING ARBITRATED ENSEMBLES

Absstract of: AU2026205299A1

Abstract Systems and methods are provided for fully automated screening for aneuploidy in a human embryo. An image of the embryo is obtained at an associated imager and provided to a neural network to generate a first clinical parameter. A set of at least one parameter representing one of biometric parameters of one of a patient receiving the embryo, an egg utilized to produce the human embryo, a sperm used to create the embryo, a sperm donor who provided sperm used to create the embryo, and an egg donor who provided the egg is retrieved, and a second clinical parameter is generated from the set of at least one parameter at a predictive model. A composite parameter, representing a likelihood of aneuploidy in the embryo, is generated from the first clinical parameter and the second clinical parameter. Abstract ul u l b s t r a c t

SYSTEM AND METHOD FOR PROCESSING ULTRASOUND IMAGES

Absstract of: US20260212999A1

0000 A computer-implemented method provides real-time visual guidance for orienting an ultrasound probe toward a canonical ultrasound view. The method involves receiving successive ultrasound images acquired by the probe during a scanning procedure. A trained neural network generates a spatial mapping from the received images without reliance on external position or motion sensors. This mapping encodes adjustments in probe position and rotation needed to achieve a target spatial pose associated with the canonical view. The spatial mapping is then transformed into visual guidance data. One or more visual guidance elements, derived from this data, are generated and displayed on a graphical user interface to instruct a user on how to manipulate the probe. The visual guidance elements are continuously updated until the canonical ultrasound view is achieved, helping non-experts capture high-quality diagnostic images.

Machine-Learning Techniques For Monotonic Neural Networks

Absstract of: AU2026205315A1

Abstract In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions. Abstract ul b s t r a c t u l

AUTOMATIZED DETECTION OF INTESTINAL INFLAMMATION IN CROHN'S DISEASE USING CONVOLUTIONAL NEURAL NETWORK

Absstract of: US20260212495A1

0000 The invention relates to system and methods for predicting and/or diagnosing of IBD from ultrasound images according to one or more of diagnostic signs.

METHODS AND APPARATUSES FOR CHARACTERIZING CHEMICAL SUBSTANCES, MEASURING PHYSICOCHEMICAL PROPERTIES AND GENERATING CONTROL DATA FOR SYNTHESIZING CHEMCIAL SUBSTANCES

Absstract of: US20260212962A1

Provided is a method for generating a digital representation of a chemical substance. This may involve training aspects of neural networks to represent chemical sub-stances. Provided further relates to applications of the digital representation including a computer program product, a database search engine for identifying chemical sub-stances, apparatuses for generating measurement data associated with chemical substances and control data associated with synthesis specifications for chemical substances.

FPGA-ORIENTED DSP PLACEMENT OPTIMIZATION METHOD FOR CNN ACCELERATORS

Absstract of: US20260212104A1

An FPGA-oriented DSP placement optimization method for CNN accelerators includes the following steps: S1. DSP path information extraction: converting a designed netlist into a graph representation, and carrying out data-path DSP node identification and data-path DSP graph building; and S2. datapath-driven DSP placement: distributing data-path DSP nodes to specific positions on an FPGA according to an extracted data-path DSP graph. According to the invention, automated extraction and building of data-path DSP graphs are carried out by means of graph neural network (GCN)-based DSP node classification and min-cost flow (MCF) model optimization algorithms, and compact placement and cascade constraint optimization are used in combination, thereby greatly improving the timing performance and computing efficiency of the placement and also significantly improving the clock frequency and throughput. Therefore, the method provides a universal and efficient FPGA placement solution for multiple CNN accelerator architectures.

PERFORMING TASKS USING GENERATIVE NEURAL NETWORKS

Absstract of: US20260212167A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing tasks. One of the methods includes obtaining a sequence of input tokens, where each token is selected from a vocabulary of tokens that includes text tokens and audio tokens, and wherein the sequence of input tokens includes tokens that describe a task to be performed and data for performing the task; generating a sequence of embeddings by embedding each token in the sequence of input tokens in an embedding space; and processing the sequence of embeddings using a language model neural network to generate a sequence of output tokens for the task, where each token is selected from the vocabulary.

INTELLIGENT TRANSPORTATION SYSTEMS

Absstract of: EP4778450A2

0001 Transportation systems have artificial intelligence including neural networks for recognition and classification of objects and behavior including natural language processing and computer vision systems. The transportation systems involve sets of complex chemical processes, mechanical systems, and interactions with behaviors of operators. System-level interactions and behaviors are classified, predicted and optimized using neural networks and other artificial intelligence systems through selective deployment, as well as hybrids and combinations of the artificial intelligence systems, neural networks, expert systems, cognitive systems, genetic algorithms and deep learning.

MULTI-VIEW CONVOLUTIONAL NEURAL NETWORKS FOR VIDEO PROCESSING

Absstract of: WO2025058768A1

The present disclosure relates to processing video data. Some aspects involve partitioning input video data into two or more clips, each clip comprising a number of T frames, wherein each frame comprises a frame height, a frame width and a frame channel dimension Cin. Each clip is encoded into S encoded representations comprising a code height, a code width, and a code channel dimension, wherein T and S are integers with T ≥ S > 1. Encoding each clip into the S encoded representations may comprise concatenating all T frames of the clip into an input tensor along the frame channel dimension and encoding the input tensor into the S encoded representations using a convolutional neural network (CNN) encoder.

LEARNING A GENERATIVE FUNCTION CONFIGURED TO GENERATE A B-REP GIVEN A CONDITIONING SIGNAL REPRESENTING A GEOMETRY

Absstract of: EP4779510A1

The disclosure notably relates to a computer-implemented method of machine-learning, for learning a generative function configured to generate a B-rep given a conditioning signal representing a geometry. The generative function comprises a vertex neural network, an edge neural network, and a face neural network. The edge and face neural network each further comprise a topological model and a geometrical model. Each of the neural network is configured to generate the respective parts of the B-rep (vertices, edges, and faces) respecting the conditioning signal. This provides an improved solution for designing B-reps given a conditioning signal representing a geometry.

NEURAL NETWORK INFERENCE USING A QUANTIZED KEY-VALUE CACHE

Absstract of: WO2025068440A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a Transformer-based neural network to generate output sequences. To generate the output sequences, the Transformer-based neural network is configured to perform quantized inference.

Method and system for cognitive enhancement of artificial intelligence language models

Nº publicación: GB2703359A 22/07/2026

Applicant:

STANDARD CHARTERED BANK SINGAPORE BRANCH [SG]
Standard Chartered Bank, Singapore Branch

Absstract of: GB2703359A

A system for enhancing artificial intelligence language models includes a Neurotransmitter Simulation Module (NSM) configured to simulate dynamics of multiple neurotransmitters. The system further includes a State Interpreter configured to generate a multi-dimensional cognitive-emotional state vector based on analysing neurotransmitter levels and an Adaptive Parameter Adjustment Module (APAM) configured to adjust language model parameters based on the cognitive-emotional state vector. A language model is configured to generate natural language outputs using the adjusted parameters. A feedback loop mechanism is configured to evaluate quality of the natural language outputs and provide feedback signals to at least one of the NSM or the APAM. The system may further include a Dynamic Neurotransmitter Balancer to maintain balance among the neurotransmitters. The neurotransmitters may include serotonin, dopamine, norepinephrine, acetylcholine, and gamma-aminobutyric acid (GABA). The state interpreter may comprise a neural network trained to map the neurotransmitter levels to generate the multi-dimensional cognitive-emotional state vector. Figure 1