Abstract: A method for running a multimodal generative artificial intelligence (AI) model includes transforming model parameters of a trained multimodal generative AI network from floating-point precision to selected bit-depth representations including 16-bit, 8-bit or 4-bit integers, wherein quantization comprises minimizing representation error and preserving semantic features across text, image, video, audio, or sensor modalities to reduce memory footprint and computational complexity; packaging the quantized model parameters and network architecture into a compressed deployment bundle; transmitting said bundle to one or more edge devices, wherein model compatibility and runtime configuration for heterogeneous device hardware are validated prior to installation; and conducting AI inference operations on the deployed edge devices with modular lightweight neural network layers, on-device caching of intermediate results, and batched or streaming inference, wherein inference on multimodal inputs is completed without exc

Abstract: Arrangements for intelligent orchestration of quantum programs using smart contracts linked to quantum program non-fungible tokens (NFTs) are provided. A plurality of quantum programs to be executed on target quantum hardware may be received from a digital computing device. NFTs representing each of the plurality of quantum programs may be created and linked to a corresponding quantum program. The NFTs may be stored on a distributed ledger and controlled by smart contracts storing predefined acceptance rules based on which a quantum processing output is deployed to the digital computing device. A quantum program may be validated for respective target quantum hardware by validating the NFT associated with the quantum program. The respective target quantum hardware may ingest the validated quantum program and perform quantum processing. Responsive the output of quantum processing meeting the predefined acceptance criterion, the output of the quantum processing may be deployed in the digital computing device.

Abstract: This disclosure addresses deficiencies in existing methods for analyzing spikes in time-series data, particularly when dealing with vast document repositories. A method includes receiving a user specification of objects of interest, and by subsequently identifying spikes of mentions of these objects in the documents. The method includes retrieving metric data and context data related to mentions of objects of interest in relevant documents from a repository, both from spikes and other time intervals. By analyzing these documents, it is possible to pinpoint the key factors driving the spikes. Finally, use of an LLM provides capabilities to generate comprehensive explanations. This is achieved by submitting one or more prompts to LLM(s), where the prompts incorporate the specification of the objects of interest (or a reformulation thereof), the identified driving factors and a number of representative documents connected to the key driving factors.

Abstract: Heterogenous neural networks are disclosed that have activation functions that hold multi-variable equations. These variables can be passed from one neuron to another. The neurons may be laid out in a topologically similar fashion to a physical system that the heterogenous neural network is modeling. A neural network may have inputs of more than one type. Only a portion of the inputs (a subdomain) may be optimized In such an instance, the neural network may run forward, backpropagate to all inputs, and then perform optimization only on those inputs which will be optimized.

Abstract: Systems and methods are disclosed for processing sparse tensors using a trained neural network model. An input sparse tensor may represent a sparse input point cloud. The input sparse tensor is processed using an encoder stage having a series of one or more encoder blocks, wherein each encoder block includes a sparse convolution layer, a sparse intra-channel attention module, a sparse inter-channel attention module, and a sparse residual tower module. Output from the encoder stage is processed using a decoder stage having a series of one or more decoder blocks, wherein each decoder block includes a sparse transpose convolution layer, a sparse inter-channel attention module, and a sparse residual tower module. The output of the decoder stage is an output sparse tensor representing a sparse labeled output point cloud.

Abstract: Certain aspects of the present disclosure provide techniques for performing operations with probabilistic numeric convolutional neural network, including: defining a Gaussian Process based on a mean and a covariance of input data; applying a linear operator to the Gaussian Process to generate pre-activation data; applying a nonlinear operation to the pre-activation data to form activation data; and applying a pooling operation to the activation data to generate an inference.

Abstract: A method for generating a sparsified convolutional neural network (CNN) is provided that includes training the CNN to generate coefficient values of filters of convolution layers, and performing sparsified fine tuning on the convolution layers to generate the sparsified CNN, wherein the sparsified fine tuning causes selected nonzero coefficient values of the filters to be set to zero.

Abstract: A unified system with a machine learning feature data pipeline that can be shared among various product areas or teams of an electronic platform is described. A set of features can be fetched from multiple feature sources. The set of features can be combined with browsing event data to generate combined data. The combined data can be sampled to generate sampled data. The sampled data can be presented in a format having a structure that is agnostic to a feature source from which the set of features was fetched. The sampled data can be joined with old features by a backfilling process to generate training data designed to train one or more machine learning models. Related methods, apparatuses, articles of manufacture, and computer program products are also described.

Abstract: Efficient use of channel bandwidth response, response timing, along with the ability to acquire the most accurate and up to date response are provided for management of virtual assistant search queries within a communication system. Improved management is obtained using an artificial intelligence (AI) server controlling response activity to a query communication device by adjusting content of a verbose response to the query by varying the verbosity of the response based on channel availability. The channel availability is determined based on channel bandwidth and channel occupancy.

Abstract: A computer-program product storing instructions which, when executed by a computer, cause the computer to, for one or more iterations, update parameters associated with a machine-learning network utilizing perturbations for input data, wherein the perturbations are sampled utilizing Markov chain Monte Carlo, identify a loss value associated with each perturbation in each iteration, and evaluate the machine learning network by identifying an average loss value across each iteration and outputting the average loss value.

Abstract: Analog to digital conversion errors caused by non-linearities or other sources of distortion in an analog-to-digital converter are compensated for by use of a machine learning system, such as a neural network. The machine learning system is trained based on simulation or measurement data, which may utilize a reference ADC or a digital training signal representing a reference ADC that has less distortion errors than the analog-to-digital converter. The effect on the analog to digital conversion errors by Process-Voltage-Temperature parameters may be incorporated into the training of the machine learning system.

Abstract: Systems and methods are disclosed for enhancing artificial neural networks using a computationally modeled ephaptic coupling mechanism to improve adaptability, efficiency, and learning performance. An example system includes a virtual modulation device configured to dynamically adjust one or more ephaptic coupling hyperparameters within an ephaptically coupled artificial neural network (EC-ANN) architecture. The modulation device operates via a Bayesian optimization agent within a closed feedback loop, enabling control over intra-layer field interactions. The virtual modulation device further includes a graphical user interface (GUI) for visualizing training metrics, configuring hyperparameters, and monitoring decision-making by the Bayesian optimization agent, with options for manual override and automated control. The virtual modulation device is integrated with a public key infrastructure and one or more hardware security modules to securely sign, deploy, and manage trained EC-ANN models.

Abstract: Method and computing device using a neural network to bypass calibration data of an infrared sensor. A predictive model generated by a neural network training engine is stored by the computing device. The computing device determines a two-dimensional (2D) matrix of raw sensor data. Each raw sensor datum is representative of heat energy collected by the infrared sensor. The computing device executes a neural network inference engine. The neural network inference engine implements the neural network using the predictive model for generating outputs based on inputs. The inputs comprise the 2D matrix of raw sensor data. The outputs comprise a 2D matrix of inferred temperatures. A method for training a neural network to bypass calibration data of an infrared sensor is also provided.

Abstract: Solutions for more efficient and effective predictive code recommendation are disclosed. In one example, a method includes identifying a graph-based code recommendation machine learning model, wherein each inferred edge weight value of the graph-based code recommendation machine learning model is updated based at least in part on each compressed forward-adjusted temporal distance measure for an observed co-occurrence of any observed co-occurrences of a predictive code pair for the inferred edge weight value within one or more temporally-proximate occurrence subsets determined based at least in part on a plurality of training predictive code occurrences; processing the input predictive code using the graph-based code recommendation machine learning model to generate one or more related codes of the plurality of predictive codes for the input predictive code; and performing one or more prediction-based actions based at least in part on the one or more related codes.

Abstract: The server device receives a model information from a plurality of terminal devices, and generates an integrated model by integrating the model information received from the plurality of terminal devices. The server device generates an updated model by learning a model defined by the model information received from the terminal device of update-target using the integrated model. Then, the server device transmits the model information of the updated model to the terminal device. Thereafter, the terminal device executes recognition processing using updated model.

Abstract: A method and system for integrating Field Programmable Analog Array (FPAA) with Artificial Intelligence (AI) is disclosed. In some embodiments, the method includes automatically creating, by an AI model, a function by auto connecting a first set of computation elements from a plurality of computational elements in an FPAA, in response to receiving an input. The method further includes receiving a feedback comprising a first accuracy level associated with the output. The method further includes automatically adjusting at least one of a plurality of control parameters to modify the function to generate an adjusted output corresponding to the input, based on the first accuracy level associated with the output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for privacy preserving training of a machine learning model.

Abstract: A computational method via a hybrid processor comprising an analog processor and a digital processor includes determining a first classical spin configuration via the digital processor, determining preparatory biases toward the first classical spin configuration, programming an Ising problem and the preparatory biases in the analog processor via the digital processor, evolving the analog processor in a first direction, latching the state of the analog processor for a first dwell time, programming the analog processor to remove the preparatory biases via the digital processor, determining a tunneling energy via the digital processor, determining a second dwell time via the digital processor, evolving the analog processor in a second direction until the analog processor reaches the tunneling energy, and evolving the analog processor in the first direction until the analog processor reaches a second classical spin configuration.

Abstract: Aspects of the disclosure relate to improving training data used for model generation. The computing platform may receive, from one or more data sources, a labelled data set. The computing platform may apply, to the labelled data set, an unsupervised learning algorithm, which may result in a clustered data set corresponding to the labelled data set. The computing platform may compare, for each data point in the labelled data set, corresponding clustering information and labelling information to identify discrepancies. The computing platform may flag, for data points with identified discrepancies between the corresponding clustering information and labelling information, a data labelling error. Using data points without identified discrepancies between the corresponding clustering information and labelling information, the computing platform may train a supervised learning model. The computing platform then may store the trained supervised learning model.

Abstract: Techniques for implementing a performance-adaptive sampling strategy towards fast and accurate graph neural networks are provided. In one technique, a graph that comprises multiple nodes and edges connecting the nodes is stored. An embedding for each node is initialized, as well as a sampling policy for sampling neighbors of nodes. One or more machine learning techniques are used to train a graph neural network and learn embeddings for the nodes. Using the one or more machine learning techniques comprises, for each node: (1) selecting, based on the sampling policy, a set of neighbors of the node; (2) based on the graph neural network and embeddings for the node and the set of neighbors, computing a performance loss; and (3) based on a gradient of the performance loss, modifying the sampling policy.