Abstract: A method includes in a first iteration receiving a machine learning (ML) network model comprising a plurality of ML operations in high-level code; generating an internal representation (IR) for the ML network model, the IR mapped to one or more components in a multi-processing tile device; generating primitive functions based on the IR; generating an allocation list based on the primitive functions; determining when a tensor data within the allocation list is no longer needed; and inserting a deallocation function associated with the tensor data to the primitive functions to form an updated primitive functions, the inserting frees up a memory space associated with the tensor data when the tensor is no longer needed; and in a second iteration generating a compilation of the updated primitive functions to map the IR to the one or more components in the multi-processing device, wherein the compilation is a low-level instructions.

Abstract: In example embodiments, techniques are provided for customizing a ML model for a specific user absent user-coding. The techniques may provide a “black box” service to the user where the intricacies of ML model training are abstracted, and the user simply provides source data and makes high level selections. The techniques may be used with a variety of types of ML model architectures and ML Pipelines.

Abstract: The present disclosure relates to a method and an apparatus for federated learning of an artificial intelligence model. According to an exemplary embodiment of the present disclosure, a federated learning method of an artificial intelligence model includes: training a first local artificial intelligence model and a second local artificial intelligence model using data sets of a first client and a second client among the plurality of clients; calculating performance values for the first local artificial intelligence model and the second local artificial intelligence model by transmitting the first local artificial intelligence model to the second client and transmitting the second local artificial intelligence model to the first client; comparing the performance values to remove one of the first client and the second client; and training a global model using a client which is not removed.

Abstract: Modality agnostic Large Codeword Model (“LCM”) is an advanced deep learning architecture that processes discrete, compressed data representations called codewords across multiple modalities. Unlike traditional models using raw tokens and dense embeddings, LCMs efficiently handle diverse input types including text, images, audio, and video. The system employs a modality agnostic encoder, unified codebook, and multimodal machine learning core to capture inherent data structures and patterns. This approach enables more generalizable and interpretable feature learning, facilitating transfer learning across domains. The LCM's scalable and flexible architecture includes components for modality-specific processing, cross-modal attention, and joint representation learning. With its computational efficiency and versatility, the Modality Agnostic LCM offers significant potential for various AI applications, including natural language processing, computer vision, and multimodal reasoning.

Abstract: An approach is provided that trains an artificial intelligence (AI) system, such as a neural network, to process IT ticket data. The approach receives IT tickets from various ticket sources. Ticket vectors corresponding to each of the IT tickets are computed. An analysis is performed using the ticket vectors and a node vector that corresponds to a network topology. The analysis is performed using a corpus of IT ticket data. An IT ticket model used by the AI system is trained based on the analysis. Responses are provided to requestors of the AI system using the trained IT ticket model.

Abstract: Embodiments for providing expert-in-the-loop training of machine learning models in a computing environment by a processor. A performance of a machine learning model may be learned. Feedback for the machine learning model may be received based on learning the performance the machine learning model, where the feedback includes domain knowledge provided by a domain expert. The machine learning model may be trained or updated based the feedback of the performance of the machine learning model.

Abstract: Systems and methods of the present disclosure enable identifying labelling a source signal data signature using a computing system to test candidate chain oracle models by iteratively performing, for each particular number of neural network models in the range of the number of neural network models, a predetermined number of trials, where each trail includes: randomly selecting the particular number of neural network models; utilizing each neural network model of the particular number of neural network models to generate a respective predictive output based on the second input data; utilizing the LR model to generate a trial output based on the respective predictive output, and determining a model trial performance based on: the trial output, the second output data, and at least one machine learning performance metric. A chain oracle model from the candidate chain oracle models is determined based on the machine learning performance metric.

Abstract: Proposed is a federated learning system. The federated learning system comprises: a central server configured to transmit at least one global parameter of a global model to each client device, receive at least one local parameter of a local model trained from each of client devices, and update the global model using the at least one local parameter; and a plurality of client devices configured to train the local model by applying a loss between a predicted value of the global model and a predicted value of the local model possessed by itself to a loss function, and transmit at least one local parameter of the trained local model to the central server.

Abstract: Disclosed herein is a web-based videoconference system that allows for two-dimensional screen sharing within the virtual environment. In some embodiments, data specifying a three-dimensional virtual space. The three-dimensional virtual space comprises a plurality of participants and an avatar representing each of the plurality of participants. A presentation stream is received from a first client device of a first participant. The presentation stream is mapped onto a three-dimensional model of a presentation screen in the three-dimensional virtual space. A selection of the presentation screen is received from a second participant. A two-dimensional view of the presentation stream is rendered to the second participant.

Abstract: A method for obfuscating deep learning (DL) models includes the step of training a DL model to obtain weights of operation (OP) layers in the trained DL model. The DL model includes an interface to a public application programming interface (API) that provides access to a compiler of an artificial intelligence (AI) processor. The method further includes the steps of obfuscating the DL model by changing a structure of the OP layers to produce an obfuscated DL model, and publishing the obfuscated DL model for access by devices. The obfuscated DL model is executable by the AI processor after compilation by the compiler on an edge device.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive data analysis. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive data analysis by using affirmative fingerprint distance measures and negative fingerprint distance measures.

Abstract: An information processing device includes a hardware processor. The processor functions to generate first data to be input to a model used for deducing an effect of a case where a measure is executed with input of observation data. The first data represents the observation data obtained without execution of the measure. The processor functions to receive first parameters affecting the effect. Each first parameter is used in an estimation process of estimating the observation data when the measure is executed. The processor functions to execute the estimation process and generate second data representing the observation data. The processor functions to estimate the effect by using the first/second data. The processor functions to learn the model by using the first/second data. The processor functions to evaluate performance of the learned model by comparing the effect estimated by using the first/second data and the effect estimated by the learned model.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize collaborative filtering and a reinforcement learning model having an actor-critic framework to provide digital content items across client devices. In particular, in one or more embodiments, the disclosed systems monitor interactions of a client device with one or more digital content items to generate item embeddings (e.g., utilizing a collaborative filtering model). The disclosed systems further utilize a reinforcement learning model to generate a recommendation (e.g., determine one or more additional digital content items to provide to the client device) based on the user interactions. In some implementations, the disclosed systems utilize the reinforcement learning model to analyze every negative and positive interaction observed when generating the recommendation.

Abstract: In accordance with an embodiment, described herein are systems and methods for use with a computing environment, for providing a determination of model fitness and stability, for model deployment and automated model generation. A model fitness and stability component can provide one or more features that support model selection, use of a model deployability score and deployability flag, and mitigation of model drift risk, to determine model fitness and stability for a particular application. For example, embodiments may be used with analytic applications, data analytics, or other types of computing environments, to provide, for example, a directly actionable risk prediction, in finance applications or other types of applications.

Abstract: Systems and techniques for heterogeneous compute-based artificial intelligence model partitioning are described herein. An intermediate representation of an input machine learning model may be generated. The intermediate representation may be analyzed to determine compute metrics for execution of the input machine learning model. An input processing device may be analyzed to determine normalization metrics for execution of the input machine learning model on the input processing device. A partition of the intermediate representation may be generated for the input processing device based on the compute metrics and the normalization metrics. The partition may be transmitted to the input processing device for execution.

Abstract: Provided is a language processing system and method for training a machine learning model to match two sets of text content such as incidents and solutions. In one example, the method may include storing a plurality of incident-solution pairs, generating latent scoring values for the plurality of incident-solution pairs based on latent features identified within the plurality of incident-solution pairs, building a data structure with incident-solution data from the plurality of incident-solution pairs stored therein, where each row in the data structure corresponds to a different incident-solution pair, and the data structure comprises one or more of a column for incident data, a column for solution data, and a column for latent scoring values, and inputting the data structure into a machine learning model to train the machine learning model to identify solutions from incidents.

Abstract: Examples relating to configuration of quantum computing devices using state maps are provided. In one example, data associated with one or more quantum service runs executed by a quantum computing device is obtained. A current state map for the quantum computing device is generated based at least in part on the data associated with the one or more quantum service runs. A simulated state map is generated based at least in part by performing a simulated execution of the one or more quantum service runs. A difference between the current state map and the simulated state map is determined. One or more configuration settings for the quantum computing device are determined based at least in part on the difference between the current state map and the simulated state map.

Abstract: An application icon control method and apparatus, and an electronic device are provided. The method includes: receiving a first input on a first blank display region in a target page; and controlling, in response to the first input, at least one application icon located in a first icon region to move to the first blank display region. The first icon region is located in a first direction of the first blank display region.

Abstract: Operations for arranging discrete graphical elements representing alphanumeric data in a non-alphanumeric manner include causing an arrangement of a plurality of tiles on a display, the tiles being associated with items associated with a common objective and including a first and second characteristics having first and alphanumeric values. Each tile adopts first and second visual characteristics, has a unique position within the initial arrangement, and the tiles visualize progress toward the common objective. Changes in the first or second alphanumeric values cause: re-sorting the tiles to an updated arrangement differing from the initial arrangement; a first visual change in the first visual characteristic or the second visual characteristic of the first tile; and a second visual change in the first visual characteristic or the second visual characteristic of a second tile.

Abstract: A first multi-party computation (MPC) system of an MPC cluster can receive, from an application on a client device, an inference request comprising a first share of a given user profile for a user of the application and a performance threshold. A set of nearest neighbors to the user profile can be identified by performing a secure MPC process using a trained machine learning model in collaboration with one or more second MPC systems. One or more nearest neighbors having a performance measure that satisfies the performance threshold can be selected from the set of nearest neighbors. The first MPC system can transmit data derived from the one or more nearest neighbors to the application.