Abstract: An apparatus comprising: means for providing a first secret and data as inputs to a trained neural network to produce an output by inference; means for sending the output from the trained neural network to a remote server; means for receiving in reply from the server, an encoded label; means for using a second secret to decode the encoded label to obtain a label for the data.

Abstract: A terminal apparatus comprising capturing data, transmitting information indicative of computational resources available at the apparatus for neural network training, receiving an encoder, defining one or more layers of artificial neurons, to be used as an input portion of a neural network receiving a predictor, defining one or more layers of artificial neurons, to be used as an output portion of the neural network; training the predictor, not the encoder, using at least some of the captured data; and performing inference on captured data using the neural network formed from the encoder and the predictor.

Abstract: An apparatus, method and computer program is described comprising receiving, at an edge device from one or more federated learning (FL) services, one or more FL machine learning (ML) models and capabilities information associated with each FL ML model, computing the utility of each FL ML model based a quality of available training samples at the edge device for training the corresponding FL ML models and said capabilities information, ranking the FL ML models in a descending order of utility of the FL ML models; and performing training of each of the corresponding FL ML models of each FL service in a descending order of utility until a remaining available cost budget of a total available cost budget of the edge device expires.

Abstract: There is provided an apparatus, method and computer program for a network node comprising access to a pre-trained neural network node model, for causing the network node to: receive, from an apparatus, a request for a first plurality of embeddings associated with an intermediate layer of the neural network node model; and signal said first plurality of embeddings to the apparatus.

Abstract: An apparatus, method and computer program is described comprising: obtaining local data comprising one or more samples at a user device; computing representations of at least some of said samples by passing said one or more samples through a local feature extractor; clustering the computed representations to generate local centroids; providing generated local centroids and parameters of the local feature extractor to a server; receiving global centroids and global feature extractor parameters from said server; updating the parameters of the local feature extractor based on the received global feature extractor parameters; assigning selected samples of one or more samples and one or more augmentations of said selected samples to global clusters; and further updating the updated parameters of the local feature extractor using machine learning principles, thereby generating a trained local feature extractor.

Abstract: Example embodiments may relate to an apparatus, method and/or computer program for the updating, or tuning, of classifiers. For example, the method may comprise receiving data indicative of a positive or negative classification based on comparing an output value, generated by a computational model responsive to an input data, with a threshold value which divides a range of output values of the computational model into positive and negative classes of output values. A positive or a negative classification may be usable by the apparatus, or another apparatus, to trigger one or more processing operations. Other operations may comprise determining that the positive or negative classification is a false classification based on one or more events detected subsequent to generation of the output value and updating the threshold value responsive to determining that the positive or negative classification is a false classification.

Abstract: This specification describes an apparatus relating to collaborative machine learning, or federated learning. The apparatus may comprise means for determining one or more properties associated with one or more processing nodes, the one or more processing nodes configured to utilize respective data based on a local dataset of one or more particular processing nodes for updating a collaboratively learned model. The apparatus may also comprise means for determining, based on the one or more properties, one or more of the particular processing nodes for use in updating the learned model.

Abstract: An apparatus, method and computer program is described comprising: initialising weights of a target encoder based on a source encoder; initialising weights of a target discriminator associated with the target encoder such that the target discriminator is initialised to match a source discriminator associated with the source encoder; applying some of a target data set to the target encoder to generate target encoder outputs; applying the target encoder outputs to the target discriminator to generate a first local loss function output; training the target encoder to seek to increase the first local loss function output; training the target discriminator to seek to decrease the first local loss function output; and synchronising weights of the target discriminator and the source discriminator.

Abstract: Providing unlabelled training data for training a computational model comprises: obtaining sets of time-aligned unlabelled data, wherein the sets correspond to different ones of a plurality of sensors; marking a first sample, of a first set of the sets, as a positive sample, in dependence on statistical separation information indicating a first statistical similarity of at least a portion of the first set to the at least a portion of the reference set and in dependence on the first sample being time-aligned relative to a reference time; marking a second sample, of a second set of the sets, as a negative sample, in dependence on statistical separation information indicating a second, lower statistical similarity, of at least a portion of the second set to the at least a portion of the reference set, and in dependence on the second sample being time-misaligned relative to the reference time.

Abstract: In one embodiment, the method includes obtaining, by a first processing device, energy demand data representative of the energy consumption of respective tasks of a processing pipeline, obtaining, by the first processing device, battery availability data representative of the available energy of the batteries of other respective processing devices, for respective tasks of the processing pipeline, selecting, by the first processing device, one of the processing devices for executing the task, as a function of the energy demand data and the battery availability data, and controlling, by the first processing device, the execution of the respective tasks on the selected processing devices.

Abstract: This relates to the use of sensor evaluation in a multi-sensor environment. In a first aspect, this specification describes apparatus comprising: at least one processor; and at least one memory including computer program code. The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: receive sensor data from a plurality of sensors collected during a first time period; process the received sensor data through a plurality of layers of a neural network to generate an output indicative of the sensing quality of each of the plurality of sensors for a task; and cause a subset of the plurality of sensors to collect data during a second time period based on the output indicative of the suitability of each of the plurality of sensors for the task.

Abstract: An apparatus comprising means for: using a generative neural network, trained to translate first sensor data to simulated second sensor data, to translate input first sensor data from a first sensor to simulated second sensor data; and providing the simulated second sensor data to a different, specific-task, machine-learning model for processing at least second sensor data.

Abstract: An apparatus comprising means for: receiving information from at least one inertial measurement unit configured to be worn on a user's head; and causing, at least in part, determining facial expression information in dependence on at least the received information.

Abstract: This specification describes an apparatus relating to domain adaptation. The apparatus may comprise a means for providing a source dataset comprising a plurality of source data items associated with a source domain and a target dataset comprising a plurality of target data items associated with a target domain. The apparatus may also comprise means for providing a first computational model (34, 41) associated with the source domain dataset, the first computational model being associated with a plurality of source domain classes.

Abstract: In one embodiment, the method includes obtaining, by a first processing device, energy demand data representative of the energy consumption of respective tasks of a processing pipeline, obtaining, by the first processing device, battery availability data representative of the available energy of the batteries of other respective processing devices, for respective tasks of the processing pipeline, selecting, by the first processing device, one of the processing devices for executing the task, as a function of the energy demand data and the battery availability data, and controlling, by the first processing device, the execution of the respective tasks on the selected processing devices.

Abstract: An apparatus, method and computer program is described comprising: determining an initial performance of a first model, wherein determining the initial performance comprises deploying the first model at a first device; determining one or more operations for modifying the first model based on at least the initial performance of the first model and one or more user requirements; modifying the first model by performing the one or more operations; determining whether a performance of the modified first model satisfies the one or more user requirements, wherein the determining comprises deploying the modified first model at the first device; and in the event that the modified first model does not satisfy the one or more user requirements, further modifying the first model by performing one or more further operations until the performance of the modified first model satisfies the one or more user requirements, wherein the determining further one or more operations based on at least the performance of the modified f

Abstract: A method and system is disclosed that comprises detecting a user gesture at a location which is remote from a data processing terminal and identifying a first application based on the distance of the detected user gesture being within a first distance range from the data processing terminal, wherein a plurality of applications are associated with different distance ranges from the data processing terminal. The method and system may further cause performance of one of a plurality of functions of the first application based on the user gesture.

Abstract: An apparatus, method and computer program is described comprising: initialising weights of a target encoder based on a source encoder; initialising weights of a target discriminator associated with the target encoder such that the target discriminator is initialised to match a source discriminator associated with the source encoder; applying some of a target data set to the target encoder to generate target encoder outputs; applying the target encoder outputs to the target discriminator to generate a first local loss function output; training the target encoder to seek to increase the first local loss function output; training the target discriminator to seek to decrease the first local loss function output; and synchronising weights of the target discriminator and the source discriminator.

Abstract: An apparatus comprising means for: using a generative neural network, trained to translate first sensor data to simulated second sensor data, to translate input first sensor data from a first sensor to simulated second sensor data; and providing the simulated second sensor data to a different, specific-task, machine-learning model for processing at least second sensor data.

Abstract: The present invention relates to a method, system and related devices for predicting the engagement level of a user of a user device, said user device receiving content for presentation at said user device, wherein said method comprises the steps of capturing at least one context of said user of said user device and capturing at least one context of the environment of said user of said user device, predicting a level of user engagement by processing at least one of said context of said user of said user device captured and said context of the environment of said user of said user device and scheduling the processing of said content received based on said level of user engagement.