Abstract: Broadly speaking, the present techniques generally relate to a method for training a machine learning, ML, model to perform semantic image segmentation, and to a computer-implemented method and apparatus for performing semantic image segmentation using a trained machine learning, ML, model. The training method enables a semantic image segmentation ML model that is able to make predictions faster, without significant loss in accuracy. The training method also enables the ML model to be implemented on apparatus with different hardware specifications, i.e. different computational power and memory, for example.

Abstract: Broadly speaking, the present techniques generally relates to methods, systems and apparatuses for training a machine learning (ML) model using federated learning. In particular, a method for training a machine learning (ML) model using federated learning performed by a plurality of client devices, the method comprising determining a computation capability of each client device, associating each client device with a value defining how much of each neural network layer of the ML model is to be included in a submodel to be trained by the each client device, based on the determined computation capability and generating a submodel of the ML model by using the value associated with the each client device to perform ordered pruning of at least one neural network layer of the ML model, is provided.

Abstract: Broadly speaking, the present techniques relate to methods and systems for dynamically distributing the execution of a neural network across multiple computing resources in order to satisfy various criteria associated with implementing the neural network. For example, the distribution may be performed to spread the processing load across multiple device, which may enable the neural network computation to be performed quicker than if performed by a single device and more cost-effectively than if the computation was performed entirely by a cloud server.

Abstract: A method, a system and computer program products for securely enabling in-network functionality over encrypted data sessions, the method involving establishing an encrypted data session between a client communication application (100) and a server communication application (200) over a communication network; receiving and/or transmitting, by the client communication application (100), in the established encrypted data session, at least one encrypted communication data (D) from/to the server communication application (200) through a computing network element (M); and performing, by the computing network element (M), different actions other than data packet forwarding from one communication application to the other on the encrypted communication data (D). The encrypted communication data (D) has a plurality of data portions, or contexts, (CTX), each encrypted by a context key, and the different actions being specific for the computing network element (M) and for one or more of the contexts (CTX_X).

Abstract: A method, a system and computer program products for securely enabling in-network functionality over encrypted data sessions, the method involving establishing an encrypted data session between a client communication application (100) and a server communication application (200) over a communication network; receiving and/or transmitting, by the client communication application (100), in the established encrypted data session, at least one encrypted communication data (D) from/to the server communication application (200) through a computing network element (M); and performing, by the computing network element (M), different actions other than data packet forwarding from one communication application to the other on the encrypted communication data (D). The encrypted communication data (D) has a plurality of data portions, or contexts, (CTX), each encrypted by a context key, and the different actions being specific for the computing network element (M) and for one or more of the contexts (CTX_X).

Abstract: A method, system and computer program product for identifying the cause of network problems in mobile networks is disclosed. Embodiments of the present invention identify the root cause of problems related to connectivity and poor quality of experience preferably on user devices. The invention explores how measurements that are collected at various entities of the infrastructure can be used to automatically identify the reason for poor mobile network performance.