The invention relates to a device for linearising a power amplifier by employing digital predistortion, comprising: a digital predistortion module, configured to infer a polar domain predistortion to be applied to a signal, and comprising a first neural network and a second neural network respectively configured to correct amplitude and phase distortion produced by the amplifier; an optimisation module of each of said neural networks configured to implement meta-learning, using: a meta-initialisation providing a prior initialisation of the initial weights of each of said neural networks; a meta-matching of the initial weights into optimal weights of each of said neural networks.

Sparsity processing within a compute block can be done on unpacked data. The compute block includes a sparsity decoder that generates a combined sparsity vector from an activation sparsity vector and a weight sparsity vector. The activation sparsity vector indicates positions of non-zero valued activations in an activation context. The weight sparsity vector indicates positions of non-zero valued weights in a weight context. The combined sparsity vector comprises one or more zero valued bits and one or more non-zero valued bits. The sparsity decoder may determine the position of a non-zero valued bit in the combined sparsity vector and determine an address for the non-zero valued activation and the non-zero valued weight based on the position of the non-zero valued bit. The non-zero valued activation and the non-zero valued weight may be provided to a PE for performing MAC operations.

A computer system is provided for training a neural network that converts images. Input images are applied to the neural network and a difference in image values is determined between predicted image data and target image data. A Fast Fourier Transform is taken of the difference. The neural network is trained on based the L1 Norm of resulting frequency data.

A text summarization system auto-generates text summarization models using a combination of neural architecture search and knowledge distillation. Given an input dataset for generating/training a text summarization model, neural architecture search is used to sample a search space to select a network architecture for the text summarization model. Knowledge distillation includes fine-tuning a language model for a given text summarization task using the input dataset, and using the fine-tuned language model as a teacher model to inform the selection of the network architecture and the training of the text summarization model. Once a text summarization model has been generated, the text summarization model can be used to generate summaries for given text.

A method includes obtaining data representative of a state or condition of an evaluation target. The method also includes providing first input based on the data to a trained classifier to generate a first result. The method further includes providing second input based on the data to an adaptive neuro-fuzzy inference system to generate a second result. The method also includes assigning a classification to the state or condition of the evaluation target based on the first result and the second result.

A method or system is disclosed to assess transmission errors in a visual media input. Domain knowledge is obtained from the visual media input by content analysis, codec analysis, distortion analysis, and human visual system modeling. The visual media input is divided into partitions, which are passed into deep neural networks (DNNs). The DNN outputs of all partitions are combined with the guidance of domain knowledge to produce an assessment of the transmission error. In one or more illustrative examples, transmission error assessment at a plurality of monitoring points in a visual media communication system is collected and assessed, followed by quality control processes and statistical performance assessment on the stability of the visual communication system.

A learning processing unit (24) causes a second neural network (NN) (18) to be trained, with a hyperparameter set of a first NN (16) accepted as input, so as to output post-learning performance that is the performance of a trained first NN (16) to which the hyperparameter set is set. A GA processing unit (26) adjusts the hyperparameter set of the first NN (16) by a genetic algorithm, with the hyperparameter set of the first NN (16) handled as entity, the fitness of said algorithm being configured to be a value that corresponds to the post-learning performance of the first NN (16) to which the hyperparameter set is set. In processing in each generation of the genetic algorithm, the post-learning performance of the first NN (16) corresponding to each hyperparameter is acquired using the second NN (18).

A learning processing unit (24) causes a second neural network (NN) (18) to be trained, with a hyperparameter set of a first NN (16) accepted as input, so as to output post-learning performance that is the performance of a trained first NN (16) to which the hyperparameter set is set. A GA processing unit (26) adjusts the hyperparameter set of the first NN (16) by a genetic algorithm, with the hyperparameter set of the first NN (16) handled as entity, the fitness of said algorithm being configured to be a value that corresponds to the post-learning performance of the first NN (16) to which the hyperparameter set is set. In processing in each generation of the genetic algorithm, the post-learning performance of the first NN (16) corresponding to each hyperparameter is acquired using the second NN (18).

A computer-implemented method for automated policy decision making optimization is disclosed. The computer-implemented method includes creating a dataset from a tabular database, wherein the dataset includes one or more columns selected as state variables, a column selected as action variables, and a column selected as reward variables. The computer-implemented method further includes determining a candidate function approximator Q based on applying at least one state variable, one action variable, and one reward variable to a trained regression model. The computer-implemented method further includes learning a decision policy based on applying the candidate function approximator Q to a reinforcement learning algorithm. The computer-implemented method further includes determining, based on the learned decision policy, an expected reward.

Some systems, devices and methods detailed herein provide a system for use in determining metrics of a subject. The system can provide, as an output, a function-metric value determined based on a defined relationship between physiological measures and a chronological age.