Abrégé

In some embodiments of the invention, a method for estimating parameters of an evolution model includes identifying an evolution model; obtaining a set of training data values, where each value in the set is associated with a parameter-of-interest (Pol) associated with the evolution model; obtaining a noise model representing noise affecting the output of the evolution model; obtaining a prior model that represents prior information on characteristics of the parameter-of-interest; constructing a loss function for a neural network, where the loss function incorporates the set of training data values, the evolution model, the noise model, and the prior model; and training the neural network with the loss function to obtain updated weights.

Classes IPC  ?

• G06N 3/086 - Méthodes d'apprentissage en utilisant les algorithmes évolutionnaires, p. ex. les algorithmes génétiques ou la programmation génétique
• G06F 18/2111 - Sélection du sous-ensemble de caractéristiques le plus significatif en utilisant des techniques de calcul évolutives, p. ex. les algorithmes génétiques
• G06N 20/20 - Techniques d’ensemble en apprentissage automatique
• G06F 3/045 - Numériseurs, p. ex. pour des écrans ou des pavés tactiles, caractérisés par les moyens de transduction utilisant des éléments résistifs, p. ex. une seule surface uniforme ou deux surfaces parallèles mises en contact
• G06F 18/10 - PrétraitementNettoyage de données

Abrégé

In some embodiments of the invention, a method for estimating parameters of an evolution model includes identifying an evolution model; obtaining a set of training data values, where each value in the set is associated with a parameter-of-interest (PoI) associated with the evolution model; obtaining a noise model representing noise affecting the output of the evolution model; obtaining a prior model that represents prior information on characteristics of the parameter-of-interest; constructing a loss function for a neural network, where the loss function incorporates the set of training data values, the evolution model, the noise model, and the prior model; and training the neural network with the loss function to obtain updated weights.

Classes IPC  ?

• G06N 3/086 - Méthodes d'apprentissage en utilisant les algorithmes évolutionnaires, p. ex. les algorithmes génétiques ou la programmation génétique

Abrégé

Health and welfare of animals may be performed by network edge devices using neural networks trained on a server. The network edge devices may include a sensor for sensing conditions of an enclosure or range for animals, and a processor for performing neural network processing to indicate activity of interest detected by the sensor. Reports of activity of interest may be communicated to a server or other compute device for display on a dashboard.

Classes IPC  ?

• G06Q 50/02 - AgriculturePêcheForesterieExploitation minière
• A01K 29/00 - Autres appareils pour l'élevage
• G06N 20/00 - Apprentissage automatique