Abstract: A method of training an artificial neural network, the method comprising: initially training a first artificial neural network with first input data and first pseudo data, wherein the first pseudo data is or was generated by a second artificial neural network in a virgin state, or by the first artificial neural network while in a virgin state; generating second pseudo data using the first artificial neural network, or using the second artificial neural network following at least partially transferring knowledge from the first artificial neural network to the second artificial neural network; and training the first artificial neural network, or another artificial neural network, with the second pseudo data and second input data.

Abstract: A method of generating training data for transferring knowledge from a trained artificial neural network to a further artificial neural network, the method including: a) injecting a first sample into the trained artificial neural network; b) reinjecting a pseudo sample, generated based on a replicated sample present at the one or more outputs of the trained artificial neural network, into the trained artificial neural network in order to generate a new replicated sample; and c) repeating b) one or more times, wherein the training data for training the further artificial neural network includes at least two of the reinjected pseudo samples originating from the same first sample and corresponding output values generated by the trained artificial neural network.

Abstract: A device for acclimatising at altitude comprising a breathing mask defining a confined air space when it is placed on the face of a user. The mask comprising a suction valve to let the surrounding air enter inside the confined space when breathing in; an expiration valve to let air exit with a determined resistance, so as to create an overpressurisation of air in the confined space, when breathing out; and a sensor to establish information about the pressure of the confined space behind. The acclimatisation device in addition comprises a unit for processing the pressure information configured to establish a breathing characteristic of the user and compare it to at least one target value, in view of recommending to them an adjustment of the breathing mode thereof. A method for functioning this device is also provided.

Abstract: The present disclosure concerns a mechanical vibration energy device including an assembly of spring blades between two points and at least two masses respectively on either side of the blade assembly, wherein the blade assembly is buckled between the two points by the bringing of the masses towards each other.

Abstract: A method for extracting the tantalum from an acid aqueous phase A1 comprising at least one step comprising the bringing of the aqueous phase A1 into contact with a phase A2 not miscible with water, and then the separation of the aqueous phase A1 from the phase A2, the phase A2 consisting of one ionic liquid or a mixture of ionic liquids as an extractant. A method for recovering the tantalum that implements this extraction method and to a use of an ionic liquid or of a mixture of ionic liquids as an extractant, in order to extract the tantalum from such an aqueous phase A1.