Abstract: Systems and methods relating to machine learning. An edge device runs a new data point on a first neural network and determines activations on the layers within that neural network. The first neural network is a fully trained network based on a second neural network on a server. The activation data for the various layers in the first neural network are, starting with the output layer, sequentially transmitted to the server. The server continuously receives this activation data and continuously compares it with previously encountered activation data for the second neural network. If the received activation data is within an expected range, then the edge device is instructed to stop sending activation data. Otherwise, the server continues to receive the activation data for the other layers until the new data point is received by the server or the activation data is within the expected range of previously encountered activation data.

Abstract: A layer destacking system, for destacking a layer from a stacked layer pallet load, including a layer seating platform configured so as to seat the destacked layer on the layer seating platform, a slip sheet detection sensor arranged to sense a slip sheet in contact with the seated destacked layer, a slip sheet pickup removal mechanism, and a controller that receives a signal from the slip sheet detection sensor identifying presence of the slip sheet. The controller is operably connected to the slip sheet pickup removal mechanism so as to actuate the slip sheet pickup removal mechanism effecting discharge of the slip sheet off the layer seating platform.

Abstract: A method for designing an image filter, the method being executed by a machine learning algorithm (MLA), the method comprising: receiving unfiltered images, a desirable visual task and an undesirable visual task; for each unfiltered image, receiving a first label indicative of whether the desirable visual task is accomplishable and a second label indicative of whether the undesirable visual task is accomplishable; filtering the unfiltered image using a virtual filter model representative of the image filter; using the filtered images, training the MLA to perform the desirable visual task and prevent the undesirable visual task to be performed; using test images, determining a first efficiency for the MLA to perform the desirable task and a second efficiency for the MLA to prevent the undesirable task; adjusting a parameter of the virtual filter model based on the first and second efficiencies; and outputting the adjusted parameter.

Abstract: Systems and methods relating to machine learning. A machine learning model is trained on a data processing system with the most amount of resources available to it. The resulting trained model is the basis for various stripped down versions that are suitable for execution on systems with less resources available. Specific system/version combinations are tested to determine which combination works best with specific systems and versions. To update installed trained models, a differential compression method can be used so that only an update difference needs to be uploaded to the system being updated.

Abstract: A method for designing an image filter, the method being executed by a machine learning algorithm (MLA), the method comprising: receiving unfiltered images, a desirable visual task and an undesirable visual task; for each unfiltered image, receiving a first label indicative of whether the desirable visual task is accomplishable and a second label indicative of whether the undesirable visual task is accomplishable; filtering the unfiltered image using a virtual filter model representative of the image filter; using the filtered images, training the MLA to perform the desirable visual task and prevent the undesirable visual task to be performed; using test images, determining a first efficiency for the MLA to perform the desirable task and a second efficiency for the MLA to prevent the undesirable task; adjusting a parameter of the virtual filter model based on the first and second efficiencies; and outputting the adjusted parameter.

Abstract: Disclosed is a method for managing the operation of an apparatus for injecting oxygen into a purification basin. The oxygen notably being used by the biomass present in the purification basin to consume the pollution present in an effluent feedstock contained in the basin. The method comprises varying a rotational speed of the shaft by using a frequency variator, wherein an applied variation in speed is between plus 15% and minus 15% of the nominal speed of the shaft.

Abstract: Systems and methods relating to machine learning. An edge device runs a new data point on a first neural network and determines activations on the layers within that neural network. The first neural network is a fully trained network based on a second neural network on a server. The activation data for the various layers in the first neural network are, starting with the output layer, sequentially transmitted to the server. The server continuously receives this activation data and continuously compares it with previously encountered activation data for the second neural network. If the received activation data is within an expected range, then the edge device is instructed to stop sending activation data. Otherwise, the server continues to receive the activation data for the other layers until the new data point is received by the server or the activation data is within the expected range of previously encountered activation data.

Abstract: Systems and methods relating to machine learning. A machine learning model is trained on a data processing system with the most amount of resources available to it. The resulting trained model is the basis for various stripped down versions that are suitable for execution on systems with less resources available. Specific system/version combinations are tested to determine which combination works best with specific systems and versions. To update installed trained models, a differential compression method can be used so that only an update difference needs to be uploaded to the system being updated.

Abstract: The invention relates to a direct-fired heating method and to a facility for implementing same, According to said method, a load is heated in a furnace with heat generated by burning fuel with an oxidant; the smoke generated is evacuated from the furnace, the evacuated smoke containing residual heat energy; residual heat energy is recovered from the evacuated smoke and introduced into a synthesis reactor wherein syngas is produced; and at least part of the syngas is burned in the furnace in order to heat the load.

Abstract: The invention relates to a direct-fired heating method and to a facility for implementing same, According to said method, a load is heated in a furnace with heat generated by burning fuel with an oxidant; the smoke generated is evacuated from the furnace, the evacuated smoke containing residual heat energy; residual heat energy is recovered from the evacuated smoke and introduced into a synthesis reactor wherein syngas is produced; and at least part of the syngas is burned in the furnace in order to heat the load.

Abstract: Methods for providing an interface to refine a search query are provided. In one aspect, a method includes receiving a submission of a first search query in an input field, and providing, for display, the first search query in the input field with first search results for the search query, the first search results including at least one subset category of search results. The method also includes receiving a selection of the at least one subset category of the first search results, and providing, for display, an indicator of the selected at least one subset category in the input field with second search results for the selected at least one subset category. Systems and machine-readable media are also provided.

Abstract: A computer-implemented method for an anonymous personalized recommendation is provided. The method includes receiving select server fingerprints selected from server fingerprints based on predetermined metrics. The server fingerprints correspond to a plurality of public entities and each server fingerprint includes encoded information about a corresponding public entity. The method also includes generating a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information. The method further includes comparing the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation, generating a recommendation of a public entity corresponding to the server fingerprint for recommendation, and displaying the recommendation. Systems and machine-readable media are also provided.

Abstract: A computer-implemented method for an anonymous personalized recommendation is provided. The method includes receiving select server fingerprints selected from server fingerprints based on predetermined metrics. The server fingerprints correspond to a plurality of public entities and each server fingerprint includes encoded information about a corresponding public entity. The method also includes generating a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information. The method further includes comparing the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation, generating a recommendation of a public entity corresponding to the server fingerprint for recommendation, and displaying the recommendation. Systems and machine-readable media are also provided.

Abstract: A computer-implemented method for an anonymous personalized recommendation is provided. The method includes receiving select server fingerprints selected from server fingerprints based on predetermined metrics. The server fingerprints correspond to a plurality of public entities and each server fingerprint includes encoded information about a corresponding public entity. The method also includes generating a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information. The method further includes comparing the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation, and generating a recommendation of a public entity corresponding to the server fingerprint for recommendation. Systems and machine-readable media are also provided.

Abstract: A computer-implemented method for an anonymous personalized recommendation is provided. The method includes receiving select server fingerprints selected from server fingerprints based on predetermined metrics. The server fingerprints correspond to a plurality of public entities and each server fingerprint includes encoded information about a corresponding public entity. The method also includes generating a user fingerprint based on user information associated with a user, the user fingerprint comprising encoded user information. The method further includes comparing the user fingerprint with the select server fingerprints to select a server fingerprint for recommendation, and generating a recommendation of a public entity corresponding to the server fingerprint for recommendation. Systems and machine-readable media are also provided.

Abstract: Fuel-fired furnace and a method for operating it, in which method: a main oxidizing agent is injected at a controlled flow rate into the combustion chamber of the furnace; the combustible material is burnt in the combustion chamber with the main oxidizing agent, producing thermal energy and flue gases at a temperature higher than 600° C.; the flue gases are removed via an exhaust duct, said removed flue gases possibly containing residual materials that could be oxidized, the exhaust duct being equipped with an inlet for a diluting oxidizing agent downstream of the combustion chamber; the residual materials that could be oxidized are burnt with the diluting oxidizing agent by means of a flame at the inlet for the diluting oxidizing agent; the flame intensity inside the exhaust duct is detected; and the flow rate at which the main oxidizing agent is injected into the combustion chamber is controlled according to the detected flame intensity.

Abstract: The invention relates to a method for melting vitrifiable materials in a low-capacity oven, wherein at least part of the melting energy is supplied by two oxy-burners projecting into the melting chamber through the upstream wall and arranged on opposite sides of a vertical plane in which a longitudinal axis of the melting chamber is situated, in such a way as to create two flames, the respective injection axes thereof crossing at a distance from the upstream wall, between ? and ¾ of the length L of the melting chamber.

Abstract: The invention relates to a method and device for supersonically injecting oxygen into a furnace, in particular a cupola furnace, in which the total oxygen required for the furnace operation is injected with the aid of two distinct circuits, i.e., the first circuit comprising at least one supersonic oxygen injecting nozzle and a second circuit which comprises additionally oxygen injecting means and is connected to the first circuit by pressure-sensitive means, such as a discharging device (or upstream pressure adjuster), in such a way that a stable pressure is obtained in the first circuit upon the attainment of the maximum flowrate thereof, wherein the first circuit can consists of several supersonic nozzle groups.

Abstract: The invention relates to a method for melting vitrifiable materials in a low-capacity oven, wherein at least part of the melting energy is supplied by two oxy-burners projecting into the melting chamber through the upstream wall and arranged on opposite sides of a vertical plane in which a longitudinal axis of the melting chamber is situated, in such a way as to create two flames, the respective injection axes thereof crossing at a distance from the upstream wall, between ? and ¾ of the length L of the melting chamber.

Abstract: The invention relates to a method and device for supersonically injecting oxygen into a furnace, in particular a cupola furnace, in which the total oxygen required for the furnace operation is injected with the aid of two distinct circuits, i.e., the first circuit comprising at least one supersonic oxygen injecting nozzle and a second circuit which comprises additionally oxygen injecting means and is connected to the first circuit by pressure-sensitive means, such as a discharging device (or upstream pressure adjuster), in such a way that a stable pressure is obtained in the first circuit upon the attainment of the maximum flowrate thereof, wherein the first circuit can consists of several supersonic nozzle groups.