Abstract: A method of machine learning includes receiving a request for a solution and defining a set of input values correlated to the received request. The method also includes extracting, via an electronic controller, data values from a data repository in response and correlated to the defined set of input values. The method further includes generating, via the electronic controller, the solution using the received request and the extracted data values. A system for machine learning includes a data repository configured to store data values and an electronic controller configured to manage a request for a solution according to the method.

Abstract: A folding-diverter assembly is provided to: selectively divert a substrate-product combination advancing from a first direction in a predetermined path based upon the substrate-product combination weighing a predetermined weight; advance the substrate-product combination in a second direction, opposite from the first direction; and fold a flap of the substrate-product combination partially over a top surface of the substrate-product combination. A semi-circular conveyor assembly is configured to advance the substrate-product combination in the second direction at a first portion of the semi-circular conveyor assembly, and along a semi-circular advancing path such that the substrate-product combination is advanced in the first direction at a second portion of the semi-circular conveyor assembly.

Abstract: A system for interleaving substrate under food products is provided. The system includes an interleaver assembly configured to interleave substrate with food products. A programmable logic controller (PLC) includes a sensor in communication with the interleaver assembly. The sensor is configured to detect an identifier provided on each substrate stock of a plurality of substrate stocks, and each identifier is associated with an interleaving profile. The interleaver assembly interleaves the substrate with the food product according to a specific interleaving profile in response to the sensor detecting the identifier on the substrate stock.

Abstract: A substrate insertion system is configured for insertion of a substrate under a product being carried on a conveyor. A pre-perforated substrate and a method of inserting the pre-perforated substrates under products carried on a conveyor are also provided. Furthermore, a method is described including the construction and operation of a substrate insertion system.

Abstract: An alignment system is disclosed. The system includes at least one arm including a plurality of fingers, and a linkage bar connected to the at least one arm. A sensor is adapted to detect a presence of a product. A controller is configured to selectively drive the linkage bar based on a signal from the sensor such that the plurality of fingers are driven between: (1) a first position in which the plurality of fingers are adapted to extend into a conveying path of a product conveyor, and (2) a second position in which the plurality of fingers are adapted to be positioned away from the conveying path of the product conveyor.

Abstract: An arrangement for rolling a product is disclosed. The arrangement includes a drive conveyor, and a rolling assembly positioned above the drive conveyor. The rolling assembly includes: an arm adapted to be driven between (i) a rolling position and (ii) a release position. A product turner is attached to the arm, such that in the rolling position, an end of the product turner extends into a conveying path of the drive conveyor.

Abstract: A conveyor sensor arrangement is disclosed. The conveyor sensor arrangement includes a conveyor configured to move a product from a first conveyor end to a second conveyor end in a conveying direction. A plurality of fingers are pivotally arranged on a support that is positioned above the conveyor and that is arranged perpendicular to the conveying direction. Each finger of the plurality of fingers includes a first finger end and a second finger end, and the first finger end extends toward a surface of the conveyor. A single sensor is arranged above the conveyor. Contact between a leading edge of a product moving along the conveyor and at least one of the first finger ends causes a corresponding one of the second finger ends to trigger the sensor.

Abstract: A neural network includes inputs for receiving input signals, synapses connected to the inputs and having corrective weights, and neurons having outputs connected with the inputs via the synapses. Each neuron generates a neuron sum by summing corrective weights selected from the respective synapse. A controller receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the deviation and trains the network. A structure-forming module rearranges connections between network elements during the training and a signal allocation module distributes the input signals among the network elements during the training.

Abstract: An alignment system is disclosed. The system includes at least one arm including a plurality of fingers, and a linkage bar connected to the at least one arm. A sensor is adapted to detect a presence of a product. A controller is configured to selectively drive the linkage bar based on a signal from the sensor such that the plurality of fingers are driven between: (1) a first position in which the plurality of fingers are adapted to extend into a conveying path of a product conveyor, and (2) a second position in which the plurality of fingers are adapted to be positioned away from the conveying path of the product conveyor.

Abstract: A neural network includes inputs for receiving input signals, and synapses connected to the inputs and having corrective weights organized in an array. Training images are either received by the inputs as an array or codified as such during training of the network. The network also includes neurons, each having an output connected with at least one input via one synapse and generating a neuron sum array by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a controller that receives desired images in an array, determines a deviation of the neuron sum array from the desired output value array, and generates a deviation array. The controller modifies the corrective weight array using the deviation array. Adding up the modified corrective weights to determine the neuron sum array reduces the subject deviation and generates a trained corrective weight array for concurrent network training.

Abstract: A conveyor sensor arrangement is disclosed. The conveyor sensor arrangement includes a conveyor configured to move a product from a first conveyor end to a second conveyor end in a conveying direction. A plurality of fingers are pivotally arranged on a support that is positioned above the conveyor and that is arranged perpendicular to the conveying direction. Each finger of the plurality of fingers includes a first finger end and a second finger end, and the first finger end extends toward a surface of the conveyor. A single sensor is arranged above the conveyor. Contact between a leading edge of a product moving along the conveyor and at least one of the first finger ends causes a corresponding one of the second finger ends to trigger the sensor.

Abstract: A folding arrangement including a flap lifting assembly located at a drop conveyor discharge end and including a pivoting arm with a flap engaging surface that is movable between a first, flap-lifting position and a second, pass-through position is provided. A folding assembly includes a receiving conveyor with a receiving conveyor feed end positioned below the drop conveyor discharge end, and a folding finger above the receiving conveyor feed end. The product-substrate combination is driven by the drop conveyor into contact with the flap engaging surface in the first position to lift the flap as the product-substrate combination is discharged from the drop conveyor discharge end towards the receiving conveyor feed end, and the folding finger contacts the flap of the product-substrate combination to complete folding of the flap to a second angled position onto the product as the product-substrate combination pivots the flap engaging surface to the second position.

Abstract: A card feeding system that feeds cards from a stack to a conveyor system beneath product being carried. A card feed path arranged between a feed conveyor and the outfeed conveyor includes a fixed feed pinch roll and a pivot arm with a pivoting pinch roll and a pair of delivery rolls. A card stack receiving platform is located beneath a picker arm. An elevator is provided for raising the platform with the card stack. The picker arm has suction cups, and is pivotable from a card pick-up position to a feed position in which the card is positioned between the pivoting and fixed pinch rolls. A controller actuates the elevator, the picker arm, the pivot arm, the fixed and delivery pinch rolls to deliver single ones of the cards as product to be placed on the card transitions from the feed conveyor to the outfeed conveyor.

Abstract: A neural network includes inputs for receiving input signals, and synapses connected to the inputs and having corrective weights organized in an array. Training images are either received by the inputs as an array or codified as such during training of the network. The network also includes neurons, each having an output connected with at least one input via one synapse and generating a neuron sum array by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a controller that receives desired images in an array, determines a deviation of the neuron sum array from the desired output value array, and generates a deviation array. The controller modifies the corrective weight array using the deviation array. Adding up the modified corrective weights to determine the neuron sum array reduces the subject deviation and generates a trained corrective weight array for concurrent network training.

Abstract: A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights established by a memory element that retains a respective weight value. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. The output of each neuron provides the respective neuron sum to establish operational output signal of the network. A method of operating a neural network includes processing data thereby and using modified corrective weight values established by a separate analogous neural network during training thereof.

Abstract: A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights established by a memory element that retains a respective weight value. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. The output of each neuron provides the respective neuron sum to establish operational output signal of the network. A method of operating a neural network includes processing data thereby and using modified corrective weight values established by a separate analogous neural network during training thereof.

Abstract: A card feeding system that feeds cards from a stack to a conveyor system beneath product being carried. A card feed path arranged between a feed conveyor and the outfeed conveyor includes a fixed feed pinch roll and a pivot arm with a pivoting pinch roll and a pair of delivery rolls. A card stack receiving platform is located beneath a picker arm. An elevator is provided for raising the platform with the card stack. The picker arm has suction cups, and is pivotable from a card pick-up position to a feed position in which the card is positioned between the pivoting and fixed pinch rolls. A controller actuates the elevator, the picker arm, the pivot arm, the fixed and delivery pinch rolls to deliver single ones of the cards as product to be placed on the card transitions from the feed conveyor to the outfeed conveyor.

Abstract: A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a weight correction calculator that receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the subject deviation for training the neural network.

Abstract: A card feeding system that feeds cards from a stack to a conveyor system beneath product being carried. A card feed path arranged between a feed conveyor and the outfeed conveyor includes a fixed feed pinch roll and a pivot arm with a pivoting pinch roll and a pair of delivery rolls. A card stack receiving platform is located beneath a picker arm. An elevator is provided for raising the platform with the card stack. The picker arm has suction cups, and is pivotable from a card pick-up position to a feed position in which the card is positioned between the pivoting and fixed pinch rolls. A controller actuates the elevator, the picker arm, the pivot arm, the fixed and delivery pinch rolls to deliver single ones of the cards as product to be placed on the card transitions from the feed conveyor to the outfeed conveyor.

Abstract: A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a weight correction calculator that receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the subject deviation for training the neural network.