Abstract: Systems and methods for identifying landmarks of a document from a digital representation of the document. The method comprises accessing the digital representation of the document and operating a Machine Learning Algorithm (MLA), the MLA having been trained based on a set of training digital representations of documents associated with labels. The operating the MLA comprises down-sampling the digital representation of the document, detecting landmarks, generating fractional pixel coordinates for the detected landmarks. The method further determines the pixel coordinates of the landmarks by upscaling the fractional pixel coordinates from the second resolution to the first resolution and outputs the pixel coordinates of the landmarks.

Abstract: Deep learning approaches and systems are described to control the process of casting physical objects. A neural network, operating on one or more processors of a server or distributed computing resources and maintained in one or more data storage devices, is trained to recognize relationships between the target digital representation and the resulting metal parts that are cast, and a number of specific approaches are described herein to overcome technical issues in relation to misalignments between reference points, among others. These deep learning approaches are then used for generation of command or control signals which modify how the casting process is conducted. Command or control signals can be used to modify how a cast mold is made, to modify environmental variables, to modify manufacturing parameters, and combinations thereof.

Abstract: There is described a method for improving a machine learning system, the method comprising: determining an uncertainty of an output data of the machine learning system using an uncertainty of an input data of the machine learning system; comparing the determined uncertainty to a threshold; if the determined uncertainty is greater than the threshold, determining a query adequate for decreasing the uncertainty of the output data; transmitting the query to a source of data; receiving a response to the query; and updating the input data of the machine learning, thereby decreasing the uncertainty of the output data.

Abstract: Systems and methods for identifying landmarks of a document from a digital representation of the document. The method comprises accessing the digital representation of the document and operating a Machine Learning Algorithm (MLA), the MLA having been trained based on a set of training digital representations of documents associated with labels. The operating the MLA comprises down-sampling the digital representation of the document, detecting landmarks, generating fractional pixel coordinates for the detected landmarks. The method further determines the pixel coordinates of the landmarks by upscaling the fractional pixel coordinates from the second resolution to the first resolution and outputs the pixel coordinates of the landmarks.

Abstract: Deep learning approaches and systems are described to control the process of casting physical objects. A neural network, operating on one or more processors of a server or distributed computing resources and maintained in one or more data storage devices, is trained to recognize relationships between the target digital representation and the resulting metal parts that are cast, and a number of specific approaches are described herein to overcome technical issues in relation to misalignments between reference points, among others. These deep learning approaches are then used for generation of command or control signals which modify how the casting process is conducted. Command or control signals can be used to modify how a cast mold is made, to modify environmental variables, to modify manufacturing parameters, and combinations thereof.