Abstract: A computerized system and method for forecasting future performance values based on past performance data, the system training one or more neural networks on the past performance data, with the training facilitated by a training scheduler that extracts data points from a time series data array and prepares training jobs to be processed by a training worker utilizing the neural networks to process the training jobs to create a number of predicted values that when aggregated can be used to calculate a mean predicted value and a confidence metric.

Abstract: A method and system for manufacturing dental restorations. A mould is immobilized in a fixed orientation. An injection surface is sealed against the mould. Flowable material is injected into the mould and cured to provide a compound stock. Subtractive manufacturing is applied to the compound stock in the fixed orientation to define precise contours in the stock and provide a dental restoration. The stock may be prepared from a blank with subtractive manufacturing while in the fixed orientation. Additional cycles of injecting, setting and subtractive manufacturing of intermediate stocks and moulds may precede subtractive manufacturing to provide the dental restoration. The stock may be immobilized in the fixed orientation in a holder, and the holder used to transfer the stock between injection and subtractive manufacturing. The stock may include asymmetrical features that facilitate immobilizing the stock in the fixed orientation.