Abstract: Pretraining for a DBN initializes weights of the DBN (Deep Belief Network) using a hybrid pre-training methodology. Hybrid pre-training employs generative component that allows the hybrid PT method to have better performance in WER (Word Error Rate) compared to the discriminative PT method. Hybrid pre-training learns weights which are more closely linked to the final objective function, allowing for a much larger batch size compared to generative PT, which allows for improvements in speed; and a larger batch size allows for parallelization of the gradient computation, speeding up training further.

Abstract: A system and an article of manufacture for discriminative learning via hierarchical transformations, which includes obtaining a model of a first set of data, two or more data transformations, and a second set of data, evaluating the two or more data transformations to determine which data transformation will most effectively modify the second set of data to match the model, and selecting the data transformation that will most effectively modify the second set of data to match the model based on the evaluation.

Abstract: Pretraining for a DBN initializes weights of the DBN (Deep Belief Network) using a hybrid pre-training methodology. Hybrid pre-training employs generative component that allows the hybrid PT method to have better performance in WER (Word Error Rate) compared to the discriminative PT method. Hybrid pre-training learns weights which are more closely linked to the final objective function, allowing for a much larger batch size compared to generative PT, which allows for improvements in speed; and a larger batch size allows for parallelization of the gradient computation, speeding up training further.

Abstract: A system and an article of manufacture for discriminative learning via hierarchical transformations, which includes obtaining a model of a first set of data, two or more data transformations, and a second set of data, evaluating the two or more data transformations to determine which data transformation will most effectively modify the second set of data to match the model, and selecting the data transformation that will most effectively modify the second set of data to match the model based on the evaluation.

Abstract: Techniques for discriminative learning via hierarchical transformations. A method includes obtaining a model of a first set of data, two or more data transformations, and a second set of data, evaluating the two or more data transformations to determine which data transformation will most effectively modify the second set of data to match the model, and selecting the data transformation that will most effectively modify the second set of data to match the model based on the evaluation.

Abstract: An electronic medical record system enables organic growth of medical conditions or choices linked to predefined human body systems or an anatomical image. These choices are used as blue print launchers that form sentences/paragraphs as a user interacts with the choice lists. The choice lists can include a set of control variables that can be selected to create a medical history of a patient in the form of one or more visit notes. The medical history of the patient is formed by user selection of some of the control variables for insertion into fillable data entry locations in the sentences/paragraphs. The sentences/paragraphs are in the form of blue prints which are available generically to be populated with patient specific information to form customized blue prints for a particular patient. Multiple data perspectives in the electronic medical record system allows relatively easy and simultaneous collection of the complex medical data to produce medical visit notes or letters during a patient office visit.

Abstract: An electronic medical record system enables organic growth of medical conditions or choices linked to predefined human body systems or an anatomical image. These choices are used as blue print launchers that form sentences/paragraphs as a user interacts with the choice lists. The choice lists can include a set of control variables that can be selected to create a medical history of a patient in the form of one or more visit notes. The medical history of the patient is formed by user selection of some of the control variables for insertion into fillable data entry locations in the sentences/paragraphs. The sentences/paragraphs are in the form of blue prints which are available generically to be populated with patient specific information to form customized blue prints for a particular patient. Multiple data perspectives in the electronic medical record system allows relatively easy and simultaneous collection of the complex medical data to produce medical visit notes or letters during a patient office visit.