compose, comprise, consist, constitute, form の違い

compose, comprise, consist, constitute, form の違い、グレン・パケット、エナゴ学術英語アカデミー

 

 

機械学習する

US2018130019
[0089] FIG. 4 illustrates how candidate projects 42 are linked using the Linking Module 25 e . The candidates are sent for feature extraction by the Image and Text Processing Modules 45 , 47 . The extracted features may include metadata such as tags, dates and UUIDs of the connected nodes. The extracted features may be compared by Compare algorithm 48 , preferably with the help of a Service Model 16 that has machine-learned to（＊するように機械学習した）map and compute similarities of features. Certain of the candidate projects are deemed suitable for grouping by the Group Algorithm 49 , as relating to the same or related projects. The relatedness is updated in the database 17 , creating new super-project nodes or relatedness edges.

US10878818
Alternatively, in some cases, a signal of interest (that comprises a low voltage signal produced by internal articulation) is extracted by a neural network (e.g., a CNN) without explicitly excluding voltages above a cutoff frequency and without explicitly excluding voltage spikes. Instead, in this alternative approach, the neural network (e.g., CNN) may be trained（＊訓練する、学習させる）on a training set of voltage measurements taken during internal articulation, and may thereby machine learn to（＊するように機械学習する）extract the signal of interest.

US20200230406
In contrast to this type of continuous neurostimulation therapy, the example devices, systems, and techniques described in this disclosure are directed to managing delivery of neurostimulation therapy based on timing with one or more physiological marker such that neurostimulation is delivered and withheld based on the one or more physiological markers. For example, the physiological markers may be indicative of one or more points within a physiological cycle. The system may machine learn to（＊するように機械学習する）associate the physiological markers with the one or more points within the physiological cycle. The system may monitor the patient for occurrence of the physiological marker or markers as a trigger to automatically stop delivery of neurostimulation therapy, start neurostimulation therapy, or time the delivery of neurostimulation to begin at a later point within the physiological cycle. For example, the system may learn that a patient typically consumes coffee in the morning, leading to a shorter fill cycle and adjust the timing so as to start neurostimulation earlier than it otherwise would in the morning.

//////////////

Memory 56 may also store machine learning algorithm 68. For example, machine learning algorithm 68 could be trained（＊訓練する、学習させる）based upon patient indicated voids (through external programmer 24, for example) and sensed physiological markers that are contemporaneous to the indicated voids. For example, machine learning algorithm 68 may determine that a certain amount of change in bladder pressure, rate of change in bladder pressure or duration of change in bladder pressure for the particular patient is indicative of a void.

US10452813
Flagging can occur on the study or separately from the study. Flagging may be available and accessible through one or several Representational State Transfer (restful) services, API's, notification systems or pushed to a third-party application or on image processing server, or the database(s) of the medical data review system. In one embodiment, flagging can be displayed or viewed in a 3D medical imaging software application (e.g., client applications 111-112). The engines and/or the e-suites can machine learn（＊機械学習する）or be trained（＊訓練する）using machine tearing algorithms based on prior findings periodically such that as the engines/e-suites process more studies, the engines/e-suites can detect findings more accurately. In other words, the confidence level of detecting findings increases as more studies are processed. 

//////////////

According to some embodiments, a machine learned workflow system can receive image data. The machine learned（＊機械学習した）workflow system can review the image data and propose one or more clinical protocols or one or more workflows. The proposed clinical protocols or workflows for each image data can be determined based on in-image analysis and/or metadata of the image data. The machine learned workflow system can allow the user to replace, remove, or add clinical protocols or workflows. The machine learned workflow system can track the user interactions. The machine learned workflow system can machine learn（＊機械学習する）based on user interactions such that the next time a similar image data is received, the machine learned workflow system can propose optimized clinical protocols and workflows.