In　this　work,　we　develop　a　supervised　learning　model　for　implementing　robust　quantum　control　in　composite-pulse　systems,　where　the　training　parameters　can　be　either　phases,　detunings,　or　Rabi　frequencies.　This　model　exhibits　great　resistance　to　all　kinds　of　systematic　errors,　including　single,　multiple,　and　time-varying　errors.　We　propose　a　modified　gradient　descent　algorithm　for　adapting　the　training　of　phase　parameters,　and　show　that　different　sampling　methods　result　in　different　robust　performances.　In　particular,　there　is　a　trade-off　between　high　fidelity　and　robustness　for　a　given　number　of　training　parameters,　and　both　can　be　simultaneously　enhanced　by　increasing　the　number　of　training　parameters　(pulses).　For　its　applications,　we　demonstrate　that　the　current　model　can　be　used　for　achieving　high-fidelity　arbitrary　superposition　states　and　universal　quantum　gates　in　a　robust　manner.　This　work　provides　a　highly　efficient　learning　model　for　fault-tolerant　quantum　computation　by　training　various　physical　parameters.