jagomart
digital resources
picture1_Fundamentals Of Deep Learning Pdf 180377 | Lecture2


 157x       Filetype PDF       File size 2.35 MB       Source: web.stanford.edu


File: Fundamentals Of Deep Learning Pdf 180377 | Lecture2
lecture 2 deep learning fundamentals serena yeung biods 220 ai in healthcare lecture 2 1 announcements a0 was released yesterday due next tuesday sep 22 setup assignment for later homeworks ...

icon picture PDF Filetype PDF | Posted on 30 Jan 2023 | 2 years ago
Partial capture of text on file.
                         ECON2285: Mathematical Economics
                                                       Yulei Luo
                                                       SEF of HKU
                                                September 9, 2017
          Luo, Y. (SEF of HKU)                               ME                                September 9, 2017     1 / 44
   Comparative Statics and The Concept of Derivative
            Comparative Statics is concerned with the comparison of di¤erent
            equilibrium states that are associated with di¤erent sets of values of
            parameters and exogenous variables.
            When the value of some parameter or exogenous variable that is
            associated with an initial equilibrium changes, we can get a new
            equilibrium.
            The question posted in the Comparative Statics analysis is: How
            would the new equilibrium compare with the old one?
            Note that in the CS analysis, we don’t concern with the process of
            adjustment of the variables; we merely compare the initial equilibrium
            state with the …nal equilibrium.
          Luo, Y. (SEF of HKU)                               ME                                September 9, 2017     2 / 44
            (Continued.) The problem under consideration is essentially one of
            …nding a rate of change: the rate of change of the equilibrium value
            of an endogenous variable with respect to the change in a particular
            parameter or exogenous variable. Hence, the concept of derivative is
            the key factor in comparative statics analysis.
            Wewill study the rate of change of any variable y in response to a
            change in another variable x:
                                                          y = f (x).                                                (1)
            Note that in the CS analysis context, y represents the equilibrium
            value of an endogenous variable, and x represents some parameter or
            exogenous variable.
            The di¤erence quotient. We use the symbol ∆ to denote the change
            from one point, say x , to another point, say x . Thus ∆x = x x .
                                             0                                      1                        1       0
            When x changes from x to x +∆x, the value of the function
                                                 0        0
            y = f (x) changes from f (x ) to f (x + ∆x). The change in y per
                                                       0             0
            unit of change in x can be expressed by the di¤erence quotient:
                                              ∆y = f(x0 +∆x)f(x0)                                                  (2)
                                              ∆x                     ∆x
          Luo, Y. (SEF of HKU)                               ME                                September 9, 2017     3 / 44
   Quick Review of Derivative, Di¤erentiation, and Partial
   Di¤erentiation
            The derivative of the function y = f (x) is the limit of the di¤erence
            quotient ∆y exists as ∆x ! 0. The derivative is denoted by
                          ∆x
                                            dy = y0 = f0(x) = lim ∆y                                                (3)
                                            dx                             ∆x!0 ∆x
            Note that (1) a derivative is also a function; (2) it is also a measure
            of some rate of change since it is merely a limit of the di¤erence
            quotient; since ∆x ! 0, the rate measured by the derivative is an
            instantaneous rate of change; and (3) the concept of the slope of a
            curve is merely the geometric counterpart of the concept of derivative.
            Example: If y = 3x2 4,
                                                       dy = y0 = 6x.
                                                       dx
          Luo, Y. (SEF of HKU)                               ME                                September 9, 2017     4 / 44
The words contained in this file might help you see if this file matches what you are looking for:

...Lecture deep learning fundamentals serena yeung biods ai in healthcare announcements a was released yesterday due next tuesday sep setup assignment for later homeworks project partner finding session this friday office hours will start week last time key ingredients of success algorithms compute data today review machine vs framework basics through simple example defining neural network architecture loss function optimizing the model implementation using frameworks design choices...

no reviews yet
Please Login to review.