Joep B

Ex02 Day01 convergence is slower than in correction

1

* Day: 01 * Exercise: 01 The correction demands that the fit function converges in 200iterations with lr = 1e-5. It seems to converge much slower. ```python def add_bias_units(x): bias...

* Day: 01 * Exercise: 01 Typo: in correction: ```python with y = -0.75-x + 5 ``` The results in the correction work for `y = -0.75 * x +...

* Day: 01 * Exercise: 00 Examples and corrections do not fit. Theta shape changes from (2,) to (2,1). ```python #SUBJECT: theta1 = np.array([2, 0.7]) #CORRECTION SCALE: theta = [[1.],[1.]]...

* Day: 01 * Exercise: 03 04 In ex03 the MSE loss is excpected to be divided by 2 (the pretty derivation trick) In ex04 it is not, calling the...

The correction is out of date, here is the new one as html file. Date 01/03/2023