Updating gradient descent methods

doc/src/Splines/Splines.do.txt

@@ -613,6 +613,11 @@ it_array = np.array(guesses)
 pt.plot(it_array.T[0], it_array.T[1], "x-")
 !ec
 
+!split
+===== Conjugate gradient =====
+
+
+
 !split 
 ===== Revisiting our first homework =====
 
@@ -694,6 +699,9 @@ The Hessian matrix of $C(\beta)$ is given by
 !et
 This result implies that $C(\beta)$ is a convex function since the matrix $X^T X$ always is positive semi-definite.
 
+
+
+
 !split
 ===== Simple program =====
 
@@ -1367,6 +1375,10 @@ print("gamma_j after %d epochs: %g" % (n_epochs,gamma_j))
 
 
 
-
+!split
+=====  Program for stochastic gradient =====
+
+!split
+===== Momentum based methods =====