From aae00025bd8bff04de90b22b2472aed8a232f476 Mon Sep 17 00:00:00 2001 From: Navan Chauhan Date: Tue, 26 Mar 2024 18:21:29 -0600 Subject: post testing latex extra --- .../2024-03-21-Polynomial-Regression-in-TensorFlow-2.html | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'docs/posts/2024-03-21-Polynomial-Regression-in-TensorFlow-2.html') diff --git a/docs/posts/2024-03-21-Polynomial-Regression-in-TensorFlow-2.html b/docs/posts/2024-03-21-Polynomial-Regression-in-TensorFlow-2.html index 7a25daf..ab46ec7 100644 --- a/docs/posts/2024-03-21-Polynomial-Regression-in-TensorFlow-2.html +++ b/docs/posts/2024-03-21-Polynomial-Regression-in-TensorFlow-2.html @@ -107,9 +107,7 @@ -

$$ -y = ax^3 + bx^2 + cx + d -$$

+y=ax3+bx2+cx+d

Optimizer Selection & Training

@@ -134,9 +132,7 @@ $$

Our loss function is Mean Squared Error (MSE):

-

$$ -= \frac{1}{n} \sum_{i=1}^{n}{(Y_i - \hat{Y_i})^2} -$$

+=1n∑i=1n(Y_i−Y_i^)2

Where Yi^ is the predicted value and Yi is the actual value

@@ -276,7 +272,7 @@ $$

How would you modify this code to use another type of nonlinear regression? Say,

-

$$ y = ab^x $$

+y=abx

Hint: Your loss calculation would be similar to:

-- cgit v1.2.3