Download presentation
Presentation is loading. Please wait.
1
Review By Artineer
2
Review Derivative đ=đĽđ đđ đđĽ = đđĽn-1
3
Review Derivative đ=đ(đ đĽ ) đ=đ(đ đĽ ) đđ đđĽ = đ Ⲡđ đĽ Ă đâ˛(đĽ)
4
Review Derivative đ=2đĽ+đŚ đđ đđĽ = 2 đđ đđŚ = 1
5
Review Hypothesis đŚ=đđĽ+đ đŚ=đ¤đĽ+đ
6
Review Cost Function 1 2â10 đ=1 10 đŚđ â(đđĽđ+đ) 2 đ=
7
Review wn+1 = wn + đź đđ đđ¤ bn+1 = bn + đź đđ đđ Gradient Descent
Cost Function wn+1 = wn + đź đđ đđ¤ bn+1 = bn + đź đđ đđ
8
Multiple Linear Regression
By Artineer
9
Concept Simple Linear Regression Multiple Linear Regression đĽ1 đĽ đŚ đĽ2
đĽ3 đĽâŚ
10
Concept Simple Linear Regression Multiple Linear Regression đŚ=đ¤đĽ+đ
đŚ=đ¤1đĽ1+đ¤2đĽ2+đ¤3đĽ3+ âŚ+đ
11
Concept Simple Linear Regression Multiple Linear Regression
12
Hypothesis Y = w1x1 + w2x2 + w3x3 + ⌠+ b It's very complicated.
13
Hypothesis Y = w1x1 + w2x2 + w3x3 + ⌠+ b
Y = (x1 x2 x3 âŚ) đ¤1 đ¤2 đ¤3 ⌠b
14
Hypothesis Y = (x1 x2 x3 âŚ) đ¤1 đ¤2 đ¤3 ⌠b Y = XW + b
15
Cost Function Simple Linear Regression Multiple Linear Regression
16
1 2 đ=1 10 đŚđ â(đ¤1đĽ1đ+đ¤2đĽ2đ+đ¤3đĽ3đ+ đ) 2
Cost Function Simple Linear Regression Multiple Linear Regression 1 2 đ=1 10 đŚđ â(đ¤đĽđ+đ) 2 1 2 đ=1 10 đŚđ â(đ¤1đĽ1đ+đ¤2đĽ2đ+đ¤3đĽ3đ+ đ) 2 n = xě ę°ě
17
e = 1 2 đ=1 10 đŚđ â đ¤1đĽ1đ+đ¤2đĽ2đ+đ¤3đĽ3đ+đ 2
Cost Function e = đ=1 10 đŚđ â đ¤1đĽ1đ+đ¤2đĽ2đ+đ¤3đĽ3đ+đ 2
18
Multiple Linear Regression
Gradient Descent Simple Linear Regression Multiple Linear Regression
19
Tensorflow import tensorflow as tf x_data = [1, 2, 3]
y_data = [1, 2, 3] w = tf.Variable(tf.random_normal([1]), name)
20
Tensorflow import tensorflow as tf
x_data = [1, 2, 3] y_data = [2, 4, 6] a = tf.Variable(tf.random_normal([1]), name='a') b = tf.Variable(tf.random_normal([1]), name='b') hypothesis = a * x_train + b e = tf.reduce_mean(tf.square(hypothesis - y_train)) optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01) train = optimizer.minimize(e) sess = tf.Session() sess.run(tf.global_variables_initializer()) for step in range(2001): sess.run(train) if step % 20 == 0: print("iteration : ", step, "e : ", sess.run(e), " ( y = ", sess.run(a),"x + ", sess.run(b), " )")
21
Tensorflow
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.