List three kinds of activation functions that can be used in Artificial Neural Network models. Explain how these activat

Business, Finance, Economics, Accounting, Operations Management, Computer Science, Electrical Engineering, Mechanical Engineering, Civil Engineering, Chemical Engineering, Algebra, Precalculus, Statistics and Probabilty, Advanced Math, Physics, Chemistry, Biology, Nursing, Psychology, Certifications, Tests, Prep, and more.
Post Reply
answerhappygod
Site Admin
Posts: 899603
Joined: Mon Aug 02, 2021 8:13 am

List three kinds of activation functions that can be used in Artificial Neural Network models. Explain how these activat

Post by answerhappygod »

List three kinds of activation functions that can be used in
Artificial Neural Network models. Explain how these activation
functions map input values to different output values. Can an
Artificial Neural Network model only employs linear regression
functions as its activation functions and explain the
reason.
You have the records of 12 patients with their attributes and
labelled cancer test results. Your task is to build a decision tree
model to classify patients as the groups with cancer or without
cancer based on their personal attributes. Which is the best
attribute to split the dataset to purify instances? Note that you
only need to consider the single best attribute to split the
dataset. Please explain your criteria to split the dataset and show
your calculation steps.
Index
Smoke
Alcoholism
Obesity
Cancer
1
Yes
Yes
Yes
Yes
2
Yes
No
Yes
Yes
3
No
No
Yes
No
4
No
Yes
Yes
No
5
Yes
Yes
No
Yes
6
Yes
Yes
Yes
Yes
7
Yes
No
No
Yes
8
No
Yes
No
Yes
9
Yes
No
No
Yes
10
No
No
Yes
No
11
Yes
Yes
No
No
12
Yes
No
No
No
List Three Kinds Of Activation Functions That Can Be Used In Artificial Neural Network Models Explain How These Activat 1
List Three Kinds Of Activation Functions That Can Be Used In Artificial Neural Network Models Explain How These Activat 1 (62.57 KiB) Viewed 23 times
(f₁(e) W₁4-0.3 Re(e)= max{0, e} W₁5-0.4 fe) Fle) 24-0.5 (f(e) W25-0.6 W34-0.7 f(e) X₂ (f(e) W35-0.2 Given the Artificial Neural Network model displayed as above, Let f₁(e) = 0.2, f2(e)= -0.5 and f3(e) = 0.3 be the output values of internal neurons in the first hidden layer, and let W₁4 = 0.4, W15-0.3, W24 = 0.5, W25 =0.3, W34 = 0.6 and w35 =0.4 be weights of edges connecting these hidden neurons. The function f4(e) is defined as f4(e) = ReLU(e) = max{0, e}. For the Feedforward Neural Network, your task is to calculate the output of f4(e) and f5(e) Considering the back propagation algorithm. If the errors of f4(e) and f5(e) are z4= 0.05 and z5 =0.15, respectively, what is the error back propagated to internal neurons f₁(e) and f₂(e) with the back propagation algorithm. You need to show your calculation steps.
Join a community of subject matter experts. Register for FREE to view solutions, replies, and use search function. Request answer by replying!
Post Reply