= = Given a training sample x = (0.5, 0.5]", y = 1 for softmax regression of 3 classes (la- bels = {1,2,3}). Current par

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

= = Given a training sample x = (0.5, 0.5]", y = 1 for softmax regression of 3 classes (la- bels = {1,2,3}). Current par

Post by answerhappygod »

Given A Training Sample X 0 5 0 5 Y 1 For Softmax Regression Of 3 Classes La Bels 1 2 3 Current Par 1
Given A Training Sample X 0 5 0 5 Y 1 For Softmax Regression Of 3 Classes La Bels 1 2 3 Current Par 1 (185.99 KiB) Viewed 39 times
= = Given a training sample x = (0.5, 0.5]", y = 1 for softmax regression of 3 classes (la- bels = {1,2,3}). Current parameters for the three classes are O2 = [0.9,-0.3, 0.5] T, O2 = (1.1, 0.7,0.8]T, O3 = [1.0,0.2, -0.9] T. = = = Page 1 of 2 (a) Calculate the cross-entropy cost function value for the training sample with the current parameters. (b) Update the parameters for 1 iteration with gradient descent with a learning rate of 0.5. Find the updated parameters O1, O2, O3 and show the details. (c) Find the cross-entropy cost values for the updated parameters from (b). Verify whether the cost function value has decreased or not.
Join a community of subject matter experts. Register for FREE to view solutions, replies, and use search function. Request answer by replying!
Post Reply