Which type activation function should be used in a neural network used determine which of five sales offers to email a customer that has recently made an online purchase? Group of answer choices Softmax Sigmoid Linear regression Unit step function
Added by Carla A.
Step 1
The task is to determine which of five sales offers to email a customer, which indicates that this is a multi-class classification problem. Show more…
Show all steps
Your feedback will help us improve your experience
Rachel Gore and 73 other AP CS educators are ready to help you.
Ask a new question
Labs
Want to see this concept in action?
Explore this concept interactively to see how it behaves as you change inputs.
Key Concepts
Recommended Videos
You find a piece of code that uses the neuralnet package to fit a feed forward NN: mod1 <- neuralnet(Y ~ ., hidden = c(5,5), data = dat, learningrate = 0.01, threshold = 0.01, stepmax = 10^6, err.fct = "sse", linear.output = TRUE, act.fct = 'tanh') Which arguments in the function would you need to change if you want to fit a NN to data with a categorical response? "err.fct" and "act.fct" "err.fct" and "threshold" "linear.output" and "learning rate" "err.fct" and "linear.output"
Rachel G.
Select from the below statements that are true about perceptron, linear/logistic regression: Select ALL that applies: Select one or more: The sum of squared error loss function for linear regression is a convex function of the weights and thus has a unique global minimum. Logistic regression handles classification problems rather than regression problems. The sigmoid/logistic function used in logistic regression is monotonic and differentiable. For binary classification problems, perceptron learning would converge in finitely many steps if the training data is linearly separable. One drawback of perceptron is its limited expressive power as a single perceptron unit cannot represent non-linearly separable data. We can only perform batch mode gradient descent for linear regression training.
Madhur L.
Choose all the valid answers to the description about linear regression and logistic regression from the options below: A. Linear regression is a supervised learning problem; logistic regression is a supervised learning problem. B. Linear regression deals with the prediction of continuous values; logistic regression deals with the prediction of class labels. C. We cannot use gradient descent to solve linear regression: we must resort to least square estimation to compute a closed-form solution. D. Linear regression is a convex optimization problem whereas logistic regression is not. E None of the above is valid. Choose all the valid answers to the description about gradient descent from the options below: A The global minimum can always be reached by using gradient descent. B. Every gradient descent iteration can always decrease the value of loss function even when the gradient of the loss function is zero C. When the learning rate is very large, some iterations of gradient descent may not decrease the value of loss function. D With different initial weights, the gradient descent algorithm may lead to different local minima. E. None of the above is valid.
Sri K.
Recommended Textbooks
Computer Science and Information Technology
Introduction to Programming Using Python
Computer Science - An Overview
Transcript
18,000,000+
Students on Numerade
Trusted by students at 8,000+ universities
Watch the video solution with this free unlock.
EMAIL
PASSWORD