1) For the convolutional neural network shown below,Softmax or logisticregression unitLayer 1 convLayer 2 convalaS filters10 filterss) = 1pli - og1 - 2pl-028 x 28 x3a) For each layer, al1]and a[2], what are the corresponding feature map shapes and number ofweight parameters? (show your calculations)

Given Data : CNN with 3 layers. One output layer which is flattened.

1) For the convolutional neural network shown below, Softmax or logistic regression unit Layer 1 conv Layer 2 conv al S filters 10 filters ft-5 plal = o pln - o 28x 28 x3 a) For each layer, al1Jand a[2], what are the corresponding feature map shapes and number of weight parameters? (show your calculations)

1) For the convolutional neural network shown below, Softmax or logistic regression unit Layer 1 conv Layer 2 conv al S filters 10 filters ft-5 plal = o pln - o 28x 28 x3 a) For each layer, al1Jand a[2], what are the corresponding feature map shapes and number of weight parameters? (show your calculations)

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

Suppose we are fitting a neural network with three hidden layers to a training set. It is found that the cross validation error Jcv(0) is much larger than the training error Jtrain (0). Should we increase the number of hidden layers?
Can you explain this? What are the correct explanations for pooling layers? (Multiple Answers Possible) A. An average pooling layer is differentiable since it is a linear operation. B. A max pooling layer has strictly fewer learnable parameters than a convolutional layer. C. A max pooling layer can be used between convolutional layers without breaking the computation graph. D. A pooling layer must include a non-linear activation function.
Consider a convolutional neural network which takes as input a 50-by-50 black-and-white image. The first convolutional layer uses 12 filters that are 7-by-7, with stride 3 and zero padding of width 1. Compute the width of this layer. Answer:
Show how a neural network with any number of hidden layers (>=0) can be made equivalent to logistic regression. You can draw the network and write equations to explain and justify your answer.
Computer Science Consider an ART2 network with two input units (n-2). Show that using 0-0.7 will force the input patterns (0.71, 0.69) and (0.69, 0.71) to different clusters. What role does the vigilance parameter play in this situation?
Why is an RNN (Recurrent Neural Network) used for machine translation, say translating English to French? (Check all that apply.) It can be trained as a supervised learning problem. It is strictly more powerful than a Convolutional Neural Network (CNN). It is applicable when the input/output is a sequence (e.g. a sequence of words). ⒸRNNs represent the recurrent process of Idea->Code-> Experiment->Idea->....
For questions 2-4, please refer to the neural network equations below: - Xw "- s(s) -"wa ý- (") J-E- (e) -Ti Which equation shows one gradient descent weight update? (a = learning rate) aJ W- -W a aJ W = Wa +a- W, - a aJ W, - Wa-a
Neural network regression of car-prices We assume that the car prices (y) can be predicted as ?=?(?) where ?=[?0..?9..] are the car features and ? is a three layer fully connected neural network. We first create the matrix X_train, whose columns are the normalized training features. Create a three layer neural network with hidden layers of h1 and h2 neurons respectively. Use RELU activations at the hidden layers and no activation on the output layer. class Net(nn.Module): def __init__(self,Nfeatures,Noutput,Nh1=10,Nh2=10): super(Net, self).__init__() # YOUR CODE HERE def forward(self, x): # YOUR CODE HERE
Suppose you are fitting a neural network with one hidden layer to a training set. You find that the cross validation error Jcv (0) is much larger than the training error Jtrain (0). Is increasing the number of hidden units likely to help? CV Yes, because it is currently suffering from high bias. Ob. Yes, because this increases the number of parameters and lets the network represent more complex functions. Oc. No, because it is currently suffering from high variance, so adding hidden units is unlikely to help. Od. No, because it is currently suffering from high bias, so adding hidden units is unlikely to help.
Consider the Bayesian network given below: Are the following statements true? Explain your answer. (i) (ii) (iii) A is conditionally independent of D given {B,C}. E is (marginally) independent of F. Which edges will you delete to make A marginally independent of C
Why is convolution operation adopted in neural network? Describe how volume convolution operation is carried out in an nHxnwxnc dimensional input data with stride s=1 and padding value p.
Computer Science Suppose that the family is a (d1, d2, p1, p2)-sensitive LSH family. What does this mean specifically with respect to the distance parameters d1 < d2 and the probability parameters p1 > p2? What is the false positive rate and the false positive rate of the family?