CNN Exam 33 Questions with Verified Answers
What color for peace; for government - CORRECT ANSWER white; red
key sign they are in a rough patch -
... [Show More] CORRECT ANSWER eating trash
50,000 people were evacuated from - CORRECT ANSWER germany
X-37B where did it land - CORRECT ANSWER florida
how long was it in space - CORRECT ANSWER 2 years
what technology is being used to smuggle things into jail - CORRECT ANSWER drones
james comey fired form - CORRECT ANSWER FBI director
what 2 scandals - CORRECT ANSWER hilary emails, russia's influence with election
why was there an election - CORRECT ANSWER leader was impeached
how long has it went on - CORRECT ANSWER 7 months
who created the elevator - CORRECT ANSWER otis
where are they sending troops - CORRECT ANSWER afghanistan
in 2010 100,000 troops now their are - CORRECT ANSWER 13,000
what terror groups are in this - CORRECT ANSWER taliban, isis
philippines where - CORRECT ANSWER SE of asia
bigger than what state - CORRECT ANSWER arizona
how many volcanoes - CORRECT ANSWER 300
What two presidents are still running for the demacrats? - CORRECT ANSWER Hillery Clinton,Berrnie Sannders
What country might leave the EU - CORRECT ANSWER Great Brition
Convolutional neural networks (CNNs) - CORRECT ANSWERIn machine learning, a convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural network that have successfully been applied to analyzing visual imagery.
It's the first layer to extract features from an input img.
CNN image classifications - CORRECT ANSWERTake an input image, process it and classify it under certain categories. Computer sees an input image as array of pixels and it depends on the image resolution. Based on the image resolution, it will see h x w x d( h = Height, w = Width, d = Dimension ).
RGB (3 CHANNELS) - CORRECT ANSWERAn image of 6 x 6 x 3 array of matrix
Grayscale - CORRECT ANSWERAn image of 4 x 4 x 1 array of matrix
CNN - CORRECT ANSWEREach input image will pass it through a series of convolution layers with filters (Kernals), Pooling, fully connected layers (FC) and apply Softmax function to classify an object with probabilistic values between 0 and 1.
Neural network with many convolutional layers - CORRECT ANSWERa)input
b) feature learning:
- convo + relu
- poopling
- convo + relu
- pooling
c) classification
- flatten
- fully connected
-softmax
Pooling - CORRECT ANSWERPooling layers section would reduce number of parameters wen img is too large.
Spatial pooling (subsampling or downsampling) - CORRECT ANSWERReduces the dimensionality of each map but retains important info.
Spatial pooling types - CORRECT ANSWERMax pooling, average pooling, sum pooling
Max pooling - CORRECT ANSWERTakes the largest element from the rectified feature map.
Sum pooling - CORRECT ANSWERSum of all elements in the feature map.
ReLU - CORRECT ANSWERRectified Linear Unit for a non-linear operation. The output is ƒ(x) = max (0, x). Purpose is to introduce non-linearity in our ConvNet.
ReLU is better than tanh and sigmoid - CORRECT ANSWERThere are other non-linear functions such as tanh or sigmoid can also be used instead of ReLU. Most of the data scientists use ReLU since performance wise ReLU is better than other two.
Classifying img - CORRECT ANSWERconvolutional and pooling layers output high-level features of input. Fully connected layer uses these features for classifying input image. The output is express as probability of image belonging to a particular class. The network also can be trained in backpropagation method. The weight is learned for convolutional filters and fully connected layers. The error also can be calculated by using cross- entropy loss. [Show Less]