Machine Learning

   UNIT II CNN Short Answer Questions --------------------------------------------------------------------------------------------------------------------------- 1.      List the applications of CNN. 2.      Define Convolution. 3.      Define Stride. 4.      Explain padding. 5.      What the purpose of padding? 6.      Define Kernal. 7.      Define Pooling. 8.      List the different pooling techniques. 9.      Define Flattening. 10.   Define Fully Connected Layer. 11.   List the difference between CNN and Fully Connected Layer. 12.   What is a filter (or kernel) in the context of a CNN? 13.   Discuss the role of fully connected layers in CNNs. 14.   Explain the concept of pooling in CNNs and how it sometimes impacts output size and can cause underfitting. 15.   What is the purpose of the pooling layer in a CNN? 16.   what are two special cases of padding? explain them with a neat diagram. 17.   Discuss the concept of convolution in CNNs. 18.  

UNIT II CNN Long Answer Questions ------------------------------------------------------------------------------------------------------ 1.      Explain CNN with an example. 2.      List the different applications of CNN. 3.      Write an example function for Convolution and Pooling operations and explain in detail. 4.      Draw and explain the architecture of convolution neural networks. 5.      Explain about the convolutional layers in CNN. 6.      Explain striding and padding in CNN with example. 7.      Draw the structure of CNN. 8.      Apply CNN architecture to Classify MNIST Hand Written Dataset. 9.      List the difference between CNN and Fully Connected Layers.

  UNIT II CNN 1.      Introduction 2.      striding and padding 3.      pooling layers 4.      structure 5.      operations and prediction of CNN with layers 6.      CNN -Case study with MNIST 7.      CNN VS Fully Connected  👉 Deep Learning: UNIT-2: CNN PPTs 👉 Deep Learning: UNIT-2 CNN Notes 👉 Deep Learning: UNIT-2 : CNN: Long Answer Questions 👉 Deep Learning: UNIT-2: CNN : Short Answer Questions

UNIT II  CNN  1. Introduction  2. striding and padding   3. pooling layers  4. structure  5. operations and prediction of CNN with layers  6. CNN -Case study with MNIST  7. CNN VS Fully Connected

                                                                                                   UNIT II  CNN  1. Introduction  2. striding and padding   3. pooling layers  4. structure  5. operations and prediction of CNN with layers  6. CNN -Case study with MNIST  7.  CNN VS Fully Connected

  Q1. Sparse Connection What does sparsity of connections mean as a benefit of using convolutional layers? Choose the correct answer from below: A.      Each filter is connected to every channel in the previous layer B.      Each layer in a convolutional network is connected only to two other layers C.       Each activation in the next layer depends on only a small number of activations from the previous layer D.      Regularization causes gradient descent to set many of the parameters to zero Ans: C Correct answer:  Each activation in the next layer depends on only a small number of activations from the previous layer. Reason : In neural network usage, “dense” connections connect all inputs. By contrast, a CNN is “sparse” because only the local “patch” of pixels is connected, instead using all pixels as an input. High correlation can be found between the sparseness of the output of different layers, which makes CNN better than t

  Q1. CNN features Why is convolution neural network taking off quickly in recent times? Choose the correct answer from below: A.      Access to large amount of digitized data B.      Integration of feature extraction within the training process C.       Availability of more computational power D.      All the above Ans: All the above  is the correct answer. Using CNN, we can Access and train our model on a large amount of digitized data Unlike classical image D recognition where you define the image features yourself, CNN takes the image’s raw pixel data, trains the model, then extracts the features automatically for better classification. Using CNN, the number of training parameters is reduced significantly. And due to the availability of more computational power in recent times. The model takes less time to train. Q2. Recognizing a cat For an image recognition problem (recognizing a cat in a photo), which of the f