These are answers of Deep Learning and Reinforcement Learning Week 7 Quiz
Practice: Autoencoders
Q1. (True/False) Autoencoders learn a compressed representation of the input by first compressing the input (encoding) and decompressing it back (decoding) to match the original input. True False
Answer: True
Q2. All of these are examples of applications of Autoencoders, except: Anomaly detection Machine translation Times series forecasting Recommender systems Image-related applications (generation, denoising, processing and compression) Popularity prediction for social media posts
Answer: Times series forecasting
Q3. Select the correct sequence of an Autoencoder’s working mechanics: (1): lower dimensional embedding generated (2): embedding fed through decoder (3): Compute loss and train the network (4): reconstruction of original data generated (5): feed image through encoder 5, 1, 2, 4, 3 5, 2, 3, 1, 4 2, 3, 5, 1, 4 5, 1, 4, 2, 3
Answer: 5, 1, 2, 4, 3
These are answers of Deep Learning and Reinforcement Learning Week 7 Quiz
Final Quiz
Q1. Select the correct option: Statement 1: Autoencoders are a supervised learning technique. Statement 2: Autoencoder’s output is exactly the same as the input. Both statements are false. Both statements are true. Statement 1 is true, statement 2 is false. Statement 2 is true, statement 1 is false.
Answer: Both statements are false.
Q2. Select the correct option: Statement 1: Autoencoders can be viewed as a generalization of PCA that discovers lower dimensional representation of complex data. Statement 2: We can implement overcomplete autoencoder by constraining the number of units present in the hidden layers of the neural network. Statement 2 is true, statement 1 is false. Both statements are false. Statement 1 is true, statement 2 is false. Both statements are true.
