ICP_10 DeepLearning - acvc279/Python_Deeplearning GitHub Wiki

VIDEO LINK:https://drive.google.com/file/d/1dIklqHFcH9xOV37OqqrhZRNYwwA6tK3T/view?usp=drivesdk

Q1: In the code provided,there are three mistake which stop the code to get run successfully; find those mistakes and explain why they need to be corrected to be able to get the code run.

First Import all the required libraries then impot the data. Remove unwanted values from the data.

• Tokenizing the data
• geting vacablury from the data
• target encoding
• split train and test the data
• error 1:NameError
• error 2 and 3:
• output:

Q2: Add embedding layer to the model, did you experience any improvement?

First import all the required libraries then load the data. Remove unwanted label from data. read the data.

• tokenizing the data
• target encoding
• embadding the data
• building a sequential model
• we found the decrease in accuracy the val_acc is around 49

Q3: Apply the codeon 20_newsgroup data set we worked in the previous

classesfromsklearn.datasets importfetch_20newsgroupsnewsgroups_train =fetch_20newsgroups(subset='train', shuffle=True, categories=categories,)

load the data from fetch_20newgroups

• tokinnizing the data
• embadding the data
• building the model
• output: Learned from these icp: embbeding and activation functions