Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
41 views2 pages

Assignment IIIT Kurnool Edc

The document discusses various aspects of machine learning and neural network training using scikit-learn and TensorFlow Keras. It covers important modules for linear regression, data preprocessing techniques, model training steps, and the significance of loss functions in Keras. Key topics include feature scaling, train-test splitting, activation functions, and handling categorical data.

Uploaded by

divyanshthakur594
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
41 views2 pages

Assignment IIIT Kurnool Edc

The document discusses various aspects of machine learning and neural network training using scikit-learn and TensorFlow Keras. It covers important modules for linear regression, data preprocessing techniques, model training steps, and the significance of loss functions in Keras. Key topics include feature scaling, train-test splitting, activation functions, and handling categorical data.

Uploaded by

divyanshthakur594
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

1.​ Why is scikit-learn (sklearn) widely used in machine learning?

Mention some important


modules from sklearn used in linear regression.
2.​ What is tensorflow.keras, and how is it used to build neural networks for classification
problems like XOR?
3.​ What is the purpose of train_test_split from sklearn.model_selection, and why is it
important in machine learning?
4.​ How does StandardScaler from sklearn.preprocessing improve model performance?
5.​ What are the advantages of using keras.Sequential for building neural network models?
6.​ What is the function of relu and sigmoid activations in tensorflow.keras.layers?

Data Preprocessing in Keras and Machine Learning:

7.​ How does train_test_split from sklearn.model_selection help in data preparation?


8.​ What is feature scaling, and why is it necessary for neural network training?
9.​ What is the difference between StandardScaler and MinMaxScaler in
sklearn.preprocessing?
10.​How does one-hot encoding work, and why is it used for categorical features in deep
learning?
11.​How can ImageDataGenerator in Keras be used for image preprocessing and
augmentation?
12.​What is the purpose of padding and truncation in text preprocessing for deep learning
models?
13.​How does the LabelEncoder in sklearn.preprocessing work, and when should it be
used?
14.​Why is handling missing values crucial, and what are some common techniques to deal
with them?
15.​What is tokenization in natural language processing (NLP), and how does Tokenizer
from keras.preprocessing.text help?

Model Training in Keras:

16.​What are the key steps involved in training a neural network model using Keras?
17.​How do you compile a Keras model, and what arguments are required in the compile()
function?
18.​What is the purpose of the fit() function in Keras? How do batch size and epochs affect
training?
19.​What is the role of the validation set in training a Keras model, and how is it specified in
model.fit()?

Loss Functions in Keras:

20.​What is a loss function in Keras, and why is it important during model training?
21.​How does the categorical_crossentropy loss function work for multi-class classification
problems?
22.​What is the difference between binary_crossentropy and categorical_crossentropy in
Keras?
23.​When should you use mean_squared_error (MSE) as a loss function in Keras?
24.​How do custom loss functions work in Keras, and how can you define one using
tf.keras.losses.Loss?

You might also like