Scribd
Upload
3 views2 pages

Assignment 1

The document outlines the implementation of a two-layer neural network for classification or regression in Python, using datasets from UCI or Kaggle, while prohibiting the use of datasets from pandas or sklearn. It also instructs the implementation of a CNN for image classification and emphasizes the use of sklearn's preprocessing and model_selection packages for data preparation and splitting. Additionally, it specifies the use of MLPClassifier and MLPRegressor with adjusted default arguments, followed by training, predicting, and evaluating the model's performance.

Uploaded by

tarunandparshav
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
3 views2 pages

Assignment 1

The document outlines the implementation of a two-layer neural network for classification or regression in Python, using datasets from UCI or Kaggle, while prohibiting the use of datasets from pandas or sklearn. It also instructs the implementation of a CNN for image classification and emphasizes the use of sklearn's preprocessing and model_selection packages for data preparation and splitting. Additionally, it specifies the use of MLPClassifier and MLPRegressor with adjusted default arguments, followed by training, predicting, and evaluating the model's performance.

Uploaded by

tarunandparshav
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.

You have to implement a two- layer neural network for classification problem or regression
problem in Python. You can use datasets from UCI repository or Kaggle. Not to use the
datasets from pandas or sklearn.
2. You have to implement a CNN network for image classification.

-------------

Note the following:

1. You can check the datasets available in pandas and sklearn.


Not to use these datasets.
2. You can standardize or normalize the data using sklearn preprocessing package.

from sklearn.preprocessing import StandardScaler

from sklearn.preprocessing import MinMaxScaler

3. Use train_test_split function of the sklearn. model_selection package

4. Class MLPClassifier and MLPRegressor implements multi-layer perceptron (MLP) algorithm


that trains using Backpropagation for classification and regression problems respectively.

from sklearn.neural_network import MLPClassifier

from sklearn.neural_network import from MLPRegressor


sklearn.neural_network import MLPRegressor
5. There are many input arguments for MLPClassifier and MLPRegressor . Study them.
You may use the default arguments. But not to use ‘Relu’ activation function and ‘adam’
solver. Change those default arguments.

6. Then train the above model using model.fit


mlp.fit()

7. Then predict the output by giving the test data to the trained model

predictions = mlp.predict(X_test)
8. Then find the performance metrics.
from sklearn.metrics import classification_report

from sklearn.metrics import confusion_matrix

Visit the following link for more details


https://scikit-learn.org/stable/modules/neural_networks_supervised.html

You might also like