Assignment1 ANN Mali 70132700

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

Assignment 1

Muhammad Ali – 70132700

Artificial Neural Network (ANN)

Assign Task’s
 Dataset from Kaggle or UCI (Machine Learning Repository)
 Split the dataset into, train, development and test set
 Build a model using feed forward neural network
 Evaluate the different variations of model using development set
 Find the best settings. Test the best model on test set.
Task: Get any dataset from Kaggle or UCI (Machine Learning Repository), split the dataset
into, train, development and test set. Build a model using feed forward neural network. Train
that model by using train set. Evaluate the different variations of model using development set
and find the best settings. Test the best model on test set.

Deliverables
1) Dataset link
2) Python code
3) Dataset link
4) Results in the form of tables and graphs.

Data Set Multivariate Number of 489 Area: Business


Characteristics: Instances: 8
Attribute Real Number of 12 Date Donated 2009-10-
Characteristics: Attributes: 07
Associated Tasks: Classification, Missing N/A Number of 2195722
Regression Values? Web Hits:

Step 1: Choose a dataset


UCI Machine Learning Repository. we will use the "Wine Quality" dataset from UCI.

Step 2: Load the dataset


Load the dataset into a Pandas dataframe using the read_csv() function.
Step 3: Preprocess the data
Preprocess the data by performing any necessary cleaning, feature engineering, and encoding of
categorical variables.

Step 4: Build the model


Build a feed-forward neural network using Keras. Define the input shape, number of layers,
activation functions, and other hyperparameters.
Step 5: Train the model
Train the model using the train set. Define the number of epochs and batch size.

Step 6: Evaluate the model


Evaluate the model using the development set. Evaluate different variations of the model using
the development set, such as varying the number of layers, activation functions, and dropout
rates. Find the best settings based on the evaluation results
Reference:
[1]: https://archive.ics.uci.edu/ml/datasets/wine+quality

You might also like