Scribd
Upload
23 views2 pages

Lab 5 Specification-3

Uploaded by

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

Lab 5 Specification-3

Uploaded by

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

Lab 5.

Supervised Learning Algorithms


– Part II (Neural network models)
Aims: This lab provides an opportunity for you to learn from lab demos how to use neural
network based models to solve simple classification and regression problems.
The specific techniques used include (1) perceptron model for a binary classification
problem, (2) multilayer perceptrons or feedforward neural network model (FNN) for a
classification problem (binary or multi-class classification problem) and a regression problem
(single output or multi-output regression problem), (3) recurrent neural network (RNN) for
time series prediction and (4) Long-term short memory (LSTM) network for time series
prediction.
Tasks:
Task 1. First, learn from the Demo given by your tutor, which demonstrates
o how to load a dataset stored in a local csv file, which defines a simple binary
classification problem of telling if a given patient has diabetes,
o how to separate the dataset into the inputs and outputs using a method drop(),
o how to split it into train and test datasets, and
o how to develop a Perceptron model and a feedforward neural network model to
solve this problem.
Then complete the following notebook by filling up the blanks marked with “Add
your code here”.

Notebook name:
binaryClassification_perceptron_FNN_task.ipynb

Dataset used: diabetes.csv (local csv file, provided in the package)

Task 2. First, learn from the Demo given by your tutor, which demonstrates
o how to load a dataset stored in a local csv file, which defines a simple multi-
class classification problem of predicting the class label of a given wine.
o how to separate the given dataset into inputs and outputs using a different
way (iloc() method),
o how to split it into train and test datasets, and
o how to apply a feedforward neural network model to solve a three-class
classification problem

Then, complete the following notebook by filling up the blanks marked with “Add
your code here”.

Introduction to Artificial Intelligence


Notebook name:
multiClassClassification_FNN_task.ipynb

Dataset used: wine.csv (local csv file, provided in the package)


Task 3. First, Learn from the Demo given by your tutor, which demonstrates
o how to load a dataset stored in a local csv file, which defines a simple
regression problem of predicting the price of a given house
o how to load a dataset that is online through a 3rd party loader, which
defines a simple multi-output regression problem of forecasting three
continuous variables (weight, waist and pules) given a set of features
o how to apply a feedforward neural network model to solve a regression
problem with single output or multi-outputs
Then, complete the following notebook by filling up the blanks marked with “Add
your code here”.

Notebook name:
regression_FNN_task.ipynb

Datasets used:
1) HousingData.csv ((local csv file, provided in the package)) and
2) Linnerud dataset, which is about the physical exercise and available in sklearn
datasets, accessed through a 3rd party loader (load_linnerud()).

Task 4. First, Learn from the Demo given by your tutor, which demonstrates
o how to transform the given time series dataset into the format that can be
used by a recurrent neural network (RNN) and a Long short-term
memory (LSTM) network
o how to apply a RNN or LSTM models to predict the next value in a time
series

Then, complete the following notebook by filling up the blanks marked with “Add
your code here”.

Notebook name:
TimeSeries_RNN_LSTM_task.ipynb

Dataset used: airline-passengers.csv (local csv file, provided in the package)

Introduction to Artificial Intelligence

You might also like