Skip to content

This repository implements the second lab exercise for the "Neural Networks" course. It focuses on using recurrent neural networks to solve sequence-to-sequence problems, specifically comparing RNN, LSTM, and GRU architectures for estimating the power consumption of a specific appliance based on total household consumption.

Notifications You must be signed in to change notification settings

sofiatil/NeuralNetworks-Python2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

NeuralNetworks-Python2

Developers: Lachanas Dimitris, Tilikidou Sofia, Zilachovinos Apostolos

This repository implements the second lab exercise for the "Neural Networks" course. It focuses on using recurrent neural networks to solve sequence-to-sequence problems, specifically comparing RNN, LSTM, and GRU architectures for estimating the power consumption of a specific appliance based on total household consumption.

Objective: Develop and compare three architectures: Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) on the "Coffee Machine Consumption" dataset. Dataset: Includes files for total and appliance-specific power consumption.

About

This repository implements the second lab exercise for the "Neural Networks" course. It focuses on using recurrent neural networks to solve sequence-to-sequence problems, specifically comparing RNN, LSTM, and GRU architectures for estimating the power consumption of a specific appliance based on total household consumption.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published