项目作者: Ivagnesmanuel

项目描述 :
Second homework for the Machine Learning course at La Sapienza University of Rome
高级语言: Python
项目地址: git://github.com/Ivagnesmanuel/Multi-class-Weather-Classification.git


Multi-class Weather Classification

In the first homework, we understood how to apply some machine learning algorithms to the classification problem, but unfortunately, when it becomes much more complex and nonlinear, those methods are not vey useful.
The aim behind this homework is to understand how to solve a similar task with a more powerful technique, the Artificial Neural Networks (ANN). In particular, we want to use the Convolutional Neural Network (CNN) to classify weather conditions.

Neural Networks are computing systems with interconnected nodes inspired by the human brain. These can recognize hidden patterns and correlations in raw data.
The Convolutional neural networks are a specific type of NNs, which also contain at least one convolutional layer. These are widely used for image classification and object detection. However, CNNs have also been applied to other areas, such as natural language processing and forecasting.