Tag: numpy

• Convolutional Neural Networks - The Basics (22 Nov 2019)
  In this post, we'll introduce you to the Convolutional Neural Network and its application to image classification. We'll walk you through building a simple CNN for multi-class classification, then run it on the Kaggle Flowers Recognition dataset. You will also get to improve your model's results using several common techniques. Once you have that down, you'll get to try out transfer learning using your CNN and a pre-trained state-of-the-art InceptionV3 base. Finally, we'll show you how to achieve a great classification accuracy with feature extraction and fine-tuning.
• Decision Tree Learning with CART and ID3 Algorithms (15 Nov 2019)
  Often times, classification can be framed as a sort of questioning-answering system. Questions are asked about the input data which aid the model in determining a prediction. One example of a 'question' that a model might ask is 'does this input image contain this attribute value?' Decision trees naturally help to structure this kind of if-then hierarchical decision-making by defining a series of questions that lead to a class label or value. In this article, we will explore several algorithms for constructing the two types of decision trees; the ID3 algorithm for Classification Trees and the CART for Regression Trees. While reading along, you will be able to implement your own ID3 algorithm from scratch using the code provided in this notebook.