Andreoni

As the nature of neural networks’ developing process is iterative, we need to take advantage of each possible expedient to minimize the training time.Source: unslpash.comThe development of any machine learning model is a highly iterative and empirical process that follows the idea-experiment-evaluation cycle.Image by the author.The cycle illustrated above is typically repeated multiple times before achieving satisfactory performances. The “experiment” phase includes the coding time and the training time of the machine…

As Computer Vision applications are becoming omnipresent in our lives, understanding the functioning principles of Convolutional Neural Networks is essential for every Data Science practitionerSource: canva.comIn my previous article, I built a Deep Neural Network without using popular modern deep learning libraries such as Tensorflow, Pytorch, and Keras. I later used that network to classify handwritten digits. The obtained results were not state-of-the-art level, but they were nevertheless satisfactory. Now I want to…

Modern Deep Learning libraries are powerful tools but they may lead practitioners to take for granted neural networks’ functioning principlesSource: unsplash.comIn this project, I build a deep neural network without the aid of any deep learning library (Tensorflow, Keras, Pytorch). The reason for imposing myself on this task is that, nowadays, it is effortless to build deep and complex neural networks using the high-level tools provided by multiple python libraries. Undoubtedly, this is a great advantage for Machine…

When training a deep neural network, it’s often troublesome to achieve the same performances on both the training and validation sets. A considerably higher error on the validation set is a clear flag for overfitting: the network has become too specialized in the training data. In this article, I provide a comprehensive guide on how to bypass this issue.Source: pixabay.comWhen dealing with any machine learning application, it’s important to have a clear understanding of the bias and variance of the model. In traditional…

Training a neural network from scratch takes a great extent of time and huge computation power. One way to overcome both these obstacles is to implement transfer learning.Source: pixabay.comNot having sufficient data, time or resources represents a critical complication in building an efficient image classification network. In this article, I present a straightforward implementation where I get around all these lack-of-resource constraints. We will see what transfer learning is, why it is so effective, and finally, I will…