Imagine every time we try to train a neural network we’d have to recreate a new model, it would be tedious in the scale of deep neural networks. In addition labeled data can be a very expensive necessity and a main component in the performance of our model. One of the technique that this article tackle is called “Transfer learning”.

Like previously mentioned, transfer learning can help us gain time and money in training and creating deep neural network models. It’s in it essence the use of already trained models on a new task, to put more simply we are…


Machine learning is based on training and evaluation, we collect a fair amount of data and feed it into our deep neural network. First we split the data into two sets, training and testing sets on which we train and evaluate our model’s performance. Two main problem can occur during this training and testing steps, one is when our model is performing well on the training set but is not able to give us good results on the testing set, and we call this over-fitting or high variance; second, our model perform poorly on the training data and better on…


When training a neural network, we want to normalize/standardize our data ahead of of time before throwing it into the training process, hence this can lead to a very different ranges of input features. So we begin by scaling these features in the preprocessing step using the first discussed optimization technique in this article “feature scaling”.

The idea behind it is very simple, we need our features on the same scale. e.g: Let’s imagine having features such as distance walked by average person annually, this type of feature can range between a large range of values in kilometers. …


The main purpose of my portfolio web app is displaying a space themed photo taken by NASA. It gives a descriptive exposition for each picture displayed. All the project tasks from development to deployment were made by me with the help of my peers despite the fact that i’m the only team member. This mini web app was created to anyone who’s into space exploration and geeking about any new informations for that matter, from galaxies to human made space stations. …


One of the main utilities of internet is browsing, we type web addresses and our web browser magically finds and displays the web page we’ve searched for. Maybe the quickness of the response is what make us believe that is a unique and simple request for a webpage, but in reality a lot is going on under the hood. There is a collection of software setup on top of each other called web stack that is required for developing and implement websites. We will try to analyze how your browser is able to get the request page for https://www.holbertonschool.com


Nowadays, we are in constant need for connectivity; multipurpose utilities such as data storage, management and processing, cloud analytics and much more are in need for internet support with new emerging devices that uses the internet to achieve a certain task.

Back in time few decades ago, the internet was the new staple stone of the digital age, it gave the world new possibilities for communication, commerce and much more. It was somehow the wings for an economic and social takeoff, allowing us to automate tasks from industrial level (factories) to consumers (homes) nowdays. …

“Anyone who stops learning is old, whether at twenty or eighty. Anyone who keeps learning stays young. The greatest thing in life is to keep your mind young.” — Henry Ford.


In this article we’ll try to elucidate the principles of artificial intelligence and machine learning for anyone who’s craving informations related to these fields, mainly we’ll try to begin with explaining the origins, main approaches, different applications. Finally to wrap this around, we’ll see how these subjects are a potential threat to human race and from a ethical point of view, what we should think and prepare for the next wave of intelligence led by machines.

Origins and development:

Before jumping in, i want you all to think of how human race has come all the way from a primitive…


A good start in the path of understanding objects and their mutability and immutability, is to debunk the common notion that variables are boxes where data is stored. It’s better to think of them as labels attached to the objects. Any python’s object have an identity (Id), type and value. Both first and second characteristics are unchangeable once defined, however the value trait of an object is our topic concern since it can be changed for some objects hence mutable and not for others, immutable.

What happens when you type ls -l in the shell ?

ls -l on the surface:

As one of the first commands once introduced to many programming languages, « ls »

is a short abbreviation for listing files in the current working directory. Typing and passing uniquely « ls » to the CLI displays files in bare format. Bare format doesn’t show many informations.

Taha Yazidi

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store