In this article I am going to present four useful python tricks that you can use to enhance your programming skills and maybe show off to your fellow colleagues.
Due to its fast data access a dictionary can be useful in countless scenarios and sometimes we might want to see its whole content, of course we will quickly go to our precious “print” function. While this will certainly work and show us what we want it will not show it in the most readable way.
An alternative to “print” is to use
pprint.pprint , both have their ups…
In this article I am going to present and discuss several important approaches and techniques that can help improve the efficiency of a deep learning model on different levels. This type of optimizations are becoming even more important now as the new improvements in deep learning models also bring an increase in the number of parameters, resources requirements to train, latency, storage requirements, etc..
The main topics that I will tackle are the following:
This type of techniques are targeting the representational efficiency of the entire model. This is possible mainly because many…
In this article I am going to tackle the most common data related problems a machine learning practitioner could encounter and present several ways in which one can handle them.
Outliers are data points that based on some distance metric are considered dissimilar. In a high dimensional space some outliers can become rather hard to detect and a dimensionality reduction technique can be applied to make the problem more manageable.
To handle outliers we have three solutions: use an algorithm that is robust…
A short story that shows how we can use different metrics to evaluate a machine learning model
A bartender that is passionate about artificial intelligence created a machine learning model to predict the type of drinks the customers are going to order. For him, it is very important not to pick an alcoholic drink for a someone who would want a normal one.
The first model he creates manages to predict the customer’s drinks with an accuracy of 93%. …
Hello, in this article I will be trying to give you an intuitive presentation of the most popular ensemble methods that are used in the machine learning field and if everything goes well I will also venture to deep learning to see how we can apply the same concepts to neural networks.
At its core, the concept is rather simple: Ensemble learning algorithms combine the predictions of multiple models trained on the whole dataset or multiple samples using different techniques for aggregating the results.
By using ensemble methods we have a more general and robust solution than by using a…
It is said that above the arch of the gates of life, it lay written the following: “Abandon all hope ye who are born”. Fortunately no one knows how to read at that point so here we are, falling together, after the very first step we took.
From the moment we are born we begin to fall through time, the destination becoming clearer and clearer as time passes. In that newly found desperation we try to find something to cling to, we want to find a certainty from which we can build ourselves.
And for a time we fall peacefully…
In this article I am going to explain several important python concepts and present their usage. They are very useful in the daily life of a python engineer and are very likely to be found in almost any python interviewer repertoire of question in one form or another.
The basic idea of a generator is that it allows you to create a function that has the same behavior as an iterator but without the boiler plate that comes with it.
If for an iterator we have to create a whole new class that implements the __next__ and __iter__…
Inspired by the existing virtual assistants like Alexa, Google Home or Echo I wanted to create a similar application that was easy customizable and extensible. Of course I know that there is a lot of work and research behind the aforementioned products, but a more basic virtual assistant type application is still doable.
From a high level perspective there are several requirements:
These days the world is exposed, like a nerve, to a series of harsh truths, that nothing is permanent, there is no certainty, our governments are mostly formed by the “old” and the “blind” and that our democracies are deeply corrupted by demagogy. Of course not all truths are equal or even deserve to be placed in that same sentence, but their validity remains the same and here will serve as base for a lesson that I consider to be important for the years to follow.
Our brain wants to live in a world of certainties and of safety, thus…
For some time now i wanted to take a better look at how gRPC works and try to implement something with it. After a short session of brainstorming i decided to build a face recognition type application that can be run on different machines or at least in different processes and this is where gRPC comes in. …