April 27, 2024

Artificial Intelligence

  • YOLO (Part 4) Reduce detected classes - In this article we will see a trick that reduces the scope of object detection using YOLO v4.
  • YOLO (Part 3) Non Maxima Suppression (NMS) - In my previous articles on YOLO we saw how to use this network ... but when we apply this algorithm on complex images we quickly see that multiple detections are made for the same objects. We will see in this article how to remove these duplicate frames with the so-called NMS technique.
  • YOLO (Part 2) Object detection with YOLO & OpenCV - In this article we will see step by step how to use the YOLO neural network with its implementation in OpenCV. Follow the guide 😉
  • YOLO (Part 1) Introduction with Darknet - We will see in this article, how with the YOLO neural network we can very simply detect several objects in a photo. The objective is not to go into the details of the implementation of this neural network (much more complex than a simple sequential CNN) but rather to show how to use the implementation which was carried out in C ++ and which is called Darknet.
  • Introduction to nlpcloud.io - NLPCloud.io is an API for easily using NLP in production. The API is based on the pre-trained models of spaCy and Hugging Face (based on transformers). In and article we will see how to use this API in a few lines ...
  • Discover Gradio: a simple web UI for your Models - In this tutorial, I invite you to discover a small open source framework that is very easy to set up and use and which will allow you to create an interface for your Machine Learning models. Follow the leader ...
  • Transfer Learning with VGG - In this article we will discuss the concept of Transfer Learning ... or how to avoid redoing long and consuming learning by partially reusing a pre-trained neural network. To do this we will use a network which is the reference in the matter: VGG-Net (vgg16).
  • Fake News ? - I propose in this article to create a convolutional neural network to do NLP, and for the data I will use a dataset that you can simply find in the Kaggle datasets: FrenchFakeNewsDetector. You have understood the objective is twofold: on the one hand to see how we can use the convolution technique with vectors (1 dimension instead of images with 2+ dimensions) and on the other hand to do NLP with data in French.
  • The Stochastic Gradient Descent (SGD) & Learning Rate - When I finished the article on gradient descent, I realized that there were two important points missing. The first concerns the stochastic approach when we have too large data sets, the second being to see very concretely what happens when we poorly choose the value of the learning rate. I will therefore take advantage of this article to finally continue the previous article 😉
  • The Gradient Descent - How to talk about Machine Learning or even Deep Learning without addressing the - famous - gradient descent? There are many articles on this subject of course, but often you have to read several in order to fully understand all the mechanisms. Often too mathematical or not enough, I will try especially here to explain its operation smoothly and step by step in order to try to demystify the subject.

Data Preparation

  • dataprep.eda: a newcomer in data analysis - In this article I show you how to use the new arrival of data analysis with Python: datapre.eda
  • Explore your data with DataExplore - Discover in this article how to use the Open Source DataExplore tool to visualize and even manipulate your data.
  • Analyze your data with Pandas-profiling - Analyze your data effortlessly with the pandas_profiling Python library.
  • Strings Comparison - Find out in this article how to use distance algorithms and the Fuzzywuzzy library to compare strings.
  • Get started with Tesseract - 122/5000 Interested in OCRs? learn how to use Tesseract (Open Source OCR) from the command line but also via Python.
  • Preparing the datasets - preparing the datasets in a Machine Learning project is a very important step that should not be neglected, otherwise you risk over evaluating your model (over-fitting) or quite simply the opposite (under fitting). In this article we will go through the essential steps for this delicate operation.
  • Variables correlation - This article shows you how to detect links between observation variables.
  • Orange Data Science Tool - Discover in this article in the form of a tutorial how this small Open-Source Data-science tool can save you a lot of time!
  • Bag of Words - To follow up on my article on the management of character strings, here is a first part which will allow us to have a progressive approach to the processing of this type of data. Far from any semantic approach (which will be the subject of a later post) we will discuss here the technique of bags of words
  • Managing string character - If you want to have an analytical approach to your data, you have of course been faced with the difficulty of using character strings. So much so that very often you have certainly had to put some aside. Lack of tools, complexity of managing complex semantics ... In this article (first in a series) we will tackle these problems and especially see how to solve them.

Modeling

  • The Stochastic Gradient Descent (SGD) & Learning Rate - When I finished the article on gradient descent, I realized that there were two important points missing. The first concerns the stochastic approach when we have too large data sets, the second being to see very concretely what happens when we poorly choose the value of the learning rate. I will therefore take advantage of this article to finally continue the previous article 😉
  • The Gradient Descent - How to talk about Machine Learning or even Deep Learning without addressing the - famous - gradient descent? There are many articles on this subject of course, but often you have to read several in order to fully understand all the mechanisms. Often too mathematical or not enough, I will try especially here to explain its operation smoothly and step by step in order to try to demystify the subject.
  • Bias & Variance… dilemma or compromise? - As soon as you begin to create machine learning models, you will be faced with the delicate problem of balance in the adjustment of bias and variance. In this article I try to simply explain how understand these two very important concepts.
  • Markov chains - If this method of "prediction" based on probabilities and states / transitions had its heyday, it now seems less fashionable. In this article we will come back to the fundamentals of Markov chains and their application in Python.
  • Sentiment analysis on movie reviews - The purpose of this article is to show through a concrete and French case the method to perform a sentiment analysis with Python.
  • Getting started in Auto-ML with AutoGluon - Discover Auto-ML with AutoGluon. Simple accelerator or real revolution in the way of creating machine learning models? get an idea by doing ...
  • Keras to the rescue of the Titanic? - In this article we will see by practice if deep learning via keras can help us find Titanic survivors more efficiently than traditional algorithms.
  • Publish your Machine Learning models with Flask! - In this article we will see how to install and especially use the Python Flask micro-framework. very useful for publishing your Machine learning models in REST!
  • The persistence of machine learning models - In this short article you will see how in a few lines of Python code you can save your model and recall it.
  • CatBoost ! - Discover in this article how to use the latest open-source gradient boosting algorithms: the CatBoost!

Machine Learning

Deep Learning

  • YOLO (Part 4) Reduce detected classes - In this article we will see a trick that reduces the scope of object detection using YOLO v4.
  • YOLO (Part 3) Non Maxima Suppression (NMS) - In my previous articles on YOLO we saw how to use this network ... but when we apply this algorithm on complex images we quickly see that multiple detections are made for the same objects. We will see in this article how to remove these duplicate frames with the so-called NMS technique.
  • YOLO (Part 2) Object detection with YOLO & OpenCV - In this article we will see step by step how to use the YOLO neural network with its implementation in OpenCV. Follow the guide 😉
  • YOLO (Part 1) Introduction with Darknet - We will see in this article, how with the YOLO neural network we can very simply detect several objects in a photo. The objective is not to go into the details of the implementation of this neural network (much more complex than a simple sequential CNN) but rather to show how to use the implementation which was carried out in C ++ and which is called Darknet.
  • Transfer Learning with VGG - In this article we will discuss the concept of Transfer Learning ... or how to avoid redoing long and consuming learning by partially reusing a pre-trained neural network. To do this we will use a network which is the reference in the matter: VGG-Net (vgg16).
  • Fake News ? - I propose in this article to create a convolutional neural network to do NLP, and for the data I will use a dataset that you can simply find in the Kaggle datasets: FrenchFakeNewsDetector. You have understood the objective is twofold: on the one hand to see how we can use the convolution technique with vectors (1 dimension instead of images with 2+ dimensions) and on the other hand to do NLP with data in French.
  • Image processing (part 7) Convolution Neural Networks – CNN - In this article we will see step by step how to create and use a convolutional neural network (CNN) to classify images.
  • Understanding Neural Networks with Tensorflow Playground - In this article, I suggest you discover a brilliant tool that allows you to better understand how a neural network works and the real impact of its main settings.
  • Getting started in Auto-ML with AutoGluon - Discover Auto-ML with AutoGluon. Simple accelerator or real revolution in the way of creating machine learning models? get an idea by doing ...
  • Keras to the rescue of the Titanic? - In this article we will see by practice if deep learning via keras can help us find Titanic survivors more efficiently than traditional algorithms.

NLP

  • Introduction to nlpcloud.io - NLPCloud.io is an API for easily using NLP in production. The API is based on the pre-trained models of spaCy and Hugging Face (based on transformers). In and article we will see how to use this API in a few lines ...
  • Sentiment analysis on movie reviews - The purpose of this article is to show through a concrete and French case the method to perform a sentiment analysis with Python.
  • NLP with Python NLTK - Find out in this article how to do NLP simply with Python and NLTK.
  • Tutorial: Just do NLP with SpaCy! - Discover in a simple and progressive approach how to do NLP simply with the SpaCy Python library!

Tools


Fork me on GitHub