Maël Fabien

My girlfriend and I were recently looking for a house to buy. Rather than spending time on each of the real-estate websites individually, I decided to build ...

Submitting a first paper to ArXiv

Other

Introduction to Automatic Speech Recognition (ASR)

Speech Processing

Expectation Maximization for Gaussian Mixture Models and Hidden Markov Models

Speech Processing

Illustrating EM for GMMs and HMMs

I recently gave a talk on EM for GMMs and HMMs at EPFL and published the slides here. For the sake of the presentation, I built an interactive web applicatio...

Building a Dash Web application for Data Viz and ML

I recently had to build a Dash web application to illustrate what Dash-Plotly can do. I chose to present some capabilities regarding Data Viz and Machine Lea...

A supervised learning approach to predicting nodes betweenness-centrality in time-varying networks

Criminal Networks

Destabilizing Netorks

Criminal Networks

Autograde, a grading tool for teachers

Many teachers are working from home during COVID-19 crisis, receiving and grading works online. My mother is in this situation. To help her, I built AutoGrad...

Probabilistic Linear Discriminant Analysis (PLDA)

Speech Processing

Structural Analysis of Criminal Network and Predicting Hidden Links using Machine Learning

Criminal Networks

Leveraging side information for speaker identification with the Enron conversational telephone speech collection

Criminal Networks

Disrupting Resilient criminal networks through data analysis

Criminal Networks

Basics of Speaker Verification

Speech Processing

COVID-19 in Senegal Live application

Due to the lack of regularly updated database of COVID-19 cases in Senegal, I decided to build an open database and a web application to display this informa...

Fundamental Speech Processing Papers

Speech Processing

Kaldi for Speaker Verification

Speech Processing

Introduction to Kaldi

Speech Processing

Voice Gender Identification

Signal Processing

Voice Gender Identification

Can we detect the gender of a voice using ML methods? I recently came across this article which I found quite interesting in the way it addresses Gender Iden...

Voice Activity Detection Application

Voice activity detection is a field which consists in identifying whether someone is speaking or not at a given moment. It can be useful to launch a vocal as...

2019

Interview by DataCast

Thoughts

Implementing YoloV3 for object detection

Yolo is one of the greatest algorithm for real-time object detection. In its large version, it can detect thousands of object types in a quick and efficient ...

Sound Feature Extraction

Signal Processing

Voice Computing in Python

Signal Processing

Introduction to Digital Signal Processing

Signal Processing

Introduction to Continuous Signal Processing

Signal Processing

Voice Activity Detection

Speech Processing

Sound Visualization

Signal Processing

Introduction to Continuous Signal Processing

Signal Processing

Easy Question Answering with AllenNLP

AllenNLP is an Apache 2.0 NLP research library, built on PyTorch, for developing state-of-the-art deep learning models on a wide variety of linguistic tasks....

Implementing YoloV3 for object detection

Computer Vision

Easy Question Answering with AllenNLP

Natural Language Processing

Speaker Verification using I-vector features

Speech Processing

Speaker Verification using SVM-based methods

Speech Processing

Speaker Verification using Gaussian Mixture Model (GMM-UBM)

Speech Processing

Deploy a container on GCP

In the previous article, we managed to build a container from a simple web application using Spacy, Streamlit and Docker. We ran the container locally. In th...

Deploy a Streamlit WebApp with Docker

Deploying your model in an interactive web application as a container can be challenging. Well, at least it used to. In this project, I will show you how to ...

Traitement Automatique du Langage Naturel en Français (TAL)

Stat4Decision

Data Augmentation in Natural Language Processing

Natural Language Processing

Character-Level LSTMs for Gender Classification from Name

Natural Language Processing

Modéliser la distribution de données avec Python (Distribution Fitting)

Stat4Decision

Improved Few-Shot Text classification

Natural Language Processing

Text classification from few training examples

Natural Language Processing

Planning by Dynamic Programming

Advanced AI

Markov Decision Process

Advanced AI

Introduction to Reinforcement Learning

Advanced AI

I trained a Network to Speak Like Me (and it’s funny)

Natural Language Processing

Emotion Recognition WebApp

We developped a multimodal emotion recognition platform to analyze the emotions of job candidates, in partnership with the French Employment Agency.

A No-SQL Big Data project from scratch

The GDELT Project monitors the world’s broadcast, print, and web news from nearly every corner of every country in over 100 languages and identifies the peop...

Face Detection

In this tutorial, we’ll see how to create and launch a face detection algorithm in Python using OpenCV. We’ll also add some features to detect eyes and mouth...

I trained a Network to Speak Like Me

Over the course of the past months, I wrote over 100 articles on my blog. That’s quite a large amount of content. An idea then came to my mind : train a lang...

A guide to Data Acquisition

Applied Data Science

Predicting the next hit song (Part 2)

Applied Data Science

Predicting the next hit song (Part 1)

Applied Data Science

Who’s the painter ?

In this article, we will be using data from the Web Gallery of Art, a virtual museum and searchable database of European fine arts from the \(3^{rd}\) to \(1...

Interactive Map with D3.js

I developped an interactive D3.js plot of the population density of France. The tool highlights dense regions of France, and has a zoom feature.

How do Neural Networks learn ?

Deep Learning with PyTorch

Activation Functions

Deep Learning with PyTorch

Making your code production-ready

Tips & Tricks

Full introduction to Neural Nets

Deep Learning with PyTorch

Anomaly Detection

Supervise and Unsupervised Algorithms

Run jobs on Dataproc - Week 1 Module 2

Road to Google Cloud Platform Certification

Lab - Create a Cloud DataProc Cluster

Road to Google Cloud Platform Certification

Introduction to Cloud Dataproc - Week 1 Module 1

Road to Google Cloud Platform Certification

Handle Missing Values in Time Series

Time Series

Time Series Forecasting with Prophet

Time Series

Create a streaming data pipeline with Cloud DataFlow

In this project, we will analyze data from a taxi business. The aim of the lab is to : Connect to a streaming data Topic in Cloud Pub/sub Ingest streami...

Lab - Create a streaming data pipeline with Cloud DataFlow

Road to Google Cloud Platform Certification

Create Streaming Data Pipelines - Week 2 Module 1

Road to Google Cloud Platform Certification

Basic Time Series Forecasting

Time Series

Run ML models in SQL with BigQuery ML - Week 1 Module 3

Road to Google Cloud Platform Certification

Lab - Recommend products using Cloud SQL and SparkML

Road to Google Cloud Platform Certification

Lab - Running a Apache Spark job on Cloud DataProc

Road to Google Cloud Platform Certification

Lab - Classify Images with Pre-Built ML models using Cloud Vision and AutoML

Road to Google Cloud Platform Certification

Classify Images using Vision API and Cloud AutoML - Week 2 Module 2

Road to Google Cloud Platform Certification

Using OpenPose on macOS

“OpenPose represents the first real-time multi-person system to jointly detect human body, hand, facial, and foot key points (in total 135 keypoints) on sing...

Earthquake Analysis on GCP

In this project, our aim will be to create a VM instance to process real earthquake data and make the analysis publicly available.

Recommendation Systems in GCP - Week 1 Module 2

Road to Google Cloud Platform Certification

Introduction to Google Cloud Platform - Week 1 Module 1

Road to Google Cloud Platform Certification

Explore a dataset on Google BigQuery

Storing and querying massive datasets can be time-consuming and expensive without the right hardware and infrastructure. Google BigQuery is an enterprise dat...

Lab - Explore a BigQuery Public Dataset

Road to Google Cloud Platform Certification

Lab - VM and Storage for Earthquake Data

Road to Google Cloud Platform Certification

A Guide to Hyperparameter Optimization (HPO)

Parameters and Model Optimization

Interactive Data Visualization

For a recent project, I developped an interactive data visualization tool that was deployed on a web app. The corresponding GitHub repository can be found he...

Container Dwell Time prediction

More than 80% of the goods consumed worldwide are transported in containers. The invention of the container is no less than the greatest revolution in our mo...

The phylosophy game in Wikipedia

According to ReadWriteWeb, all articles in the English version of Wikipedia lead to the article “Philosophy”. If you click on the first link of each article,...

Graph Embedding

Graph Analysis and Graph Learning

Estimate location using RSSI

Smart devices such as IoT sensors use low energy consuming networks such as the ones provided by Sigfox or Lora. But without using GPS networks, it becomes h...

Face Classification using XCeption

In this challenge, our aim was to develop face classification algorithms using Deep Learning Architectures. I have explored hand-made CNNs, Inception, XCepti...

Automated Graphs with Visual Recommendation Systems

Data Viz

NLP on GitHub comments

The dataset I am using in this project (github_comments.tsv) that carries 4000 comments that were published on pull requests on Github by developer teams.

Interpretability and explainability (2/2)

Better ML

Interpretability and explainability (1/2)

Better ML

Grid Search vs. Randomized Search

Advanced Machine Learning

Machine Learning Explainability

Advanced Machine Learning

Who’s the painter ?

Better features, better data

Introduction to Natural Language Processing

Natural Language Processing

Using Spark-Scala for Machine Learning

Parallel and Distributed Computing

Install Spark-Scala and PySpark

Parallel and Distributed Computing

Introduction to Spark

Parallel and Distributed Computing

Introduction to Bash Scripting

Tips & Tricks

Execute MapReduce Job in Python locally

Parallel and Distributed Computing

Linear Classification

Advanced Machine Learning

Introduction to Online Learning

Advanced Machine Learning

Introduction to D3.js

Data Viz

Create Ubuntu VMs with Virtual Box

Hadoop runs only on GNU/Linux platforms. Therefore, if you have another OS, you need to install Virtual Box. Virtual Box is a software that lets you create a...

Virtual Machines with Virtual Box

Parallel and Distributed Computing

MapReduce Jobs in Python (4/4)

Parallel and Distributed Computing

Launch a MapReduce Job (3/4)

Parallel and Distributed Computing

Hadoop with the HortonWorks Sandbox (1/4)

Parallel and Distributed Computing

Load and move files to HDFS (2/4)

Parallel and Distributed Computing

Introduction to Hadoop

Parallel and Distributed Computing

MapReduce, Illustrated

Parallel and Distributed Computing

Hadoop Distributed File System (HDFS)

Parallel and Distributed Computing

Bayesian Hyperparameter Optimization

Parameters and Model Optimization

AutoML with h2o

Parameters and Model Optimization

Gradient Boosting Classification

Supervised Learning Algorithms

Gradient Boosting Regression

Supervised Learning Algorithms

Key Concepts of Data Visualization

Data Viz

Tableau-like in Python with Altair

Data Viz

Binary output prediction and Logistic Regression

Logistic Regression

Build a Language Recognition app

In this project, we will build a language recognition app using Markov Chains and likelihood decoding algorithm. If you have not seen my previous articles on...

Build a Language Recognition app from scratch

Markov Processes and HMM

Hidden Markov Model (HMM)

Markov Processes and HMM

Markov Processes

Markov Processes and HMM

Word Embedding with Skip-Gram Word2Vec

Natural Language Processing

From text to vectors with BoW and TF-IDF

Natural Language Processing

Text Preprocessing

Natural Language Processing

Graph Learning

Graph Analysis and Graph Learning

Key Concepts of Time Series

Time Series

Introduction to Time Series

Time Series

XCeption Model and Depthwise Separable Convolutions

Deep Neural Networks

AWS Cloud Practitioner - Core Services

Amazon Web Services

AWS Cloud Practitioner - Core Services

Amazon Web Services

Key Computer Components

Parallel and Distributed Computing

AWS Cloud Practitioner - Cloud Concepts

Amazon Web Services

A day at the Neo4J GraphTour

Neo4J

Introduction to Graph Database

Neo4J

Graph Algorithms

Graph Analysis and Graph Learning

Graph Analysis

Graph Analysis and Graph Learning

Introduction to Graphs

Graph Analysis and Graph Learning

Image Alignment and Image Warping

Computer Vision

Local features, Detection, Description and Matching

Computer Vision

Image subsampling and downsampling

Computer Vision

Image formation and Filtering

Computer Vision

Large Scale Kernel Methods

Supervised Learning Algorithms

Forest Type Prediction

In this challenge, I am trying to predict the forest cover type (the predominant kind of tree cover) from strictly cartographic variables (as opposed to remo...

Introduction to Computer Vision

Computer Vision

Create an Auto-Encoder

Autoencoder is a type a neural network widely used for unsupervised dimension reduction. So, how does it work? What can it be used for? And how do we impleme...