Jean-Christophe Bianic

307 Flips | 17 Magazines | 1 Like | @JeanChristo3q68 | Data Scientist.

Building Scikit-Learn Pipelines With Pandas DataFrames

You’ll notice that the transformation pipeline above is quite general. Most Pipelines, whether they be classification or regression problems, require …

Data Science

How to construct valuable data science projects in the real world

Lessons learned by making several mistakesIntroductionMost articles about how to “complete” a data science <b>task</b> usually discuss how to write an …

Data Science

The Camera IS The Lidar

It was clear when Ouster started developing the OS-1 three years ago that deep learning research for cameras was outpacing lidar research. Lidar data …

Deep Learning

Visualizing Geographic Statistical Data with Google Maps

This tutorial will teach you how to create a custom Google Maps based map for visualizing geographic statistical data. Such maps can be a useful tool …

Maps

AI for cybersecurity is a hot new thing—and a dangerous gamble - MIT Technology Review

Machine learning and artificial intelligence can help guard against cyberattacks, but hackers can foil security algorithms by targeting the data they …

Machine Learning

Five books every data scientist should read that are not about data science

I wrote my first line of R code in 2010 for a class at the University of Washington (UW). Once I realized how much more powerful coding is than …

Data Science

Routing Multiple Vehicles Cooperatively: Minimizing Road Network Breakdown Probability

For IEEE to continue sending you helpful information on our products and services, please consent to our updated Privacy Policy.

Un nouvel algorithme permet d’éviter les embouteillages dans n’importe quelle mégalopole

Pour que le système fonctionne, il suffit que 10% des véhicules soient connectés au réseau d'optimisation d'itinéraire.<p>Le trafic routier est sans doute le domaine où l'irrationalité humaine fait le plus de dégâts. Nous construisons toujours plus de voies de circulation autour des villes, en gardant …

‘The Beginning of a Wave’: A.I. Tiptoes Into the Workplace

There is no shortage of predictions about how artificial intelligence is going to reshape where, how and if people work in the future.<p>But the grand work-changing projects of A.I., like self-driving cars and humanoid robots, are not yet commercial products. A more humble version of the technology, …

Bots

When Bots Teach Themselves to Cheat

Once upon a time, a bot deep in a game of tic-tac-toe figured out that making improbable moves caused its bot opponent to crash. Smart. Also …

Artificial Intelligence

Understanding OpenAI Five

In this blog ( my first blog on medium o_o ), I will explain the challenges in making a Dota bot, appreciate how OpenAI addressed these challenges, …

Fine-tuning XGBoost in Python like a boss

XGBoost (or e<b>X</b>teme <b>G</b>radient <b>Boost</b>ing) is not to be introduced anymore, proved relevant in only too many data science competitions, is still one model …

Don’t Use Dropout in Convolutional Networks.

If you are wondering how to implement dropout, here is your answer.I have noticed that there is an abundance of resources for learning the what and …

Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data

The Most Complete List of Best AI Cheat Sheets<p>Over the past few months, I have been collecting AI cheat sheets. From time to time I share them with …

Machine Learning

30 Amazing Machine Learning Projects for the Past Year (v.2018)

<b>For the past year</b>, we’ve compared nearly 8,800 open source Machine Learning projects to pick Top 30 (0.3% chance).<p>This is an extremely competitive …

Fingerprinting fraudulent behavior

Using neural networks to gobble up the trail of breadcrumbs left by fraudsters<i>You’re a Lyft driver and you’ve just accepted a ride. You start making</i> …

Deep Learning

Learn ML Algorithms by coding: Decision Trees

<b>Since the focus is on learning the algorithms, efficiency is not given priority. At places, I have even traded off efficiency for explainability</b><p><b>Me</b>: …

Learning Math for Machine Learning

<i>Vincent Chen is a student at Stanford University studying Computer Science. He is also a Research Assistant at the Stanford AI Lab.</i>It’s not entirely …

Deploying Keras Deep Learning Models with Flask

Source: Wikimedia CommonsThis post demonstrates how to set up an endpoint to serve predictions using a deep learning model built with Keras. It first …

Data Science Leaders: There are too many of you

Data science has a problem. Several problems, actually, but to begin at the beginning, let’s start with one: leadership.Today I spoke at a summit for …

Top 10 roles in AI and data science

When you think of the perfect data science team, are you imagining 10 copies of the same professor of computer science and statistics, hands …

GluonNLP: a Deep Learning Toolkit for Natural Language Processing (NLP) — gluonnlp 0.3.1 documentation

GluonNLP: a Deep Learning Toolkit for Natural Language Processing (NLP)¶<p>GluonNLP provides implementations of the state-of-the-art (SOTA) deep …

How to build a deep learning model in 15 minutes – tech-at

<i>An open source framework for configuring, building, deploying and maintaining deep learning models in Python.</i><p>As Instacart has grown, we’ve learned a …

22 nuggets of wisdom to structure your machine learning project

Completing a machine learning project is hard. This summary helps you structure your machine learning project.<p>This post examines the third course of …

A Tour of The Top 10 Algorithms for Machine Learning Newbies

In machine learning, there’s something called the “No Free Lunch” theorem. In a nutshell, it states that no one algorithm works best for every …

Machine Learning

AutoGraph converts Python into TensorFlow graphs

By Alex Wiltschko, Dan Moldovan, Wolff Dobson<p>We’d like to tell you about a new TensorFlow feature called “AutoGraph”. AutoGraph converts Python code, …

AI in the Factory of the Future

<b>Focus |</b> Tomorrow’s end-to-end manufacturing AI will think alongside—and sometimes ahead of—human coworkers. But ambitions for the technology far …

Where we’re going, we won’t need real images — Q4 papers

After my first post on medical image segmentation papers (here’s the link), I worked on an update with mostly Q4 papers, based on Google Scholar …

Is There a Smarter Path to Artificial Intelligence? Some Experts Hope So

For the past five years, the hottest thing in artificial intelligence has been a branch known as deep learning. The grandly named statistical technique, put simply, gives computers a way to learn by processing vast amounts of data. Thanks to deep learning, computers can easily identify faces and …

Artificial Intelligence