# Jean-Christophe Bianic

## 190 Added | 10 Magazines | 1 Like | @JeanChristo3q68 | Data Scientist.

### Spotify’s Discover Weekly: How machine learning finds your new music

The science behind personalized music recommendations<p>This Monday — just like every Monday— over 100 million Spotify users found a fresh new playlist …

### 1 year doing data science in the real world

The most important lessons I’ve learned so far<p>Ok, so it’s actually 14 months but it didn’t have the same ring to it as “1 year”. I’ve spent that 14 …

Data Science### A Wake-Up Call For Tech Managers

“Don’t you have a loop to write?”The most popular article I’ve written is called <i>Why your programmer just wants to code.</i> To date it has received over …

Emerging Technology### Baidu Apollo Releases Massive Self-driving Dataset; Teams Up With Berkeley DeepDrive

Baidu this Thursday announced the release of ApolloScape, billed as the world’s largest open-source dataset for autonomous driving …

Machine Learning### A Radical, And Simple, Approach To Product Prioritization

How Do You Decide What Belongs In Your Product?<p>Ironically, the biggest threat to getting things done: is knowing what to get done. In our book …

Product Management### A guide to receptive field arithmetic for Convolutional Neural Networks

The <b>receptive field</b> is perhaps one of the most important concepts in Convolutional Neural Networks (CNNs) that deserves more attention from the …

Deep Learning### Using Q-Learning to teach a robot how to walk — A.I. Odyssey part. 3

In this episode: Q-Values, Reinforcement learning, and more.<i><br>Make sure to check out</i><b></b> <b>part. 1</b><b></b> <i>and</i><b></b> <b>part. 2</b><b></b> <i>too!</i>IntroductionToday, we’re gonna learn how to …

Machine Learning### Accuracy, Precision, Recall or F1?

Which metrics to choose?Often when I talk to organizations that are looking to implement data science into their processes, they often ask the …

Data Science### Data science with Python: Turn your conditional loops to Numpy vectors

Vectorization trick is fairly well-known to data scientists and is used routinely in coding, to speed up the overall data transformation, where …

Data Science### From Python to Numpy

Introduction<p>Code vectorization means that the problem you're trying to solve is inherently vectorizable and only requires a few NumPy tricks to make …

Python Programming### How to Build a Real-time Hand-Detector using Neural Networks (SSD) on Tensorflow

If you are <b>not</b> interested in the process of training the detector, you can skip straight to the section on applying the model to detect hands.<p>Bambach, …

Deep Learning### Introduction to Recommender System. Part 1 (Collaborative Filtering, Singular Value Decomposition)

2. Traditional Approach<p>Traditionally, there are two methods to construct a recommender system :<p><b>Content-based recommendation</b>• <b><br>Collaborative Filtering</b><p>The …

Data Science### Using Machine Learning to Explore Neural Network Architecture

Posted by Quoc Le & Barret Zoph, Research Scientists, Google Brain team<br>At Google, we have successfully applied deep learning models to many …

Machine Learning### Deep Learning for Object Detection: A Comprehensive Review

With the rise of autonomous vehicles, smart video surveillance, facial detection and various people counting applications, fast and accurate object …

### Auto-Regressive Generative Models (PixelRNN, PixelCNN++)

Generative models are a subset of unsupervised learning wherein given some training data we generate new samples/data from the same distribution. …

### Welcoming the Era of Deep Neuroevolution

By leveraging neuroevolution to train deep neural networks, Uber AI Labs is developing solutions to solve reinforcement learning problems.The post …

Machine Learning### Evolution Strategies as a Scalable Alternative to Reinforcement Learning

We've discovered that <b>evolution strategies (ES)</b>, an optimization technique that's been known for decades, rivals the performance of standard</b> …

Deep Learning### Understanding GRU networks

In this article, I will try to give a fairly simple and understandable explanation of one really fascinating type of neural network. Introduced by …

Deep Learning### Estimating an Optimal Learning Rate For a Deep Neural Network

The learning rate is one of the most important hyper-parameters to tune for training deep neural networks.<p>In this post, I’m describing a simple and …

Deep Learning### An overview of gradient descent optimization algorithms

Note: If you are looking for a review paper, this blog post is also available as an article on arXiv.Update 15.06.2017: Added derivations of AdaMax …

Deep Learning### Demystifying “Matrix Capsules with EM Routing.” Part 1: Overview

Recently, Geoffrey Hinton, one of the fathers of deep learning, made waves in the machine learning community by publishing a revolutionary computer …

Deep Learning### Introduction to Bayesian Thinking: from Bayes theorem to Bayes networks

Suppose that in the world exist a very rare disease. There is only 1 in 1000 chance that you have the disease. You want to know <i>whether</i> you are …

Data Science### Gradient descent vs. neuroevolution

In March 2017, OpenAI released a blog post on evolution strategies, an optimisation technique that has been around for several decades. The novelty …

Machine Learning### Local outlier factor

In anomaly detection, the <b>local outlier factor</b> (<b>LOF</b>) is an algorithm proposed by Markus M. Breunig, Hans-Peter Kriegel, Raymond T. Ng and Jörg Sander …

### How to Generate Music using a LSTM Neural Network in Keras

We start by loading each file into a Music21 stream object using the <i>converter.parse(file)</i> function<i>.</i> Using that stream object we get a list of all the …

Deep Learning### Transfer Learning using differential learning rates

In this post, I will be sharing how one can use popular deep learning models for their own specific task using transfer learning. We will cover some …

Machine Learning### UpMem lève 3 millions d’euros pour traiter le big data 20 fois plus vite

La pépite grenobloise UpMem boucle un tour de table de 3 millions d’euros. De quoi achever le développement de sa puce destinée à accélérer les …

Big Data### Deep Learning & Medical Diagnosis

Over the last few months, there have been a number of announcements of research findings that claim that deep learning has been applied to, and often …

Machine Learning